[0-9]+)\.'
- _TEST = {
- 'url': 'http://minhateca.com.br/pereba/misc/youtube-dl+test+video,125848331.mp4(video)',
- 'info_dict': {
- 'id': '125848331',
- 'ext': 'mp4',
- 'title': 'youtube-dl test video',
- 'thumbnail': r're:^https?://.*\.jpg$',
- 'filesize_approx': 1530000,
- 'duration': 9,
- 'view_count': int,
- }
- }
-
- def _real_extract(self, url):
- video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
-
- token = self._html_search_regex(
- r'(.*?)', webpage, 'title')
- title, _, ext = title_str.rpartition('.')
- filesize_approx = parse_filesize(self._html_search_regex(
- r'(.*?)
',
- webpage, 'file size approximation', fatal=False))
- duration = parse_duration(self._html_search_regex(
- r'(?s).*?class="bold">(.*?)<',
- webpage, 'duration', fatal=False))
- view_count = int_or_none(self._html_search_regex(
- r'
([0-9]+)
',
- webpage, 'view count', fatal=False))
-
- return {
- 'id': video_id,
- 'url': video_url,
- 'title': title,
- 'ext': ext,
- 'filesize_approx': filesize_approx,
- 'duration': duration,
- 'view_count': view_count,
- 'thumbnail': self._og_search_thumbnail(webpage),
- }
diff --git a/youtube_dl/extractor/mit.py b/youtube_dl/extractor/mit.py
index 1aea78d11..e1506a745 100644
--- a/youtube_dl/extractor/mit.py
+++ b/youtube_dl/extractor/mit.py
@@ -65,30 +65,6 @@ class TechTVMITIE(InfoExtractor):
}
-class MITIE(TechTVMITIE):
- IE_NAME = 'video.mit.edu'
- _VALID_URL = r'https?://video\.mit\.edu/watch/(?P[^/]+)'
-
- _TEST = {
- 'url': 'http://video.mit.edu/watch/the-government-is-profiling-you-13222/',
- 'md5': '7db01d5ccc1895fc5010e9c9e13648da',
- 'info_dict': {
- 'id': '21783',
- 'ext': 'mp4',
- 'title': 'The Government is Profiling You',
- 'description': 'md5:ad5795fe1e1623b73620dbfd47df9afd',
- },
- }
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- page_title = mobj.group('title')
- webpage = self._download_webpage(url, page_title)
- embed_url = self._search_regex(
- r'<iframe .*?src="(.+?)"', webpage, 'embed url')
- return self.url_result(embed_url)
-
-
class OCWMITIE(InfoExtractor):
IE_NAME = 'ocw.mit.edu'
_VALID_URL = r'^https?://ocw\.mit\.edu/courses/(?P<topic>[a-z0-9\-]+)'
diff --git a/youtube_dl/extractor/mitele.py b/youtube_dl/extractor/mitele.py
index 40f214a87..ad9da9612 100644
--- a/youtube_dl/extractor/mitele.py
+++ b/youtube_dl/extractor/mitele.py
@@ -4,8 +4,8 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
+ parse_iso8601,
smuggle_url,
- parse_duration,
)
@@ -18,16 +18,18 @@ class MiTeleIE(InfoExtractor):
'info_dict': {
'id': 'FhYW1iNTE6J6H7NkQRIEzfne6t2quqPg',
'ext': 'mp4',
- 'title': 'Tor, la web invisible',
- 'description': 'md5:3b6fce7eaa41b2d97358726378d9369f',
+ 'title': 'Diario de La redacción Programa 144',
+ 'description': 'md5:07c35a7b11abb05876a6a79185b58d27',
'series': 'Diario de',
- 'season': 'La redacción',
+ 'season': 'Season 14',
'season_number': 14,
- 'season_id': 'diario_de_t14_11981',
- 'episode': 'Programa 144',
+ 'episode': 'Tor, la web invisible',
'episode_number': 3,
'thumbnail': r're:(?i)^https?://.*\.jpg$',
'duration': 2913,
+ 'age_limit': 16,
+ 'timestamp': 1471209401,
+ 'upload_date': '20160814',
},
'add_ie': ['Ooyala'],
}, {
@@ -39,13 +41,15 @@ class MiTeleIE(InfoExtractor):
'title': 'Cuarto Milenio Temporada 6 Programa 226',
'description': 'md5:5ff132013f0cd968ffbf1f5f3538a65f',
'series': 'Cuarto Milenio',
- 'season': 'Temporada 6',
+ 'season': 'Season 6',
'season_number': 6,
- 'season_id': 'cuarto_milenio_t06_12715',
- 'episode': 'Programa 226',
+ 'episode': 'Episode 24',
'episode_number': 24,
'thumbnail': r're:(?i)^https?://.*\.jpg$',
'duration': 7313,
+ 'age_limit': 12,
+ 'timestamp': 1471209021,
+ 'upload_date': '20160814',
},
'params': {
'skip_download': True,
@@ -54,67 +58,36 @@ class MiTeleIE(InfoExtractor):
}, {
'url': 'http://www.mitele.es/series-online/la-que-se-avecina/57aac5c1c915da951a8b45ed/player',
'only_matching': True,
+ }, {
+ 'url': 'https://www.mitele.es/programas-tv/diario-de/la-redaccion/programa-144-40_1006364575251/player/',
+ 'only_matching': True,
}]
def _real_extract(self, url):
- video_id = self._match_id(url)
-
- paths = self._download_json(
- 'https://www.mitele.es/amd/agp/web/metadata/general_configuration',
- video_id, 'Downloading paths JSON')
-
- ooyala_s = paths['general_configuration']['api_configuration']['ooyala_search']
- base_url = ooyala_s.get('base_url', 'cdn-search-mediaset.carbyne.ps.ooyala.com')
- full_path = ooyala_s.get('full_path', '/search/v1/full/providers/')
- source = self._download_json(
- '%s://%s%s%s/docs/%s' % (
- ooyala_s.get('protocol', 'https'), base_url, full_path,
- ooyala_s.get('provider_id', '104951'), video_id),
- video_id, 'Downloading data JSON', query={
- 'include_titles': 'Series,Season',
- 'product_name': ooyala_s.get('product_name', 'test'),
- 'format': 'full',
- })['hits']['hits'][0]['_source']
-
- embedCode = source['offers'][0]['embed_codes'][0]
- titles = source['localizable_titles'][0]
-
- title = titles.get('title_medium') or titles['title_long']
-
- description = titles.get('summary_long') or titles.get('summary_medium')
-
- def get(key1, key2):
- value1 = source.get(key1)
- if not value1 or not isinstance(value1, list):
- return
- if not isinstance(value1[0], dict):
- return
- return value1[0].get(key2)
-
- series = get('localizable_titles_series', 'title_medium')
-
- season = get('localizable_titles_season', 'title_medium')
- season_number = int_or_none(source.get('season_number'))
- season_id = source.get('season_id')
-
- episode = titles.get('title_sort_name')
- episode_number = int_or_none(source.get('episode_number'))
-
- duration = parse_duration(get('videos', 'duration'))
+ display_id = self._match_id(url)
+ webpage = self._download_webpage(url, display_id)
+ pre_player = self._parse_json(self._search_regex(
+ r'window\.\$REACTBASE_STATE\.prePlayer_mtweb\s*=\s*({.+})',
+ webpage, 'Pre Player'), display_id)['prePlayer']
+ title = pre_player['title']
+ video = pre_player['video']
+ video_id = video['dataMediaId']
+ content = pre_player.get('content') or {}
+ info = content.get('info') or {}
return {
'_type': 'url_transparent',
# for some reason only HLS is supported
- 'url': smuggle_url('ooyala:' + embedCode, {'supportedformats': 'm3u8,dash'}),
+ 'url': smuggle_url('ooyala:' + video_id, {'supportedformats': 'm3u8,dash'}),
'id': video_id,
'title': title,
- 'description': description,
- 'series': series,
- 'season': season,
- 'season_number': season_number,
- 'season_id': season_id,
- 'episode': episode,
- 'episode_number': episode_number,
- 'duration': duration,
- 'thumbnail': get('images', 'url'),
+ 'description': info.get('synopsis'),
+ 'series': content.get('title'),
+ 'season_number': int_or_none(info.get('season_number')),
+ 'episode': content.get('subtitle'),
+ 'episode_number': int_or_none(info.get('episode_number')),
+ 'duration': int_or_none(info.get('duration')),
+ 'thumbnail': video.get('dataPoster'),
+ 'age_limit': int_or_none(info.get('rating')),
+ 'timestamp': parse_iso8601(pre_player.get('publishedTime')),
}
diff --git a/youtube_dl/extractor/mixcloud.py b/youtube_dl/extractor/mixcloud.py
index bcac13ec5..9759560f1 100644
--- a/youtube_dl/extractor/mixcloud.py
+++ b/youtube_dl/extractor/mixcloud.py
@@ -1,6 +1,5 @@
from __future__ import unicode_literals
-import functools
import itertools
import re
@@ -11,28 +10,37 @@ from ..compat import (
compat_ord,
compat_str,
compat_urllib_parse_unquote,
- compat_urlparse,
compat_zip
)
from ..utils import (
- clean_html,
- ExtractorError,
int_or_none,
- OnDemandPagedList,
- str_to_int,
+ parse_iso8601,
+ strip_or_none,
try_get,
- urljoin,
)
-class MixcloudIE(InfoExtractor):
+class MixcloudBaseIE(InfoExtractor):
+ def _call_api(self, object_type, object_fields, display_id, username, slug=None):
+ lookup_key = object_type + 'Lookup'
+ return self._download_json(
+ 'https://www.mixcloud.com/graphql', display_id, query={
+ 'query': '''{
+ %s(lookup: {username: "%s"%s}) {
+ %s
+ }
+}''' % (lookup_key, username, ', slug: "%s"' % slug if slug else '', object_fields)
+ })['data'][lookup_key]
+
+
+class MixcloudIE(MixcloudBaseIE):
_VALID_URL = r'https?://(?:(?:www|beta|m)\.)?mixcloud\.com/([^/]+)/(?!stream|uploads|favorites|listens|playlists)([^/]+)'
IE_NAME = 'mixcloud'
_TESTS = [{
'url': 'http://www.mixcloud.com/dholbach/cryptkeeper/',
'info_dict': {
- 'id': 'dholbach-cryptkeeper',
+ 'id': 'dholbach_cryptkeeper',
'ext': 'm4a',
'title': 'Cryptkeeper',
'description': 'After quite a long silence from myself, finally another Drum\'n\'Bass mix with my favourite current dance floor bangers.',
@@ -40,11 +48,13 @@ class MixcloudIE(InfoExtractor):
'uploader_id': 'dholbach',
'thumbnail': r're:https?://.*\.jpg',
'view_count': int,
+ 'timestamp': 1321359578,
+ 'upload_date': '20111115',
},
}, {
'url': 'http://www.mixcloud.com/gillespeterson/caribou-7-inch-vinyl-mix-chat/',
'info_dict': {
- 'id': 'gillespeterson-caribou-7-inch-vinyl-mix-chat',
+ 'id': 'gillespeterson_caribou-7-inch-vinyl-mix-chat',
'ext': 'mp3',
'title': 'Caribou 7 inch Vinyl Mix & Chat',
'description': 'md5:2b8aec6adce69f9d41724647c65875e8',
@@ -52,11 +62,14 @@ class MixcloudIE(InfoExtractor):
'uploader_id': 'gillespeterson',
'thumbnail': 're:https?://.*',
'view_count': int,
+ 'timestamp': 1422987057,
+ 'upload_date': '20150203',
},
}, {
'url': 'https://beta.mixcloud.com/RedLightRadio/nosedrip-15-red-light-radio-01-18-2016/',
'only_matching': True,
}]
+ _DECRYPTION_KEY = 'IFYOUWANTTHEARTISTSTOGETPAIDDONOTDOWNLOADFROMMIXCLOUD'
@staticmethod
def _decrypt_xor_cipher(key, ciphertext):
@@ -66,176 +79,193 @@ class MixcloudIE(InfoExtractor):
for ch, k in compat_zip(ciphertext, itertools.cycle(key))])
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- uploader = mobj.group(1)
- cloudcast_name = mobj.group(2)
- track_id = compat_urllib_parse_unquote('-'.join((uploader, cloudcast_name)))
+ username, slug = re.match(self._VALID_URL, url).groups()
+ username, slug = compat_urllib_parse_unquote(username), compat_urllib_parse_unquote(slug)
+ track_id = '%s_%s' % (username, slug)
- webpage = self._download_webpage(url, track_id)
+ cloudcast = self._call_api('cloudcast', '''audioLength
+ comments(first: 100) {
+ edges {
+ node {
+ comment
+ created
+ user {
+ displayName
+ username
+ }
+ }
+ }
+ totalCount
+ }
+ description
+ favorites {
+ totalCount
+ }
+ featuringArtistList
+ isExclusive
+ name
+ owner {
+ displayName
+ url
+ username
+ }
+ picture(width: 1024, height: 1024) {
+ url
+ }
+ plays
+ publishDate
+ reposts {
+ totalCount
+ }
+ streamInfo {
+ dashUrl
+ hlsUrl
+ url
+ }
+ tags {
+ tag {
+ name
+ }
+ }''', track_id, username, slug)
- # Legacy path
- encrypted_play_info = self._search_regex(
- r'm-play-info="([^"]+)"', webpage, 'play info', default=None)
+ title = cloudcast['name']
- if encrypted_play_info is not None:
- # Decode
- encrypted_play_info = compat_b64decode(encrypted_play_info)
- else:
- # New path
- full_info_json = self._parse_json(self._html_search_regex(
- r'<script id="relay-data" type="text/x-mixcloud">([^<]+)</script>',
- webpage, 'play info'), 'play info')
- for item in full_info_json:
- item_data = try_get(
- item, lambda x: x['cloudcast']['data']['cloudcastLookup'],
- dict)
- if try_get(item_data, lambda x: x['streamInfo']['url']):
- info_json = item_data
- break
- else:
- raise ExtractorError('Failed to extract matching stream info')
+ stream_info = cloudcast['streamInfo']
+ formats = []
- message = self._html_search_regex(
- r'(?s)<div[^>]+class="global-message cloudcast-disabled-notice-light"[^>]*>(.+?)<(?:a|/div)',
- webpage, 'error message', default=None)
-
- js_url = self._search_regex(
- r'<script[^>]+\bsrc=["\"](https://(?:www\.)?mixcloud\.com/media/(?:js2/www_js_4|js/www)\.[^>]+\.js)',
- webpage, 'js url')
- js = self._download_webpage(js_url, track_id, 'Downloading JS')
- # Known plaintext attack
- if encrypted_play_info:
- kps = ['{"stream_url":']
- kpa_target = encrypted_play_info
- else:
- kps = ['https://', 'http://']
- kpa_target = compat_b64decode(info_json['streamInfo']['url'])
- for kp in kps:
- partial_key = self._decrypt_xor_cipher(kpa_target, kp)
- for quote in ["'", '"']:
- key = self._search_regex(
- r'{0}({1}[^{0}]*){0}'.format(quote, re.escape(partial_key)),
- js, 'encryption key', default=None)
- if key is not None:
- break
- else:
+ for url_key in ('url', 'hlsUrl', 'dashUrl'):
+ format_url = stream_info.get(url_key)
+ if not format_url:
continue
- break
- else:
- raise ExtractorError('Failed to extract encryption key')
+ decrypted = self._decrypt_xor_cipher(
+ self._DECRYPTION_KEY, compat_b64decode(format_url))
+ if url_key == 'hlsUrl':
+ formats.extend(self._extract_m3u8_formats(
+ decrypted, track_id, 'mp4', entry_protocol='m3u8_native',
+ m3u8_id='hls', fatal=False))
+ elif url_key == 'dashUrl':
+ formats.extend(self._extract_mpd_formats(
+ decrypted, track_id, mpd_id='dash', fatal=False))
+ else:
+ formats.append({
+ 'format_id': 'http',
+ 'url': decrypted,
+ 'downloader_options': {
+ # Mixcloud starts throttling at >~5M
+ 'http_chunk_size': 5242880,
+ },
+ })
- if encrypted_play_info is not None:
- play_info = self._parse_json(self._decrypt_xor_cipher(key, encrypted_play_info), 'play info')
- if message and 'stream_url' not in play_info:
- raise ExtractorError('%s said: %s' % (self.IE_NAME, message), expected=True)
- song_url = play_info['stream_url']
- formats = [{
- 'format_id': 'normal',
- 'url': song_url
- }]
+ if not formats and cloudcast.get('isExclusive'):
+ self.raise_login_required()
- title = self._html_search_regex(r'm-title="([^"]+)"', webpage, 'title')
- thumbnail = self._proto_relative_url(self._html_search_regex(
- r'm-thumbnail-url="([^"]+)"', webpage, 'thumbnail', fatal=False))
- uploader = self._html_search_regex(
- r'm-owner-name="([^"]+)"', webpage, 'uploader', fatal=False)
- uploader_id = self._search_regex(
- r'\s+"profile": "([^"]+)",', webpage, 'uploader id', fatal=False)
- description = self._og_search_description(webpage)
- view_count = str_to_int(self._search_regex(
- [r'<meta itemprop="interactionCount" content="UserPlays:([0-9]+)"',
- r'/listeners/?">([0-9,.]+)</a>',
- r'(?:m|data)-tooltip=["\']([\d,.]+) plays'],
- webpage, 'play count', default=None))
+ self._sort_formats(formats)
- else:
- title = info_json['name']
- thumbnail = urljoin(
- 'https://thumbnailer.mixcloud.com/unsafe/600x600/',
- try_get(info_json, lambda x: x['picture']['urlRoot'], compat_str))
- uploader = try_get(info_json, lambda x: x['owner']['displayName'])
- uploader_id = try_get(info_json, lambda x: x['owner']['username'])
- description = try_get(info_json, lambda x: x['description'])
- view_count = int_or_none(try_get(info_json, lambda x: x['plays']))
+ comments = []
+ for edge in (try_get(cloudcast, lambda x: x['comments']['edges']) or []):
+ node = edge.get('node') or {}
+ text = strip_or_none(node.get('comment'))
+ if not text:
+ continue
+ user = node.get('user') or {}
+ comments.append({
+ 'author': user.get('displayName'),
+ 'author_id': user.get('username'),
+ 'text': text,
+ 'timestamp': parse_iso8601(node.get('created')),
+ })
- stream_info = info_json['streamInfo']
- formats = []
+ tags = []
+ for t in cloudcast.get('tags'):
+ tag = try_get(t, lambda x: x['tag']['name'], compat_str)
+ if not tag:
+ tags.append(tag)
- def decrypt_url(f_url):
- for k in (key, 'IFYOUWANTTHEARTISTSTOGETPAIDDONOTDOWNLOADFROMMIXCLOUD'):
- decrypted_url = self._decrypt_xor_cipher(k, f_url)
- if re.search(r'^https?://[0-9a-z.]+/[0-9A-Za-z/.?=&_-]+$', decrypted_url):
- return decrypted_url
+ get_count = lambda x: int_or_none(try_get(cloudcast, lambda y: y[x]['totalCount']))
- for url_key in ('url', 'hlsUrl', 'dashUrl'):
- format_url = stream_info.get(url_key)
- if not format_url:
- continue
- decrypted = decrypt_url(compat_b64decode(format_url))
- if not decrypted:
- continue
- if url_key == 'hlsUrl':
- formats.extend(self._extract_m3u8_formats(
- decrypted, track_id, 'mp4', entry_protocol='m3u8_native',
- m3u8_id='hls', fatal=False))
- elif url_key == 'dashUrl':
- formats.extend(self._extract_mpd_formats(
- decrypted, track_id, mpd_id='dash', fatal=False))
- else:
- formats.append({
- 'format_id': 'http',
- 'url': decrypted,
- 'downloader_options': {
- # Mixcloud starts throttling at >~5M
- 'http_chunk_size': 5242880,
- },
- })
- self._sort_formats(formats)
+ owner = cloudcast.get('owner') or {}
return {
'id': track_id,
'title': title,
'formats': formats,
- 'description': description,
- 'thumbnail': thumbnail,
- 'uploader': uploader,
- 'uploader_id': uploader_id,
- 'view_count': view_count,
+ 'description': cloudcast.get('description'),
+ 'thumbnail': try_get(cloudcast, lambda x: x['picture']['url'], compat_str),
+ 'uploader': owner.get('displayName'),
+ 'timestamp': parse_iso8601(cloudcast.get('publishDate')),
+ 'uploader_id': owner.get('username'),
+ 'uploader_url': owner.get('url'),
+ 'duration': int_or_none(cloudcast.get('audioLength')),
+ 'view_count': int_or_none(cloudcast.get('plays')),
+ 'like_count': get_count('favorites'),
+ 'repost_count': get_count('reposts'),
+ 'comment_count': get_count('comments'),
+ 'comments': comments,
+ 'tags': tags,
+ 'artist': ', '.join(cloudcast.get('featuringArtistList') or []) or None,
}
-class MixcloudPlaylistBaseIE(InfoExtractor):
- _PAGE_SIZE = 24
+class MixcloudPlaylistBaseIE(MixcloudBaseIE):
+ def _get_cloudcast(self, node):
+ return node
- def _find_urls_in_page(self, page):
- for url in re.findall(r'm-play-button m-url="(?P<url>[^"]+)"', page):
- yield self.url_result(
- compat_urlparse.urljoin('https://www.mixcloud.com', clean_html(url)),
- MixcloudIE.ie_key())
+ def _get_playlist_title(self, title, slug):
+ return title
- def _fetch_tracks_page(self, path, video_id, page_name, current_page, real_page_number=None):
- real_page_number = real_page_number or current_page + 1
- return self._download_webpage(
- 'https://www.mixcloud.com/%s/' % path, video_id,
- note='Download %s (page %d)' % (page_name, current_page + 1),
- errnote='Unable to download %s' % page_name,
- query={'page': real_page_number, 'list': 'main', '_ajax': '1'},
- headers={'X-Requested-With': 'XMLHttpRequest'})
+ def _real_extract(self, url):
+ username, slug = re.match(self._VALID_URL, url).groups()
+ username = compat_urllib_parse_unquote(username)
+ if not slug:
+ slug = 'uploads'
+ else:
+ slug = compat_urllib_parse_unquote(slug)
+ playlist_id = '%s_%s' % (username, slug)
- def _tracks_page_func(self, page, video_id, page_name, current_page):
- resp = self._fetch_tracks_page(page, video_id, page_name, current_page)
+ is_playlist_type = self._ROOT_TYPE == 'playlist'
+ playlist_type = 'items' if is_playlist_type else slug
+ list_filter = ''
- for item in self._find_urls_in_page(resp):
- yield item
+ has_next_page = True
+ entries = []
+ while has_next_page:
+ playlist = self._call_api(
+ self._ROOT_TYPE, '''%s
+ %s
+ %s(first: 100%s) {
+ edges {
+ node {
+ %s
+ }
+ }
+ pageInfo {
+ endCursor
+ hasNextPage
+ }
+ }''' % (self._TITLE_KEY, self._DESCRIPTION_KEY, playlist_type, list_filter, self._NODE_TEMPLATE),
+ playlist_id, username, slug if is_playlist_type else None)
- def _get_user_description(self, page_content):
- return self._html_search_regex(
- r'<div[^>]+class="profile-bio"[^>]*>(.+?)</div>',
- page_content, 'user description', fatal=False)
+ items = playlist.get(playlist_type) or {}
+ for edge in items.get('edges', []):
+ cloudcast = self._get_cloudcast(edge.get('node') or {})
+ cloudcast_url = cloudcast.get('url')
+ if not cloudcast_url:
+ continue
+ entries.append(self.url_result(
+ cloudcast_url, MixcloudIE.ie_key(), cloudcast.get('slug')))
+
+ page_info = items['pageInfo']
+ has_next_page = page_info['hasNextPage']
+ list_filter = ', after: "%s"' % page_info['endCursor']
+
+ return self.playlist_result(
+ entries, playlist_id,
+ self._get_playlist_title(playlist[self._TITLE_KEY], slug),
+ playlist.get(self._DESCRIPTION_KEY))
class MixcloudUserIE(MixcloudPlaylistBaseIE):
- _VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P<user>[^/]+)/(?P<type>uploads|favorites|listens)?/?$'
+ _VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P<id>[^/]+)/(?P<type>uploads|favorites|listens|stream)?/?$'
IE_NAME = 'mixcloud:user'
_TESTS = [{
@@ -243,68 +273,58 @@ class MixcloudUserIE(MixcloudPlaylistBaseIE):
'info_dict': {
'id': 'dholbach_uploads',
'title': 'Daniel Holbach (uploads)',
- 'description': 'md5:def36060ac8747b3aabca54924897e47',
+ 'description': 'md5:b60d776f0bab534c5dabe0a34e47a789',
},
- 'playlist_mincount': 11,
+ 'playlist_mincount': 36,
}, {
'url': 'http://www.mixcloud.com/dholbach/uploads/',
'info_dict': {
'id': 'dholbach_uploads',
'title': 'Daniel Holbach (uploads)',
- 'description': 'md5:def36060ac8747b3aabca54924897e47',
+ 'description': 'md5:b60d776f0bab534c5dabe0a34e47a789',
},
- 'playlist_mincount': 11,
+ 'playlist_mincount': 36,
}, {
'url': 'http://www.mixcloud.com/dholbach/favorites/',
'info_dict': {
'id': 'dholbach_favorites',
'title': 'Daniel Holbach (favorites)',
- 'description': 'md5:def36060ac8747b3aabca54924897e47',
+ 'description': 'md5:b60d776f0bab534c5dabe0a34e47a789',
},
- 'params': {
- 'playlist_items': '1-100',
- },
- 'playlist_mincount': 100,
+ # 'params': {
+ # 'playlist_items': '1-100',
+ # },
+ 'playlist_mincount': 396,
}, {
'url': 'http://www.mixcloud.com/dholbach/listens/',
'info_dict': {
'id': 'dholbach_listens',
'title': 'Daniel Holbach (listens)',
- 'description': 'md5:def36060ac8747b3aabca54924897e47',
+ 'description': 'md5:b60d776f0bab534c5dabe0a34e47a789',
},
- 'params': {
- 'playlist_items': '1-100',
+ # 'params': {
+ # 'playlist_items': '1-100',
+ # },
+ 'playlist_mincount': 1623,
+ 'skip': 'Large list',
+ }, {
+ 'url': 'https://www.mixcloud.com/FirstEar/stream/',
+ 'info_dict': {
+ 'id': 'FirstEar_stream',
+ 'title': 'First Ear (stream)',
+ 'description': 'Curators of good music\r\n\r\nfirstearmusic.com',
},
- 'playlist_mincount': 100,
+ 'playlist_mincount': 271,
}]
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- user_id = mobj.group('user')
- list_type = mobj.group('type')
+ _TITLE_KEY = 'displayName'
+ _DESCRIPTION_KEY = 'biog'
+ _ROOT_TYPE = 'user'
+ _NODE_TEMPLATE = '''slug
+ url'''
- # if only a profile URL was supplied, default to download all uploads
- if list_type is None:
- list_type = 'uploads'
-
- video_id = '%s_%s' % (user_id, list_type)
-
- profile = self._download_webpage(
- 'https://www.mixcloud.com/%s/' % user_id, video_id,
- note='Downloading user profile',
- errnote='Unable to download user profile')
-
- username = self._og_search_title(profile)
- description = self._get_user_description(profile)
-
- entries = OnDemandPagedList(
- functools.partial(
- self._tracks_page_func,
- '%s/%s' % (user_id, list_type), video_id, 'list of %s' % list_type),
- self._PAGE_SIZE)
-
- return self.playlist_result(
- entries, video_id, '%s (%s)' % (username, list_type), description)
+ def _get_playlist_title(self, title, slug):
+ return '%s (%s)' % (title, slug)
class MixcloudPlaylistIE(MixcloudPlaylistBaseIE):
@@ -312,87 +332,20 @@ class MixcloudPlaylistIE(MixcloudPlaylistBaseIE):
IE_NAME = 'mixcloud:playlist'
_TESTS = [{
- 'url': 'https://www.mixcloud.com/RedBullThre3style/playlists/tokyo-finalists-2015/',
- 'info_dict': {
- 'id': 'RedBullThre3style_tokyo-finalists-2015',
- 'title': 'National Champions 2015',
- 'description': 'md5:6ff5fb01ac76a31abc9b3939c16243a3',
- },
- 'playlist_mincount': 16,
- }, {
'url': 'https://www.mixcloud.com/maxvibes/playlists/jazzcat-on-ness-radio/',
- 'only_matching': True,
- }]
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- user_id = mobj.group('user')
- playlist_id = mobj.group('playlist')
- video_id = '%s_%s' % (user_id, playlist_id)
-
- webpage = self._download_webpage(
- url, user_id,
- note='Downloading playlist page',
- errnote='Unable to download playlist page')
-
- title = self._html_search_regex(
- r'<a[^>]+class="parent active"[^>]*><b>\d+</b><span[^>]*>([^<]+)',
- webpage, 'playlist title',
- default=None) or self._og_search_title(webpage, fatal=False)
- description = self._get_user_description(webpage)
-
- entries = OnDemandPagedList(
- functools.partial(
- self._tracks_page_func,
- '%s/playlists/%s' % (user_id, playlist_id), video_id, 'tracklist'),
- self._PAGE_SIZE)
-
- return self.playlist_result(entries, video_id, title, description)
-
-
-class MixcloudStreamIE(MixcloudPlaylistBaseIE):
- _VALID_URL = r'https?://(?:www\.)?mixcloud\.com/(?P<id>[^/]+)/stream/?$'
- IE_NAME = 'mixcloud:stream'
-
- _TEST = {
- 'url': 'https://www.mixcloud.com/FirstEar/stream/',
'info_dict': {
- 'id': 'FirstEar',
- 'title': 'First Ear',
- 'description': 'Curators of good music\nfirstearmusic.com',
+ 'id': 'maxvibes_jazzcat-on-ness-radio',
+ 'title': 'Ness Radio sessions',
},
- 'playlist_mincount': 192,
- }
+ 'playlist_mincount': 59,
+ }]
+ _TITLE_KEY = 'name'
+ _DESCRIPTION_KEY = 'description'
+ _ROOT_TYPE = 'playlist'
+ _NODE_TEMPLATE = '''cloudcast {
+ slug
+ url
+ }'''
- def _real_extract(self, url):
- user_id = self._match_id(url)
-
- webpage = self._download_webpage(url, user_id)
-
- entries = []
- prev_page_url = None
-
- def _handle_page(page):
- entries.extend(self._find_urls_in_page(page))
- return self._search_regex(
- r'm-next-page-url="([^"]+)"', page,
- 'next page URL', default=None)
-
- next_page_url = _handle_page(webpage)
-
- for idx in itertools.count(0):
- if not next_page_url or prev_page_url == next_page_url:
- break
-
- prev_page_url = next_page_url
- current_page = int(self._search_regex(
- r'\?page=(\d+)', next_page_url, 'next page number'))
-
- next_page_url = _handle_page(self._fetch_tracks_page(
- '%s/stream' % user_id, user_id, 'stream', idx,
- real_page_number=current_page))
-
- username = self._og_search_title(webpage)
- description = self._get_user_description(webpage)
-
- return self.playlist_result(entries, user_id, username, description)
+ def _get_cloudcast(self, node):
+ return node.get('cloudcast') or {}
diff --git a/youtube_dl/extractor/msn.py b/youtube_dl/extractor/msn.py
index 0460cf4d5..e59b0b7b0 100644
--- a/youtube_dl/extractor/msn.py
+++ b/youtube_dl/extractor/msn.py
@@ -14,20 +14,27 @@ from ..utils import (
class MSNIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?msn\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/[a-z]{2}-(?P<id>[\da-zA-Z]+)'
+ _VALID_URL = r'https?://(?:(?:www|preview)\.)?msn\.com/(?:[^/]+/)+(?P<display_id>[^/]+)/[a-z]{2}-(?P<id>[\da-zA-Z]+)'
_TESTS = [{
- 'url': 'http://www.msn.com/en-ae/foodanddrink/joinourtable/criminal-minds-shemar-moore-shares-a-touching-goodbye-message/vp-BBqQYNE',
- 'md5': '8442f66c116cbab1ff7098f986983458',
+ 'url': 'https://www.msn.com/en-in/money/video/7-ways-to-get-rid-of-chest-congestion/vi-BBPxU6d',
+ 'md5': '087548191d273c5c55d05028f8d2cbcd',
'info_dict': {
- 'id': 'BBqQYNE',
- 'display_id': 'criminal-minds-shemar-moore-shares-a-touching-goodbye-message',
+ 'id': 'BBPxU6d',
+ 'display_id': '7-ways-to-get-rid-of-chest-congestion',
'ext': 'mp4',
- 'title': 'Criminal Minds - Shemar Moore Shares A Touching Goodbye Message',
- 'description': 'md5:e8e89b897b222eb33a6b5067a8f1bc25',
- 'duration': 104,
- 'uploader': 'CBS Entertainment',
- 'uploader_id': 'IT0X5aoJ6bJgYerJXSDCgFmYPB1__54v',
+ 'title': 'Seven ways to get rid of chest congestion',
+ 'description': '7 Ways to Get Rid of Chest Congestion',
+ 'duration': 88,
+ 'uploader': 'Health',
+ 'uploader_id': 'BBPrMqa',
},
+ }, {
+ # Article, multiple Dailymotion Embeds
+ 'url': 'https://www.msn.com/en-in/money/sports/hottest-football-wags-greatest-footballers-turned-managers-and-more/ar-BBpc7Nl',
+ 'info_dict': {
+ 'id': 'BBpc7Nl',
+ },
+ 'playlist_mincount': 4,
}, {
'url': 'http://www.msn.com/en-ae/news/offbeat/meet-the-nine-year-old-self-made-millionaire/ar-BBt6ZKf',
'only_matching': True,
@@ -41,75 +48,124 @@ class MSNIE(InfoExtractor):
}, {
'url': 'http://www.msn.com/en-ae/entertainment/bollywood/watch-how-salman-khan-reacted-when-asked-if-he-would-apologize-for-his-‘raped-woman’-comment/vi-AAhvzW6',
'only_matching': True,
+ }, {
+ # Vidible(AOL) Embed
+ 'url': 'https://www.msn.com/en-us/money/other/jupiter-is-about-to-come-so-close-you-can-see-its-moons-with-binoculars/vi-AACqsHR',
+ 'only_matching': True,
+ }, {
+ # Dailymotion Embed
+ 'url': 'https://www.msn.com/es-ve/entretenimiento/watch/winston-salem-paire-refait-des-siennes-en-perdant-sa-raquette-au-service/vp-AAG704L',
+ 'only_matching': True,
+ }, {
+ # YouTube Embed
+ 'url': 'https://www.msn.com/en-in/money/news/meet-vikram-%E2%80%94-chandrayaan-2s-lander/vi-AAGUr0v',
+ 'only_matching': True,
+ }, {
+ # NBCSports Embed
+ 'url': 'https://www.msn.com/en-us/money/football_nfl/week-13-preview-redskins-vs-panthers/vi-BBXsCDb',
+ 'only_matching': True,
}]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- video_id, display_id = mobj.group('id', 'display_id')
+ display_id, page_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, display_id)
- video = self._parse_json(
- self._search_regex(
- r'data-metadata\s*=\s*(["\'])(?P<data>.+?)\1',
- webpage, 'video data', default='{}', group='data'),
- display_id, transform_source=unescapeHTML)
+ entries = []
+ for _, metadata in re.findall(r'data-metadata\s*=\s*(["\'])(?P<data>.+?)\1', webpage):
+ video = self._parse_json(unescapeHTML(metadata), display_id)
- if not video:
+ provider_id = video.get('providerId')
+ player_name = video.get('playerName')
+ if player_name and provider_id:
+ entry = None
+ if player_name == 'AOL':
+ if provider_id.startswith('http'):
+ provider_id = self._search_regex(
+ r'https?://delivery\.vidible\.tv/video/redirect/([0-9a-f]{24})',
+ provider_id, 'vidible id')
+ entry = self.url_result(
+ 'aol-video:' + provider_id, 'Aol', provider_id)
+ elif player_name == 'Dailymotion':
+ entry = self.url_result(
+ 'https://www.dailymotion.com/video/' + provider_id,
+ 'Dailymotion', provider_id)
+ elif player_name == 'YouTube':
+ entry = self.url_result(
+ provider_id, 'Youtube', provider_id)
+ elif player_name == 'NBCSports':
+ entry = self.url_result(
+ 'http://vplayer.nbcsports.com/p/BxmELC/nbcsports_embed/select/media/' + provider_id,
+ 'NBCSportsVPlayer', provider_id)
+ if entry:
+ entries.append(entry)
+ continue
+
+ video_id = video['uuid']
+ title = video['title']
+
+ formats = []
+ for file_ in video.get('videoFiles', []):
+ format_url = file_.get('url')
+ if not format_url:
+ continue
+ if 'format=m3u8-aapl' in format_url:
+ # m3u8_native should not be used here until
+ # https://github.com/ytdl-org/youtube-dl/issues/9913 is fixed
+ formats.extend(self._extract_m3u8_formats(
+ format_url, display_id, 'mp4',
+ m3u8_id='hls', fatal=False))
+ elif 'format=mpd-time-csf' in format_url:
+ formats.extend(self._extract_mpd_formats(
+ format_url, display_id, 'dash', fatal=False))
+ elif '.ism' in format_url:
+ if format_url.endswith('.ism'):
+ format_url += '/manifest'
+ formats.extend(self._extract_ism_formats(
+ format_url, display_id, 'mss', fatal=False))
+ else:
+ format_id = file_.get('formatCode')
+ formats.append({
+ 'url': format_url,
+ 'ext': 'mp4',
+ 'format_id': format_id,
+ 'width': int_or_none(file_.get('width')),
+ 'height': int_or_none(file_.get('height')),
+ 'vbr': int_or_none(self._search_regex(r'_(\d+)\.mp4', format_url, 'vbr', default=None)),
+ 'preference': 1 if format_id == '1001' else None,
+ })
+ self._sort_formats(formats)
+
+ subtitles = {}
+ for file_ in video.get('files', []):
+ format_url = file_.get('url')
+ format_code = file_.get('formatCode')
+ if not format_url or not format_code:
+ continue
+ if compat_str(format_code) == '3100':
+ subtitles.setdefault(file_.get('culture', 'en'), []).append({
+ 'ext': determine_ext(format_url, 'ttml'),
+ 'url': format_url,
+ })
+
+ entries.append({
+ 'id': video_id,
+ 'display_id': display_id,
+ 'title': title,
+ 'description': video.get('description'),
+ 'thumbnail': video.get('headlineImage', {}).get('url'),
+ 'duration': int_or_none(video.get('durationSecs')),
+ 'uploader': video.get('sourceFriendly'),
+ 'uploader_id': video.get('providerId'),
+ 'creator': video.get('creator'),
+ 'subtitles': subtitles,
+ 'formats': formats,
+ })
+
+ if not entries:
error = unescapeHTML(self._search_regex(
r'data-error=(["\'])(?P<error>.+?)\1',
webpage, 'error', group='error'))
raise ExtractorError('%s said: %s' % (self.IE_NAME, error), expected=True)
- title = video['title']
-
- formats = []
- for file_ in video.get('videoFiles', []):
- format_url = file_.get('url')
- if not format_url:
- continue
- if 'm3u8' in format_url:
- # m3u8_native should not be used here until
- # https://github.com/ytdl-org/youtube-dl/issues/9913 is fixed
- m3u8_formats = self._extract_m3u8_formats(
- format_url, display_id, 'mp4',
- m3u8_id='hls', fatal=False)
- formats.extend(m3u8_formats)
- elif determine_ext(format_url) == 'ism':
- formats.extend(self._extract_ism_formats(
- format_url + '/Manifest', display_id, 'mss', fatal=False))
- else:
- formats.append({
- 'url': format_url,
- 'ext': 'mp4',
- 'format_id': 'http',
- 'width': int_or_none(file_.get('width')),
- 'height': int_or_none(file_.get('height')),
- })
- self._sort_formats(formats)
-
- subtitles = {}
- for file_ in video.get('files', []):
- format_url = file_.get('url')
- format_code = file_.get('formatCode')
- if not format_url or not format_code:
- continue
- if compat_str(format_code) == '3100':
- subtitles.setdefault(file_.get('culture', 'en'), []).append({
- 'ext': determine_ext(format_url, 'ttml'),
- 'url': format_url,
- })
-
- return {
- 'id': video_id,
- 'display_id': display_id,
- 'title': title,
- 'description': video.get('description'),
- 'thumbnail': video.get('headlineImage', {}).get('url'),
- 'duration': int_or_none(video.get('durationSecs')),
- 'uploader': video.get('sourceFriendly'),
- 'uploader_id': video.get('providerId'),
- 'creator': video.get('creator'),
- 'subtitles': subtitles,
- 'formats': formats,
- }
+ return self.playlist_result(entries, page_id)
diff --git a/youtube_dl/extractor/mtv.py b/youtube_dl/extractor/mtv.py
index 7a3b57abd..fedd5f46b 100644
--- a/youtube_dl/extractor/mtv.py
+++ b/youtube_dl/extractor/mtv.py
@@ -1,3 +1,4 @@
+# coding: utf-8
from __future__ import unicode_literals
import re
@@ -349,33 +350,29 @@ class MTVIE(MTVServicesInfoExtractor):
}]
-class MTV81IE(InfoExtractor):
- IE_NAME = 'mtv81'
- _VALID_URL = r'https?://(?:www\.)?mtv81\.com/videos/(?P<id>[^/?#.]+)'
+class MTVJapanIE(MTVServicesInfoExtractor):
+ IE_NAME = 'mtvjapan'
+ _VALID_URL = r'https?://(?:www\.)?mtvjapan\.com/videos/(?P<id>[0-9a-z]+)'
_TEST = {
- 'url': 'http://www.mtv81.com/videos/artist-to-watch/the-godfather-of-japanese-hip-hop-segment-1/',
- 'md5': '1edbcdf1e7628e414a8c5dcebca3d32b',
+ 'url': 'http://www.mtvjapan.com/videos/prayht/fresh-info-cadillac-escalade',
'info_dict': {
- 'id': '5e14040d-18a4-47c4-a582-43ff602de88e',
+ 'id': 'bc01da03-6fe5-4284-8880-f291f4e368f5',
'ext': 'mp4',
- 'title': 'Unlocking The Truth|July 18, 2016|1|101|Trailer',
- 'description': '"Unlocking the Truth" premieres August 17th at 11/10c.',
- 'timestamp': 1468846800,
- 'upload_date': '20160718',
+ 'title': '【Fresh Info】Cadillac ESCALADE Sport Edition',
+ },
+ 'params': {
+ 'skip_download': True,
},
}
+ _GEO_COUNTRIES = ['JP']
+ _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
- def _extract_mgid(self, webpage):
- return self._search_regex(
- r'getTheVideo\((["\'])(?P<id>mgid:.+?)\1', webpage,
- 'mgid', group='id')
-
- def _real_extract(self, url):
- video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
- mgid = self._extract_mgid(webpage)
- return self.url_result('http://media.mtvnservices.com/embed/%s' % mgid)
+ def _get_feed_query(self, uri):
+ return {
+ 'arcEp': 'mtvjapan.com',
+ 'mgid': uri,
+ }
class MTVVideoIE(MTVServicesInfoExtractor):
@@ -425,14 +422,14 @@ class MTVVideoIE(MTVServicesInfoExtractor):
class MTVDEIE(MTVServicesInfoExtractor):
IE_NAME = 'mtv.de'
- _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:artists|shows|news)/(?:[^/]+/)*(?P<id>\d+)-[^/#?]+/*(?:[#?].*)?$'
+ _VALID_URL = r'https?://(?:www\.)?mtv\.de/(?:musik/videoclips|folgen|news)/(?P<id>[0-9a-z]+)'
_TESTS = [{
- 'url': 'http://www.mtv.de/artists/10571-cro/videos/61131-traum',
+ 'url': 'http://www.mtv.de/musik/videoclips/2gpnv7/Traum',
'info_dict': {
- 'id': 'music_video-a50bc5f0b3aa4b3190aa',
- 'ext': 'flv',
- 'title': 'MusicVideo_cro-traum',
- 'description': 'Cro - Traum',
+ 'id': 'd5d472bc-f5b7-11e5-bffd-a4badb20dab5',
+ 'ext': 'mp4',
+ 'title': 'Traum',
+ 'description': 'Traum',
},
'params': {
# rtmp download
@@ -441,11 +438,12 @@ class MTVDEIE(MTVServicesInfoExtractor):
'skip': 'Blocked at Travis CI',
}, {
# mediagen URL without query (e.g. http://videos.mtvnn.com/mediagen/e865da714c166d18d6f80893195fcb97)
- 'url': 'http://www.mtv.de/shows/933-teen-mom-2/staffeln/5353/folgen/63565-enthullungen',
+ 'url': 'http://www.mtv.de/folgen/6b1ylu/teen-mom-2-enthuellungen-S5-F1',
'info_dict': {
- 'id': 'local_playlist-f5ae778b9832cc837189',
- 'ext': 'flv',
- 'title': 'Episode_teen-mom-2_shows_season-5_episode-1_full-episode_part1',
+ 'id': '1e5a878b-31c5-11e7-a442-0e40cf2fc285',
+ 'ext': 'mp4',
+ 'title': 'Teen Mom 2',
+ 'description': 'md5:dc65e357ef7e1085ed53e9e9d83146a7',
},
'params': {
# rtmp download
@@ -453,7 +451,7 @@ class MTVDEIE(MTVServicesInfoExtractor):
},
'skip': 'Blocked at Travis CI',
}, {
- 'url': 'http://www.mtv.de/news/77491-mtv-movies-spotlight-pixels-teil-3',
+ 'url': 'http://www.mtv.de/news/glolix/77491-mtv-movies-spotlight--pixels--teil-3',
'info_dict': {
'id': 'local_playlist-4e760566473c4c8c5344',
'ext': 'mp4',
@@ -466,25 +464,11 @@ class MTVDEIE(MTVServicesInfoExtractor):
},
'skip': 'Das Video kann zur Zeit nicht abgespielt werden.',
}]
+ _GEO_COUNTRIES = ['DE']
+ _FEED_URL = 'http://feeds.mtvnservices.com/od/feed/intl-mrss-player-feed'
- def _real_extract(self, url):
- video_id = self._match_id(url)
-
- webpage = self._download_webpage(url, video_id)
-
- playlist = self._parse_json(
- self._search_regex(
- r'window\.pagePlaylist\s*=\s*(\[.+?\]);\n', webpage, 'page playlist'),
- video_id)
-
- def _mrss_url(item):
- return item['mrss'] + item.get('mrssvars', '')
-
- # news pages contain single video in playlist with different id
- if len(playlist) == 1:
- return self._get_videos_info_from_url(_mrss_url(playlist[0]), video_id)
-
- for item in playlist:
- item_id = item.get('id')
- if item_id and compat_str(item_id) == video_id:
- return self._get_videos_info_from_url(_mrss_url(item), video_id)
+ def _get_feed_query(self, uri):
+ return {
+ 'arcEp': 'mtv.de',
+ 'mgid': uri,
+ }
diff --git a/youtube_dl/extractor/musicplayon.py b/youtube_dl/extractor/musicplayon.py
deleted file mode 100644
index 1854d59a5..000000000
--- a/youtube_dl/extractor/musicplayon.py
+++ /dev/null
@@ -1,66 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..compat import compat_urlparse
-from ..utils import (
- int_or_none,
- js_to_json,
- mimetype2ext,
-)
-
-
-class MusicPlayOnIE(InfoExtractor):
- _VALID_URL = r'https?://(?:.+?\.)?musicplayon\.com/play(?:-touch)?\?(?:v|pl=\d+&play)=(?P<id>\d+)'
-
- _TESTS = [{
- 'url': 'http://en.musicplayon.com/play?v=433377',
- 'md5': '00cdcdea1726abdf500d1e7fd6dd59bb',
- 'info_dict': {
- 'id': '433377',
- 'ext': 'mp4',
- 'title': 'Rick Ross - Interview On Chelsea Lately (2014)',
- 'description': 'Rick Ross Interview On Chelsea Lately',
- 'duration': 342,
- 'uploader': 'ultrafish',
- },
- }, {
- 'url': 'http://en.musicplayon.com/play?pl=102&play=442629',
- 'only_matching': True,
- }]
-
- _URL_TEMPLATE = 'http://en.musicplayon.com/play?v=%s'
-
- def _real_extract(self, url):
- video_id = self._match_id(url)
- url = self._URL_TEMPLATE % video_id
-
- page = self._download_webpage(url, video_id)
-
- title = self._og_search_title(page)
- description = self._og_search_description(page)
- thumbnail = self._og_search_thumbnail(page)
- duration = self._html_search_meta('video:duration', page, 'duration', fatal=False)
- view_count = self._og_search_property('count', page, fatal=False)
- uploader = self._html_search_regex(
- r'<div>by <a href="[^"]+" class="purple">([^<]+)</a></div>', page, 'uploader', fatal=False)
-
- sources = self._parse_json(
- self._search_regex(r'setup\[\'_sources\'\]\s*=\s*([^;]+);', page, 'video sources'),
- video_id, transform_source=js_to_json)
- formats = [{
- 'url': compat_urlparse.urljoin(url, source['src']),
- 'ext': mimetype2ext(source.get('type')),
- 'format_note': source.get('data-res'),
- } for source in sources]
-
- return {
- 'id': video_id,
- 'title': title,
- 'description': description,
- 'thumbnail': thumbnail,
- 'uploader': uploader,
- 'duration': int_or_none(duration),
- 'view_count': int_or_none(view_count),
- 'formats': formats,
- }
diff --git a/youtube_dl/extractor/myspass.py b/youtube_dl/extractor/myspass.py
index 2afe535b5..db7ebc94c 100644
--- a/youtube_dl/extractor/myspass.py
+++ b/youtube_dl/extractor/myspass.py
@@ -1,73 +1,56 @@
+# coding: utf-8
from __future__ import unicode_literals
-import os.path
+
+import re
from .common import InfoExtractor
-from ..compat import (
- compat_urllib_parse_urlparse,
-)
+from ..compat import compat_str
from ..utils import (
- ExtractorError,
+ int_or_none,
+ parse_duration,
+ xpath_text,
)
class MySpassIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?myspass\.de/.*'
+ _VALID_URL = r'https?://(?:www\.)?myspass\.de/([^/]+/)*(?P<id>\d+)'
_TEST = {
'url': 'http://www.myspass.de/myspass/shows/tvshows/absolute-mehrheit/Absolute-Mehrheit-vom-17022013-Die-Highlights-Teil-2--/11741/',
'md5': '0b49f4844a068f8b33f4b7c88405862b',
'info_dict': {
'id': '11741',
'ext': 'mp4',
- 'description': 'Wer kann in die Fu\u00dfstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?',
- 'title': 'Absolute Mehrheit vom 17.02.2013 - Die Highlights, Teil 2',
+ 'description': 'Wer kann in die Fußstapfen von Wolfgang Kubicki treten und die Mehrheit der Zuschauer hinter sich versammeln? Wird vielleicht sogar die Absolute Mehrheit geknackt und der Jackpot von 200.000 Euro mit nach Hause genommen?',
+ 'title': '17.02.2013 - Die Highlights, Teil 2',
},
}
def _real_extract(self, url):
- META_DATA_URL_TEMPLATE = 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=%s'
+ video_id = self._match_id(url)
- # video id is the last path element of the URL
- # usually there is a trailing slash, so also try the second but last
- url_path = compat_urllib_parse_urlparse(url).path
- url_parent_path, video_id = os.path.split(url_path)
- if not video_id:
- _, video_id = os.path.split(url_parent_path)
-
- # get metadata
- metadata_url = META_DATA_URL_TEMPLATE % video_id
metadata = self._download_xml(
- metadata_url, video_id, transform_source=lambda s: s.strip())
+ 'http://www.myspass.de/myspass/includes/apps/video/getvideometadataxml.php?id=' + video_id,
+ video_id)
- # extract values from metadata
- url_flv_el = metadata.find('url_flv')
- if url_flv_el is None:
- raise ExtractorError('Unable to extract download url')
- video_url = url_flv_el.text
- title_el = metadata.find('title')
- if title_el is None:
- raise ExtractorError('Unable to extract title')
- title = title_el.text
- format_id_el = metadata.find('format_id')
- if format_id_el is None:
- format = 'mp4'
- else:
- format = format_id_el.text
- description_el = metadata.find('description')
- if description_el is not None:
- description = description_el.text
- else:
- description = None
- imagePreview_el = metadata.find('imagePreview')
- if imagePreview_el is not None:
- thumbnail = imagePreview_el.text
- else:
- thumbnail = None
+ title = xpath_text(metadata, 'title', fatal=True)
+ video_url = xpath_text(metadata, 'url_flv', 'download url', True)
+ video_id_int = int(video_id)
+ for group in re.search(r'/myspass2009/\d+/(\d+)/(\d+)/(\d+)/', video_url).groups():
+ group_int = int(group)
+ if group_int > video_id_int:
+ video_url = video_url.replace(
+ group, compat_str(group_int // video_id_int))
return {
'id': video_id,
'url': video_url,
'title': title,
- 'format': format,
- 'thumbnail': thumbnail,
- 'description': description,
+ 'thumbnail': xpath_text(metadata, 'imagePreview'),
+ 'description': xpath_text(metadata, 'description'),
+ 'duration': parse_duration(xpath_text(metadata, 'duration')),
+ 'series': xpath_text(metadata, 'format'),
+ 'season_number': int_or_none(xpath_text(metadata, 'season')),
+ 'season_id': xpath_text(metadata, 'season_id'),
+ 'episode': title,
+ 'episode_number': int_or_none(xpath_text(metadata, 'episode')),
}
diff --git a/youtube_dl/extractor/nbc.py b/youtube_dl/extractor/nbc.py
index 3282f84ee..5bc39d002 100644
--- a/youtube_dl/extractor/nbc.py
+++ b/youtube_dl/extractor/nbc.py
@@ -9,10 +9,13 @@ from .theplatform import ThePlatformIE
from .adobepass import AdobePassIE
from ..compat import compat_urllib_parse_unquote
from ..utils import (
+ int_or_none,
+ js_to_json,
+ parse_duration,
smuggle_url,
try_get,
+ unified_timestamp,
update_url_query,
- int_or_none,
)
@@ -85,27 +88,41 @@ class NBCIE(AdobePassIE):
permalink, video_id = re.match(self._VALID_URL, url).groups()
permalink = 'http' + compat_urllib_parse_unquote(permalink)
response = self._download_json(
- 'https://api.nbc.com/v3/videos', video_id, query={
- 'filter[permalink]': permalink,
- 'fields[videos]': 'description,entitlement,episodeNumber,guid,keywords,seasonNumber,title,vChipRating',
- 'fields[shows]': 'shortTitle',
- 'include': 'show.shortTitle',
+ 'https://friendship.nbc.co/v2/graphql', video_id, query={
+ 'query': '''{
+ page(name: "%s", platform: web, type: VIDEO, userId: "0") {
+ data {
+ ... on VideoPageData {
+ description
+ episodeNumber
+ keywords
+ locked
+ mpxAccountId
+ mpxGuid
+ rating
+ seasonNumber
+ secondaryTitle
+ seriesShortTitle
+ }
+ }
+ }
+}''' % permalink,
})
- video_data = response['data'][0]['attributes']
+ video_data = response['data']['page']['data']
query = {
'mbr': 'true',
'manifest': 'm3u',
}
- video_id = video_data['guid']
- title = video_data['title']
- if video_data.get('entitlement') == 'auth':
+ video_id = video_data['mpxGuid']
+ title = video_data['secondaryTitle']
+ if video_data.get('locked'):
resource = self._get_mvpd_resource(
'nbcentertainment', title, video_id,
- video_data.get('vChipRating'))
+ video_data.get('rating'))
query['auth'] = self._extract_mvpd_auth(
url, video_id, 'nbcentertainment', resource)
theplatform_url = smuggle_url(update_url_query(
- 'http://link.theplatform.com/s/NnzsPC/media/guid/2410887629/' + video_id,
+ 'http://link.theplatform.com/s/NnzsPC/media/guid/%s/%s' % (video_data.get('mpxAccountId') or '2410887629', video_id),
query), {'force_smil_url': True})
return {
'_type': 'url_transparent',
@@ -117,7 +134,7 @@ class NBCIE(AdobePassIE):
'season_number': int_or_none(video_data.get('seasonNumber')),
'episode_number': int_or_none(video_data.get('episodeNumber')),
'episode': title,
- 'series': try_get(response, lambda x: x['included'][0]['attributes']['shortTitle']),
+ 'series': video_data.get('seriesShortTitle'),
'ie_key': 'ThePlatform',
}
@@ -272,13 +289,12 @@ class NBCNewsIE(ThePlatformIE):
_TESTS = [
{
'url': 'http://www.nbcnews.com/watch/nbcnews-com/how-twitter-reacted-to-the-snowden-interview-269389891880',
- 'md5': 'af1adfa51312291a017720403826bb64',
+ 'md5': 'cf4bc9e6ce0130f00f545d80ecedd4bf',
'info_dict': {
'id': '269389891880',
'ext': 'mp4',
'title': 'How Twitter Reacted To The Snowden Interview',
'description': 'md5:65a0bd5d76fe114f3c2727aa3a81fe64',
- 'uploader': 'NBCU-NEWS',
'timestamp': 1401363060,
'upload_date': '20140529',
},
@@ -296,28 +312,26 @@ class NBCNewsIE(ThePlatformIE):
},
{
'url': 'http://www.nbcnews.com/nightly-news/video/nightly-news-with-brian-williams-full-broadcast-february-4-394064451844',
- 'md5': '73135a2e0ef819107bbb55a5a9b2a802',
+ 'md5': '8eb831eca25bfa7d25ddd83e85946548',
'info_dict': {
'id': '394064451844',
'ext': 'mp4',
'title': 'Nightly News with Brian Williams Full Broadcast (February 4)',
'description': 'md5:1c10c1eccbe84a26e5debb4381e2d3c5',
'timestamp': 1423104900,
- 'uploader': 'NBCU-NEWS',
'upload_date': '20150205',
},
},
{
'url': 'http://www.nbcnews.com/business/autos/volkswagen-11-million-vehicles-could-have-suspect-software-emissions-scandal-n431456',
- 'md5': 'a49e173825e5fcd15c13fc297fced39d',
+ 'md5': '4a8c4cec9e1ded51060bdda36ff0a5c0',
'info_dict': {
- 'id': '529953347624',
+ 'id': 'n431456',
'ext': 'mp4',
- 'title': 'Volkswagen U.S. Chief:\xa0 We Have Totally Screwed Up',
- 'description': 'md5:c8be487b2d80ff0594c005add88d8351',
+ 'title': "Volkswagen U.S. Chief: We 'Totally Screwed Up'",
+ 'description': 'md5:d22d1281a24f22ea0880741bb4dd6301',
'upload_date': '20150922',
'timestamp': 1442917800,
- 'uploader': 'NBCU-NEWS',
},
},
{
@@ -330,7 +344,6 @@ class NBCNewsIE(ThePlatformIE):
'description': 'md5:74752b7358afb99939c5f8bb2d1d04b1',
'upload_date': '20160420',
'timestamp': 1461152093,
- 'uploader': 'NBCU-NEWS',
},
},
{
@@ -344,7 +357,6 @@ class NBCNewsIE(ThePlatformIE):
'thumbnail': r're:^https?://.*\.jpg$',
'timestamp': 1406937606,
'upload_date': '20140802',
- 'uploader': 'NBCU-NEWS',
},
},
{
@@ -360,20 +372,61 @@ class NBCNewsIE(ThePlatformIE):
def _real_extract(self, url):
video_id = self._match_id(url)
- if not video_id.isdigit():
- webpage = self._download_webpage(url, video_id)
+ webpage = self._download_webpage(url, video_id)
- data = self._parse_json(self._search_regex(
- r'window\.__data\s*=\s*({.+});', webpage,
- 'bootstrap json'), video_id)
- video_id = data['article']['content'][0]['primaryMedia']['video']['mpxMetadata']['id']
+ data = self._parse_json(self._search_regex(
+ r'window\.__data\s*=\s*({.+});', webpage,
+ 'bootstrap json'), video_id, js_to_json)
+ video_data = try_get(data, lambda x: x['video']['current'], dict)
+ if not video_data:
+ video_data = data['article']['content'][0]['primaryMedia']['video']
+ title = video_data['headline']['primary']
+
+ formats = []
+ for va in video_data.get('videoAssets', []):
+ public_url = va.get('publicUrl')
+ if not public_url:
+ continue
+ if '://link.theplatform.com/' in public_url:
+ public_url = update_url_query(public_url, {'format': 'redirect'})
+ format_id = va.get('format')
+ if format_id == 'M3U':
+ formats.extend(self._extract_m3u8_formats(
+ public_url, video_id, 'mp4', 'm3u8_native',
+ m3u8_id=format_id, fatal=False))
+ continue
+ tbr = int_or_none(va.get('bitrate'), 1000)
+ if tbr:
+ format_id += '-%d' % tbr
+ formats.append({
+ 'format_id': format_id,
+ 'url': public_url,
+ 'width': int_or_none(va.get('width')),
+ 'height': int_or_none(va.get('height')),
+ 'tbr': tbr,
+ 'ext': 'mp4',
+ })
+ self._sort_formats(formats)
+
+ subtitles = {}
+ closed_captioning = video_data.get('closedCaptioning')
+ if closed_captioning:
+ for cc_url in closed_captioning.values():
+ if not cc_url:
+ continue
+ subtitles.setdefault('en', []).append({
+ 'url': cc_url,
+ })
return {
- '_type': 'url_transparent',
'id': video_id,
- # http://feed.theplatform.com/f/2E2eJC/nbcnews also works
- 'url': update_url_query('http://feed.theplatform.com/f/2E2eJC/nnd_NBCNews', {'byId': video_id}),
- 'ie_key': 'ThePlatformFeed',
+ 'title': title,
+ 'description': try_get(video_data, lambda x: x['description']['primary']),
+ 'thumbnail': try_get(video_data, lambda x: x['primaryImage']['url']['primary']),
+ 'duration': parse_duration(video_data.get('duration')),
+ 'timestamp': unified_timestamp(video_data.get('datePublished')),
+ 'formats': formats,
+ 'subtitles': subtitles,
}
diff --git a/youtube_dl/extractor/nexx.py b/youtube_dl/extractor/nexx.py
index 82d526c22..586c1b7eb 100644
--- a/youtube_dl/extractor/nexx.py
+++ b/youtube_dl/extractor/nexx.py
@@ -108,7 +108,7 @@ class NexxIE(InfoExtractor):
@staticmethod
def _extract_domain_id(webpage):
mobj = re.search(
- r'<script\b[^>]+\bsrc=["\'](?:https?:)?//require\.nexx(?:\.cloud|cdn\.com)/(?P<id>\d+)',
+ r'<script\b[^>]+\bsrc=["\'](?:https?:)?//(?:require|arc)\.nexx(?:\.cloud|cdn\.com)/(?:sdk/)?(?P<id>\d+)',
webpage)
return mobj.group('id') if mobj else None
@@ -123,7 +123,7 @@ class NexxIE(InfoExtractor):
domain_id = NexxIE._extract_domain_id(webpage)
if domain_id:
for video_id in re.findall(
- r'(?is)onPLAYReady.+?_play\.init\s*\(.+?\s*,\s*["\']?(\d+)',
+ r'(?is)onPLAYReady.+?_play\.(?:init|(?:control\.)?addPlayer)\s*\(.+?\s*,\s*["\']?(\d+)',
webpage):
entries.append(
'https://api.nexx.cloud/v3/%s/videos/byid/%s'
@@ -295,13 +295,23 @@ class NexxIE(InfoExtractor):
video = None
+ def find_video(result):
+ if isinstance(result, dict):
+ return result
+ elif isinstance(result, list):
+ vid = int(video_id)
+ for v in result:
+ if try_get(v, lambda x: x['general']['ID'], int) == vid:
+ return v
+ return None
+
response = self._download_json(
'https://arc.nexx.cloud/api/video/%s.json' % video_id,
video_id, fatal=False)
if response and isinstance(response, dict):
result = response.get('result')
- if result and isinstance(result, dict):
- video = result
+ if result:
+ video = find_video(result)
# not all videos work via arc, e.g. nexx:741:1269984
if not video:
@@ -348,7 +358,7 @@ class NexxIE(InfoExtractor):
request_token = hashlib.md5(
''.join((op, domain_id, secret)).encode('utf-8')).hexdigest()
- video = self._call_api(
+ result = self._call_api(
domain_id, 'videos/%s/%s' % (op, video_id), video_id, data={
'additionalfields': 'language,channel,actors,studio,licenseby,slug,subtitle,teaser,description',
'addInteractionOptions': '1',
@@ -363,6 +373,7 @@ class NexxIE(InfoExtractor):
'X-Request-CID': cid,
'X-Request-Token': request_token,
})
+ video = find_video(result)
general = video['general']
title = general['title']
@@ -399,8 +410,8 @@ class NexxIE(InfoExtractor):
class NexxEmbedIE(InfoExtractor):
- _VALID_URL = r'https?://embed\.nexx(?:\.cloud|cdn\.com)/\d+/(?P<id>[^/?#&]+)'
- _TEST = {
+ _VALID_URL = r'https?://embed\.nexx(?:\.cloud|cdn\.com)/\d+/(?:video/)?(?P<id>[^/?#&]+)'
+ _TESTS = [{
'url': 'http://embed.nexx.cloud/748/KC1614647Z27Y7T?autoplay=1',
'md5': '16746bfc28c42049492385c989b26c4a',
'info_dict': {
@@ -409,7 +420,6 @@ class NexxEmbedIE(InfoExtractor):
'title': 'Nervenkitzel Achterbahn',
'alt_title': 'Karussellbauer in Deutschland',
'description': 'md5:ffe7b1cc59a01f585e0569949aef73cc',
- 'release_year': 2005,
'creator': 'SPIEGEL TV',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 2761,
@@ -420,7 +430,10 @@ class NexxEmbedIE(InfoExtractor):
'format': 'bestvideo',
'skip_download': True,
},
- }
+ }, {
+ 'url': 'https://embed.nexx.cloud/11888/video/DSRTO7UVOX06S7',
+ 'only_matching': True,
+ }]
@staticmethod
def _extract_urls(webpage):
diff --git a/youtube_dl/extractor/nhk.py b/youtube_dl/extractor/nhk.py
index 241412f98..6a2c6cb7b 100644
--- a/youtube_dl/extractor/nhk.py
+++ b/youtube_dl/extractor/nhk.py
@@ -10,6 +10,18 @@ class NhkVodIE(InfoExtractor):
# Content available only for a limited period of time. Visit
# https://www3.nhk.or.jp/nhkworld/en/ondemand/ for working samples.
_TESTS = [{
+ # clip
+ 'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/9999011/',
+ 'md5': '256a1be14f48d960a7e61e2532d95ec3',
+ 'info_dict': {
+ 'id': 'a95j5iza',
+ 'ext': 'mp4',
+ 'title': "Dining with the Chef - Chef Saito's Family recipe: MENCHI-KATSU",
+ 'description': 'md5:5aee4a9f9d81c26281862382103b0ea5',
+ 'timestamp': 1565965194,
+ 'upload_date': '20190816',
+ },
+ }, {
'url': 'https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2015173/',
'only_matching': True,
}, {
@@ -19,7 +31,7 @@ class NhkVodIE(InfoExtractor):
'url': 'https://www3.nhk.or.jp/nhkworld/fr/ondemand/audio/plugin-20190404-1/',
'only_matching': True,
}]
- _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sodesdlist/v7/episode/%s/%s/all%s.json'
+ _API_URL_TEMPLATE = 'https://api.nhk.or.jp/nhkworld/%sod%slist/v7/episode/%s/%s/all%s.json'
def _real_extract(self, url):
lang, m_type, episode_id = re.match(self._VALID_URL, url).groups()
@@ -28,7 +40,10 @@ class NhkVodIE(InfoExtractor):
is_video = m_type == 'video'
episode = self._download_json(
- self._API_URL_TEMPLATE % ('v' if is_video else 'r', episode_id, lang, '/all' if is_video else ''),
+ self._API_URL_TEMPLATE % (
+ 'v' if is_video else 'r',
+ 'clip' if episode_id[:4] == '9999' else 'esd',
+ episode_id, lang, '/all' if is_video else ''),
episode_id, query={'apikey': 'EJfK8jdS57GqlupFgAfAAwr573q01y6k'})['data']['episodes'][0]
title = episode.get('sub_title_clean') or episode['sub_title']
@@ -60,8 +75,8 @@ class NhkVodIE(InfoExtractor):
if is_video:
info.update({
'_type': 'url_transparent',
- 'ie_key': 'Ooyala',
- 'url': 'ooyala:' + episode['vod_id'],
+ 'ie_key': 'Piksel',
+ 'url': 'https://player.piksel.com/v/refid/nhkworld/prefid/' + episode['vod_id'],
})
else:
audio = episode['audio']
diff --git a/youtube_dl/extractor/nick.py b/youtube_dl/extractor/nick.py
index 5e34d776b..2e8b302ac 100644
--- a/youtube_dl/extractor/nick.py
+++ b/youtube_dl/extractor/nick.py
@@ -85,7 +85,8 @@ class NickBrIE(MTVServicesInfoExtractor):
https?://
(?:
(?P<domain>(?:www\.)?nickjr|mundonick\.uol)\.com\.br|
- (?:www\.)?nickjr\.[a-z]{2}
+ (?:www\.)?nickjr\.[a-z]{2}|
+ (?:www\.)?nickelodeonjunior\.fr
)
/(?:programas/)?[^/]+/videos/(?:episodios/)?(?P<id>[^/?\#.]+)
'''
@@ -101,6 +102,9 @@ class NickBrIE(MTVServicesInfoExtractor):
}, {
'url': 'http://www.nickjr.de/blaze-und-die-monster-maschinen/videos/f6caaf8f-e4e8-4cc1-b489-9380d6dcd059/',
'only_matching': True,
+ }, {
+ 'url': 'http://www.nickelodeonjunior.fr/paw-patrol-la-pat-patrouille/videos/episode-401-entier-paw-patrol/',
+ 'only_matching': True,
}]
def _real_extract(self, url):
diff --git a/youtube_dl/extractor/ninenow.py b/youtube_dl/extractor/ninenow.py
index f32f530f7..6157dc7c1 100644
--- a/youtube_dl/extractor/ninenow.py
+++ b/youtube_dl/extractor/ninenow.py
@@ -45,7 +45,11 @@ class NineNowIE(InfoExtractor):
webpage = self._download_webpage(url, display_id)
page_data = self._parse_json(self._search_regex(
r'window\.__data\s*=\s*({.*?});', webpage,
- 'page data'), display_id)
+ 'page data', default='{}'), display_id, fatal=False)
+ if not page_data:
+ page_data = self._parse_json(self._parse_json(self._search_regex(
+ r'window\.__data\s*=\s*JSON\.parse\s*\(\s*(".+?")\s*\)\s*;',
+ webpage, 'page data'), display_id), display_id)
for kind in ('episode', 'clip'):
current_key = page_data.get(kind, {}).get(
diff --git a/youtube_dl/extractor/nintendo.py b/youtube_dl/extractor/nintendo.py
index 4b4e66b05..ff8f70ba6 100644
--- a/youtube_dl/extractor/nintendo.py
+++ b/youtube_dl/extractor/nintendo.py
@@ -5,13 +5,12 @@ import re
from .common import InfoExtractor
from .ooyala import OoyalaIE
-from ..utils import unescapeHTML
class NintendoIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?nintendo\.com/games/detail/(?P<id>[^/?#&]+)'
+ _VALID_URL = r'https?://(?:www\.)?nintendo\.com/(?:games/detail|nintendo-direct)/(?P<id>[^/?#&]+)'
_TESTS = [{
- 'url': 'http://www.nintendo.com/games/detail/yEiAzhU2eQI1KZ7wOHhngFoAHc1FpHwj',
+ 'url': 'https://www.nintendo.com/games/detail/duck-hunt-wii-u/',
'info_dict': {
'id': 'MzMmticjp0VPzO3CCj4rmFOuohEuEWoW',
'ext': 'flv',
@@ -28,7 +27,19 @@ class NintendoIE(InfoExtractor):
'id': 'tokyo-mirage-sessions-fe-wii-u',
'title': 'Tokyo Mirage Sessions ♯FE',
},
- 'playlist_count': 3,
+ 'playlist_count': 4,
+ }, {
+ 'url': 'https://www.nintendo.com/nintendo-direct/09-04-2019/',
+ 'info_dict': {
+ 'id': 'J2bXdmaTE6fe3dWJTPcc7m23FNbc_A1V',
+ 'ext': 'mp4',
+ 'title': 'Switch_ROS_ND0904-H264.mov',
+ 'duration': 2324.758,
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ 'add_ie': ['Ooyala'],
}]
def _real_extract(self, url):
@@ -39,8 +50,11 @@ class NintendoIE(InfoExtractor):
entries = [
OoyalaIE._build_url_result(m.group('code'))
for m in re.finditer(
- r'class=(["\'])embed-video\1[^>]+data-video-code=(["\'])(?P<code>(?:(?!\2).)+)\2',
- webpage)]
+ r'data-(?:video-id|directVideoId)=(["\'])(?P<code>(?:(?!\1).)+)\1', webpage)]
+
+ title = self._html_search_regex(
+ r'(?s)<(?:span|div)[^>]+class="(?:title|wrapper)"[^>]*>.*?<h1>(.+?)</h1>',
+ webpage, 'title', fatal=False)
return self.playlist_result(
- entries, page_id, unescapeHTML(self._og_search_title(webpage, fatal=False)))
+ entries, page_id, title)
diff --git a/youtube_dl/extractor/nonktube.py b/youtube_dl/extractor/nonktube.py
index 63e58aae2..ca1424e06 100644
--- a/youtube_dl/extractor/nonktube.py
+++ b/youtube_dl/extractor/nonktube.py
@@ -25,9 +25,14 @@ class NonkTubeIE(NuevoBaseIE):
def _real_extract(self, url):
video_id = self._match_id(url)
- info = self._extract_nuevo(
- 'https://www.nonktube.com/media/nuevo/econfig.php?key=%s'
- % video_id, video_id)
+ webpage = self._download_webpage(url, video_id)
- info['age_limit'] = 18
+ title = self._og_search_title(webpage)
+ info = self._parse_html5_media_entries(url, webpage, video_id)[0]
+
+ info.update({
+ 'id': video_id,
+ 'title': title,
+ 'age_limit': 18,
+ })
return info
diff --git a/youtube_dl/extractor/nrk.py b/youtube_dl/extractor/nrk.py
index 5f43e692f..60933f069 100644
--- a/youtube_dl/extractor/nrk.py
+++ b/youtube_dl/extractor/nrk.py
@@ -406,7 +406,7 @@ class NRKTVSerieBaseIE(InfoExtractor):
def _extract_series(self, webpage, display_id, fatal=True):
config = self._parse_json(
self._search_regex(
- (r'INITIAL_DATA_*\s*=\s*({.+?})\s*;',
+ (r'INITIAL_DATA(?:_V\d)?_*\s*=\s*({.+?})\s*;',
r'({.+?})\s*,\s*"[^"]+"\s*\)\s*</script>'),
webpage, 'config', default='{}' if not fatal else NO_DEFAULT),
display_id, fatal=False)
diff --git a/youtube_dl/extractor/nrl.py b/youtube_dl/extractor/nrl.py
index 798b91e04..22a2df8d3 100644
--- a/youtube_dl/extractor/nrl.py
+++ b/youtube_dl/extractor/nrl.py
@@ -23,8 +23,8 @@ class NRLTVIE(InfoExtractor):
def _real_extract(self, url):
display_id = self._match_id(url)
webpage = self._download_webpage(url, display_id)
- q_data = self._parse_json(self._search_regex(
- r"(?s)q-data='({.+?})'", webpage, 'player data'), display_id)
+ q_data = self._parse_json(self._html_search_regex(
+ r'(?s)q-data="({.+?})"', webpage, 'player data'), display_id)
ooyala_id = q_data['videoId']
return self.url_result(
'ooyala:' + ooyala_id, 'Ooyala', ooyala_id, q_data.get('title'))
diff --git a/youtube_dl/extractor/ntvru.py b/youtube_dl/extractor/ntvru.py
index 4f9cedb84..c47d1dfa4 100644
--- a/youtube_dl/extractor/ntvru.py
+++ b/youtube_dl/extractor/ntvru.py
@@ -3,9 +3,10 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
- clean_html,
- xpath_text,
int_or_none,
+ strip_or_none,
+ unescapeHTML,
+ xpath_text,
)
@@ -47,10 +48,10 @@ class NTVRuIE(InfoExtractor):
'duration': 1496,
},
}, {
- 'url': 'http://www.ntv.ru/kino/Koma_film',
- 'md5': 'f825770930937aa7e5aca0dc0d29319a',
+ 'url': 'https://www.ntv.ru/kino/Koma_film/m70281/o336036/video/',
+ 'md5': 'e9c7cde24d9d3eaed545911a04e6d4f4',
'info_dict': {
- 'id': '1007609',
+ 'id': '1126480',
'ext': 'mp4',
'title': 'Остросюжетный фильм «Кома»',
'description': 'Остросюжетный фильм «Кома»',
@@ -68,6 +69,10 @@ class NTVRuIE(InfoExtractor):
'thumbnail': r're:^http://.*\.jpg',
'duration': 2590,
},
+ }, {
+ # Schemeless file URL
+ 'url': 'https://www.ntv.ru/video/1797442',
+ 'only_matching': True,
}]
_VIDEO_ID_REGEXES = [
@@ -96,37 +101,31 @@ class NTVRuIE(InfoExtractor):
'http://www.ntv.ru/vi%s/' % video_id,
video_id, 'Downloading video XML')
- title = clean_html(xpath_text(player, './data/title', 'title', fatal=True))
- description = clean_html(xpath_text(player, './data/description', 'description'))
+ title = strip_or_none(unescapeHTML(xpath_text(player, './data/title', 'title', fatal=True)))
video = player.find('./data/video')
- video_id = xpath_text(video, './id', 'video id')
- thumbnail = xpath_text(video, './splash', 'thumbnail')
- duration = int_or_none(xpath_text(video, './totaltime', 'duration'))
- view_count = int_or_none(xpath_text(video, './views', 'view count'))
-
- token = self._download_webpage(
- 'http://stat.ntv.ru/services/access/token',
- video_id, 'Downloading access token')
formats = []
for format_id in ['', 'hi', 'webm']:
- file_ = video.find('./%sfile' % format_id)
- if file_ is None:
+ file_ = xpath_text(video, './%sfile' % format_id)
+ if not file_:
continue
- size = video.find('./%ssize' % format_id)
+ if file_.startswith('//'):
+ file_ = self._proto_relative_url(file_)
+ elif not file_.startswith('http'):
+ file_ = 'http://media.ntv.ru/vod/' + file_
formats.append({
- 'url': 'http://media2.ntv.ru/vod/%s&tok=%s' % (file_.text, token),
- 'filesize': int_or_none(size.text if size is not None else None),
+ 'url': file_,
+ 'filesize': int_or_none(xpath_text(video, './%ssize' % format_id)),
})
self._sort_formats(formats)
return {
- 'id': video_id,
+ 'id': xpath_text(video, './id'),
'title': title,
- 'description': description,
- 'thumbnail': thumbnail,
- 'duration': duration,
- 'view_count': view_count,
+ 'description': strip_or_none(unescapeHTML(xpath_text(player, './data/description'))),
+ 'thumbnail': xpath_text(video, './splash'),
+ 'duration': int_or_none(xpath_text(video, './totaltime')),
+ 'view_count': int_or_none(xpath_text(video, './views')),
'formats': formats,
}
diff --git a/youtube_dl/extractor/odnoklassniki.py b/youtube_dl/extractor/odnoklassniki.py
index 114b93c07..7ed9fac55 100644
--- a/youtube_dl/extractor/odnoklassniki.py
+++ b/youtube_dl/extractor/odnoklassniki.py
@@ -1,6 +1,8 @@
# coding: utf-8
from __future__ import unicode_literals
+import re
+
from .common import InfoExtractor
from ..compat import (
compat_etree_fromstring,
@@ -121,6 +123,13 @@ class OdnoklassnikiIE(InfoExtractor):
'only_matching': True,
}]
+ @staticmethod
+ def _extract_url(webpage):
+ mobj = re.search(
+ r'<iframe[^>]+src=(["\'])(?P<url>(?:https?:)?//(?:odnoklassniki|ok)\.ru/videoembed/.+?)\1', webpage)
+ if mobj:
+ return mobj.group('url')
+
def _real_extract(self, url):
start_time = int_or_none(compat_parse_qs(
compat_urllib_parse_urlparse(url).query).get('fromTime', [None])[0])
diff --git a/youtube_dl/extractor/onet.py b/youtube_dl/extractor/onet.py
index 58da1bc27..e55b2ac89 100644
--- a/youtube_dl/extractor/onet.py
+++ b/youtube_dl/extractor/onet.py
@@ -20,6 +20,8 @@ from ..utils import (
class OnetBaseIE(InfoExtractor):
+ _URL_BASE_RE = r'https?://(?:(?:www\.)?onet\.tv|onet100\.vod\.pl)/[a-z]/'
+
def _search_mvp_id(self, webpage):
return self._search_regex(
r'id=(["\'])mvp:(?P<id>.+?)\1', webpage, 'mvp id', group='id')
@@ -45,7 +47,7 @@ class OnetBaseIE(InfoExtractor):
video = response['result'].get('0')
formats = []
- for _, formats_dict in video['formats'].items():
+ for format_type, formats_dict in video['formats'].items():
if not isinstance(formats_dict, dict):
continue
for format_id, format_list in formats_dict.items():
@@ -56,21 +58,31 @@ class OnetBaseIE(InfoExtractor):
if not video_url:
continue
ext = determine_ext(video_url)
- if format_id == 'ism':
+ if format_id.startswith('ism'):
formats.extend(self._extract_ism_formats(
video_url, video_id, 'mss', fatal=False))
elif ext == 'mpd':
formats.extend(self._extract_mpd_formats(
video_url, video_id, mpd_id='dash', fatal=False))
+ elif format_id.startswith('hls'):
+ formats.extend(self._extract_m3u8_formats(
+ video_url, video_id, 'mp4', 'm3u8_native',
+ m3u8_id='hls', fatal=False))
else:
- formats.append({
+ http_f = {
'url': video_url,
'format_id': format_id,
- 'height': int_or_none(f.get('vertical_resolution')),
- 'width': int_or_none(f.get('horizontal_resolution')),
'abr': float_or_none(f.get('audio_bitrate')),
- 'vbr': float_or_none(f.get('video_bitrate')),
- })
+ }
+ if format_type == 'audio':
+ http_f['vcodec'] = 'none'
+ else:
+ http_f.update({
+ 'height': int_or_none(f.get('vertical_resolution')),
+ 'width': int_or_none(f.get('horizontal_resolution')),
+ 'vbr': float_or_none(f.get('video_bitrate')),
+ })
+ formats.append(http_f)
self._sort_formats(formats)
meta = video.get('meta', {})
@@ -105,12 +117,12 @@ class OnetMVPIE(OnetBaseIE):
class OnetIE(OnetBaseIE):
- _VALID_URL = r'https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/(?P<display_id>[0-9a-z-]+)/(?P<id>[0-9a-z]+)'
+ _VALID_URL = OnetBaseIE._URL_BASE_RE + r'[a-z]+/(?P<display_id>[0-9a-z-]+)/(?P<id>[0-9a-z]+)'
IE_NAME = 'onet.tv'
- _TEST = {
+ _TESTS = [{
'url': 'http://onet.tv/k/openerfestival/open-er-festival-2016-najdziwniejsze-wymagania-gwiazd/qbpyqc',
- 'md5': 'e3ffbf47590032ac3f27249204173d50',
+ 'md5': '436102770fb095c75b8bb0392d3da9ff',
'info_dict': {
'id': 'qbpyqc',
'display_id': 'open-er-festival-2016-najdziwniejsze-wymagania-gwiazd',
@@ -120,7 +132,10 @@ class OnetIE(OnetBaseIE):
'upload_date': '20160705',
'timestamp': 1467721580,
},
- }
+ }, {
+ 'url': 'https://onet100.vod.pl/k/openerfestival/open-er-festival-2016-najdziwniejsze-wymagania-gwiazd/qbpyqc',
+ 'only_matching': True,
+ }]
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
@@ -140,18 +155,21 @@ class OnetIE(OnetBaseIE):
class OnetChannelIE(OnetBaseIE):
- _VALID_URL = r'https?://(?:www\.)?onet\.tv/[a-z]/(?P<id>[a-z]+)(?:[?#]|$)'
+ _VALID_URL = OnetBaseIE._URL_BASE_RE + r'(?P<id>[a-z]+)(?:[?#]|$)'
IE_NAME = 'onet.tv:channel'
- _TEST = {
+ _TESTS = [{
'url': 'http://onet.tv/k/openerfestival',
'info_dict': {
'id': 'openerfestival',
- 'title': 'Open\'er Festival Live',
- 'description': 'Dziękujemy, że oglądaliście transmisje. Zobaczcie nasze relacje i wywiady z artystami.',
+ 'title': "Open'er Festival",
+ 'description': "Tak było na Open'er Festival 2016! Oglądaj nasze reportaże i wywiady z artystami.",
},
- 'playlist_mincount': 46,
- }
+ 'playlist_mincount': 35,
+ }, {
+ 'url': 'https://onet100.vod.pl/k/openerfestival',
+ 'only_matching': True,
+ }]
def _real_extract(self, url):
channel_id = self._match_id(url)
@@ -173,7 +191,7 @@ class OnetChannelIE(OnetBaseIE):
'Downloading channel %s - add --no-playlist to just download video %s' % (
channel_id, video_name))
matches = re.findall(
- r'<a[^>]+href=[\'"](https?://(?:www\.)?onet\.tv/[a-z]/[a-z]+/[0-9a-z-]+/[0-9a-z]+)',
+ r'<a[^>]+href=[\'"](%s[a-z]+/[0-9a-z-]+/[0-9a-z]+)' % self._URL_BASE_RE,
webpage)
entries = [
self.url_result(video_link, OnetIE.ie_key())
diff --git a/youtube_dl/extractor/onionstudios.py b/youtube_dl/extractor/onionstudios.py
index c6e3d5640..cf5c39e66 100644
--- a/youtube_dl/extractor/onionstudios.py
+++ b/youtube_dl/extractor/onionstudios.py
@@ -4,12 +4,8 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..utils import (
- determine_ext,
- int_or_none,
- float_or_none,
- mimetype2ext,
-)
+from ..compat import compat_str
+from ..utils import js_to_json
class OnionStudiosIE(InfoExtractor):
@@ -17,14 +13,16 @@ class OnionStudiosIE(InfoExtractor):
_TESTS = [{
'url': 'http://www.onionstudios.com/videos/hannibal-charges-forward-stops-for-a-cocktail-2937',
- 'md5': '719d1f8c32094b8c33902c17bcae5e34',
+ 'md5': '5a118d466d62b5cd03647cf2c593977f',
'info_dict': {
- 'id': '2937',
+ 'id': '3459881',
'ext': 'mp4',
'title': 'Hannibal charges forward, stops for a cocktail',
+ 'description': 'md5:545299bda6abf87e5ec666548c6a9448',
'thumbnail': r're:^https?://.*\.jpg$',
- 'uploader': 'The A.V. Club',
- 'uploader_id': 'the-av-club',
+ 'uploader': 'a.v. club',
+ 'upload_date': '20150619',
+ 'timestamp': 1434728546,
},
}, {
'url': 'http://www.onionstudios.com/embed?id=2855&autoplay=true',
@@ -44,38 +42,12 @@ class OnionStudiosIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
- video_data = self._download_json(
- 'http://www.onionstudios.com/video/%s.json' % video_id, video_id)
-
- title = video_data['title']
-
- formats = []
- for source in video_data.get('sources', []):
- source_url = source.get('url')
- if not source_url:
- continue
- ext = mimetype2ext(source.get('content_type')) or determine_ext(source_url)
- if ext == 'm3u8':
- formats.extend(self._extract_m3u8_formats(
- source_url, video_id, 'mp4', 'm3u8_native', m3u8_id='hls', fatal=False))
- else:
- tbr = int_or_none(source.get('bitrate'))
- formats.append({
- 'format_id': ext + ('-%d' % tbr if tbr else ''),
- 'url': source_url,
- 'width': int_or_none(source.get('width')),
- 'tbr': tbr,
- 'ext': ext,
- })
- self._sort_formats(formats)
-
- return {
- 'id': video_id,
- 'title': title,
- 'thumbnail': video_data.get('poster_url'),
- 'uploader': video_data.get('channel_name'),
- 'uploader_id': video_data.get('channel_slug'),
- 'duration': float_or_none(video_data.get('duration', 1000)),
- 'tags': video_data.get('tags'),
- 'formats': formats,
- }
+ webpage = self._download_webpage(
+ 'http://onionstudios.com/embed/dc94dc2899fe644c0e7241fa04c1b732.js',
+ video_id)
+ mcp_id = compat_str(self._parse_json(self._search_regex(
+ r'window\.mcpMapping\s*=\s*({.+?});', webpage,
+ 'MCP Mapping'), video_id, js_to_json)[video_id]['mcp_id'])
+ return self.url_result(
+ 'http://kinja.com/ajax/inset/iframe?id=mcp-' + mcp_id,
+ 'KinjaEmbed', mcp_id)
diff --git a/youtube_dl/extractor/ooyala.py b/youtube_dl/extractor/ooyala.py
index 995b24d1b..eb957b8fe 100644
--- a/youtube_dl/extractor/ooyala.py
+++ b/youtube_dl/extractor/ooyala.py
@@ -1,12 +1,12 @@
from __future__ import unicode_literals
+import base64
import re
from .common import InfoExtractor
from ..compat import (
compat_b64decode,
compat_str,
- compat_urllib_parse_urlencode,
)
from ..utils import (
determine_ext,
@@ -21,9 +21,9 @@ from ..utils import (
class OoyalaBaseIE(InfoExtractor):
_PLAYER_BASE = 'http://player.ooyala.com/'
_CONTENT_TREE_BASE = _PLAYER_BASE + 'player_api/v1/content_tree/'
- _AUTHORIZATION_URL_TEMPLATE = _PLAYER_BASE + 'sas/player_api/v2/authorization/embed_code/%s/%s?'
+ _AUTHORIZATION_URL_TEMPLATE = _PLAYER_BASE + 'sas/player_api/v2/authorization/embed_code/%s/%s'
- def _extract(self, content_tree_url, video_id, domain='example.org', supportedformats=None, embed_token=None):
+ def _extract(self, content_tree_url, video_id, domain=None, supportedformats=None, embed_token=None):
content_tree = self._download_json(content_tree_url, video_id)['content_tree']
metadata = content_tree[list(content_tree)[0]]
embed_code = metadata['embed_code']
@@ -31,59 +31,62 @@ class OoyalaBaseIE(InfoExtractor):
title = metadata['title']
auth_data = self._download_json(
- self._AUTHORIZATION_URL_TEMPLATE % (pcode, embed_code)
- + compat_urllib_parse_urlencode({
- 'domain': domain,
+ self._AUTHORIZATION_URL_TEMPLATE % (pcode, embed_code),
+ video_id, headers=self.geo_verification_headers(), query={
+ 'domain': domain or 'player.ooyala.com',
'supportedFormats': supportedformats or 'mp4,rtmp,m3u8,hds,dash,smooth',
'embedToken': embed_token,
- }), video_id, headers=self.geo_verification_headers())
-
- cur_auth_data = auth_data['authorization_data'][embed_code]
+ })['authorization_data'][embed_code]
urls = []
formats = []
- if cur_auth_data['authorized']:
- for stream in cur_auth_data['streams']:
- url_data = try_get(stream, lambda x: x['url']['data'], compat_str)
- if not url_data:
- continue
- s_url = compat_b64decode(url_data).decode('utf-8')
- if not s_url or s_url in urls:
- continue
- urls.append(s_url)
- ext = determine_ext(s_url, None)
- delivery_type = stream.get('delivery_type')
- if delivery_type == 'hls' or ext == 'm3u8':
- formats.extend(self._extract_m3u8_formats(
- re.sub(r'/ip(?:ad|hone)/', '/all/', s_url), embed_code, 'mp4', 'm3u8_native',
- m3u8_id='hls', fatal=False))
- elif delivery_type == 'hds' or ext == 'f4m':
- formats.extend(self._extract_f4m_formats(
- s_url + '?hdcore=3.7.0', embed_code, f4m_id='hds', fatal=False))
- elif delivery_type == 'dash' or ext == 'mpd':
- formats.extend(self._extract_mpd_formats(
- s_url, embed_code, mpd_id='dash', fatal=False))
- elif delivery_type == 'smooth':
- self._extract_ism_formats(
- s_url, embed_code, ism_id='mss', fatal=False)
- elif ext == 'smil':
- formats.extend(self._extract_smil_formats(
- s_url, embed_code, fatal=False))
- else:
- formats.append({
- 'url': s_url,
- 'ext': ext or delivery_type,
- 'vcodec': stream.get('video_codec'),
- 'format_id': delivery_type,
- 'width': int_or_none(stream.get('width')),
- 'height': int_or_none(stream.get('height')),
- 'abr': int_or_none(stream.get('audio_bitrate')),
- 'vbr': int_or_none(stream.get('video_bitrate')),
- 'fps': float_or_none(stream.get('framerate')),
- })
- else:
+ streams = auth_data.get('streams') or [{
+ 'delivery_type': 'hls',
+ 'url': {
+ 'data': base64.b64encode(('http://player.ooyala.com/hls/player/all/%s.m3u8' % embed_code).encode()).decode(),
+ }
+ }]
+ for stream in streams:
+ url_data = try_get(stream, lambda x: x['url']['data'], compat_str)
+ if not url_data:
+ continue
+ s_url = compat_b64decode(url_data).decode('utf-8')
+ if not s_url or s_url in urls:
+ continue
+ urls.append(s_url)
+ ext = determine_ext(s_url, None)
+ delivery_type = stream.get('delivery_type')
+ if delivery_type == 'hls' or ext == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ re.sub(r'/ip(?:ad|hone)/', '/all/', s_url), embed_code, 'mp4', 'm3u8_native',
+ m3u8_id='hls', fatal=False))
+ elif delivery_type == 'hds' or ext == 'f4m':
+ formats.extend(self._extract_f4m_formats(
+ s_url + '?hdcore=3.7.0', embed_code, f4m_id='hds', fatal=False))
+ elif delivery_type == 'dash' or ext == 'mpd':
+ formats.extend(self._extract_mpd_formats(
+ s_url, embed_code, mpd_id='dash', fatal=False))
+ elif delivery_type == 'smooth':
+ self._extract_ism_formats(
+ s_url, embed_code, ism_id='mss', fatal=False)
+ elif ext == 'smil':
+ formats.extend(self._extract_smil_formats(
+ s_url, embed_code, fatal=False))
+ else:
+ formats.append({
+ 'url': s_url,
+ 'ext': ext or delivery_type,
+ 'vcodec': stream.get('video_codec'),
+ 'format_id': delivery_type,
+ 'width': int_or_none(stream.get('width')),
+ 'height': int_or_none(stream.get('height')),
+ 'abr': int_or_none(stream.get('audio_bitrate')),
+ 'vbr': int_or_none(stream.get('video_bitrate')),
+ 'fps': float_or_none(stream.get('framerate')),
+ })
+ if not formats and not auth_data.get('authorized'):
raise ExtractorError('%s said: %s' % (
- self.IE_NAME, cur_auth_data['message']), expected=True)
+ self.IE_NAME, auth_data['message']), expected=True)
self._sort_formats(formats)
subtitles = {}
diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py
index 237b0d8fb..0c20d0177 100644
--- a/youtube_dl/extractor/openload.py
+++ b/youtube_dl/extractor/openload.py
@@ -3,21 +3,17 @@ from __future__ import unicode_literals
import json
import os
-import re
import subprocess
import tempfile
-from .common import InfoExtractor
from ..compat import (
compat_urlparse,
compat_kwargs,
)
from ..utils import (
check_executable,
- determine_ext,
encodeArgument,
ExtractorError,
- get_element_by_id,
get_exe_version,
is_outdated_version,
std_headers,
@@ -240,241 +236,3 @@ class PhantomJSwrapper(object):
self._load_cookies()
return (html, encodeArgument(out))
-
-
-class OpenloadIE(InfoExtractor):
- _DOMAINS = r'(?:openload\.(?:co|io|link|pw)|oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|press|pw|life|live|space|services|website)|oladblock\.(?:services|xyz|me)|openloed\.co)'
- _VALID_URL = r'''(?x)
- https?://
- (?P<host>
- (?:www\.)?
- %s
- )/
- (?:f|embed)/
- (?P<id>[a-zA-Z0-9-_]+)
- ''' % _DOMAINS
- _EMBED_WORD = 'embed'
- _STREAM_WORD = 'f'
- _REDIR_WORD = 'stream'
- _URL_IDS = ('streamurl', 'streamuri', 'streamurj')
- _TESTS = [{
- 'url': 'https://openload.co/f/kUEfGclsU9o',
- 'md5': 'bf1c059b004ebc7a256f89408e65c36e',
- 'info_dict': {
- 'id': 'kUEfGclsU9o',
- 'ext': 'mp4',
- 'title': 'skyrim_no-audio_1080.mp4',
- 'thumbnail': r're:^https?://.*\.jpg$',
- },
- }, {
- 'url': 'https://openload.co/embed/rjC09fkPLYs',
- 'info_dict': {
- 'id': 'rjC09fkPLYs',
- 'ext': 'mp4',
- 'title': 'movie.mp4',
- 'thumbnail': r're:^https?://.*\.jpg$',
- 'subtitles': {
- 'en': [{
- 'ext': 'vtt',
- }],
- },
- },
- 'params': {
- 'skip_download': True, # test subtitles only
- },
- }, {
- 'url': 'https://openload.co/embed/kUEfGclsU9o/skyrim_no-audio_1080.mp4',
- 'only_matching': True,
- }, {
- 'url': 'https://openload.io/f/ZAn6oz-VZGE/',
- 'only_matching': True,
- }, {
- 'url': 'https://openload.co/f/_-ztPaZtMhM/',
- 'only_matching': True,
- }, {
- # unavailable via https://openload.co/f/Sxz5sADo82g/, different layout
- # for title and ext
- 'url': 'https://openload.co/embed/Sxz5sADo82g/',
- 'only_matching': True,
- }, {
- # unavailable via https://openload.co/embed/e-Ixz9ZR5L0/ but available
- # via https://openload.co/f/e-Ixz9ZR5L0/
- 'url': 'https://openload.co/f/e-Ixz9ZR5L0/',
- 'only_matching': True,
- }, {
- 'url': 'https://oload.tv/embed/KnG-kKZdcfY/',
- 'only_matching': True,
- }, {
- 'url': 'http://www.openload.link/f/KnG-kKZdcfY',
- 'only_matching': True,
- }, {
- 'url': 'https://oload.stream/f/KnG-kKZdcfY',
- 'only_matching': True,
- }, {
- 'url': 'https://oload.xyz/f/WwRBpzW8Wtk',
- 'only_matching': True,
- }, {
- 'url': 'https://oload.win/f/kUEfGclsU9o',
- 'only_matching': True,
- }, {
- 'url': 'https://oload.download/f/kUEfGclsU9o',
- 'only_matching': True,
- }, {
- 'url': 'https://oload.cloud/f/4ZDnBXRWiB8',
- 'only_matching': True,
- }, {
- # Its title has not got its extension but url has it
- 'url': 'https://oload.download/f/N4Otkw39VCw/Tomb.Raider.2018.HDRip.XviD.AC3-EVO.avi.mp4',
- 'only_matching': True,
- }, {
- 'url': 'https://oload.cc/embed/5NEAbI2BDSk',
- 'only_matching': True,
- }, {
- 'url': 'https://oload.icu/f/-_i4y_F_Hs8',
- 'only_matching': True,
- }, {
- 'url': 'https://oload.fun/f/gb6G1H4sHXY',
- 'only_matching': True,
- }, {
- 'url': 'https://oload.club/f/Nr1L-aZ2dbQ',
- 'only_matching': True,
- }, {
- 'url': 'https://oload.info/f/5NEAbI2BDSk',
- 'only_matching': True,
- }, {
- 'url': 'https://openload.pw/f/WyKgK8s94N0',
- 'only_matching': True,
- }, {
- 'url': 'https://oload.pw/f/WyKgK8s94N0',
- 'only_matching': True,
- }, {
- 'url': 'https://oload.live/f/-Z58UZ-GR4M',
- 'only_matching': True,
- }, {
- 'url': 'https://oload.space/f/IY4eZSst3u8/',
- 'only_matching': True,
- }, {
- 'url': 'https://oload.services/embed/bs1NWj1dCag/',
- 'only_matching': True,
- }, {
- 'url': 'https://oload.press/embed/drTBl1aOTvk/',
- 'only_matching': True,
- }, {
- 'url': 'https://oload.website/embed/drTBl1aOTvk/',
- 'only_matching': True,
- }, {
- 'url': 'https://oload.life/embed/oOzZjNPw9Dc/',
- 'only_matching': True,
- }, {
- 'url': 'https://oladblock.services/f/b8NWEgkqNLI/',
- 'only_matching': True,
- }, {
- 'url': 'https://oladblock.xyz/f/b8NWEgkqNLI/',
- 'only_matching': True,
- }, {
- 'url': 'https://oladblock.me/f/b8NWEgkqNLI/',
- 'only_matching': True,
- }, {
- 'url': 'https://openloed.co/f/b8NWEgkqNLI/',
- 'only_matching': True,
- }]
-
- @classmethod
- def _extract_urls(cls, webpage):
- return re.findall(
- r'<iframe[^>]+src=["\']((?:https?://)?%s/%s/[a-zA-Z0-9-_]+)'
- % (cls._DOMAINS, cls._EMBED_WORD), webpage)
-
- def _extract_decrypted_page(self, page_url, webpage, video_id):
- phantom = PhantomJSwrapper(self, required_version='2.0')
- webpage, _ = phantom.get(page_url, html=webpage, video_id=video_id)
- return webpage
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- host = mobj.group('host')
- video_id = mobj.group('id')
-
- url_pattern = 'https://%s/%%s/%s/' % (host, video_id)
-
- for path in (self._EMBED_WORD, self._STREAM_WORD):
- page_url = url_pattern % path
- last = path == self._STREAM_WORD
- webpage = self._download_webpage(
- page_url, video_id, 'Downloading %s webpage' % path,
- fatal=last)
- if not webpage:
- continue
- if 'File not found' in webpage or 'deleted by the owner' in webpage:
- if not last:
- continue
- raise ExtractorError('File not found', expected=True, video_id=video_id)
- break
-
- webpage = self._extract_decrypted_page(page_url, webpage, video_id)
- for element_id in self._URL_IDS:
- decoded_id = get_element_by_id(element_id, webpage)
- if decoded_id:
- break
- if not decoded_id:
- decoded_id = self._search_regex(
- (r'>\s*([\w-]+~\d{10,}~\d+\.\d+\.0\.0~[\w-]+)\s*<',
- r'>\s*([\w~-]+~\d+\.\d+\.\d+\.\d+~[\w~-]+)',
- r'>\s*([\w-]+~\d{10,}~(?:[a-f\d]+:){2}:~[\w-]+)\s*<',
- r'>\s*([\w~-]+~[a-f0-9:]+~[\w~-]+)\s*<',
- r'>\s*([\w~-]+~[a-f0-9:]+~[\w~-]+)'), webpage,
- 'stream URL')
- video_url = 'https://%s/%s/%s?mime=true' % (host, self._REDIR_WORD, decoded_id)
-
- title = self._og_search_title(webpage, default=None) or self._search_regex(
- r'<span[^>]+class=["\']title["\'][^>]*>([^<]+)', webpage,
- 'title', default=None) or self._html_search_meta(
- 'description', webpage, 'title', fatal=True)
-
- entries = self._parse_html5_media_entries(page_url, webpage, video_id)
- entry = entries[0] if entries else {}
- subtitles = entry.get('subtitles')
-
- return {
- 'id': video_id,
- 'title': title,
- 'thumbnail': entry.get('thumbnail') or self._og_search_thumbnail(webpage, default=None),
- 'url': video_url,
- 'ext': determine_ext(title, None) or determine_ext(url, 'mp4'),
- 'subtitles': subtitles,
- }
-
-
-class VerystreamIE(OpenloadIE):
- IE_NAME = 'verystream'
-
- _DOMAINS = r'(?:verystream\.com)'
- _VALID_URL = r'''(?x)
- https?://
- (?P<host>
- (?:www\.)?
- %s
- )/
- (?:stream|e)/
- (?P<id>[a-zA-Z0-9-_]+)
- ''' % _DOMAINS
- _EMBED_WORD = 'e'
- _STREAM_WORD = 'stream'
- _REDIR_WORD = 'gettoken'
- _URL_IDS = ('videolink', )
- _TESTS = [{
- 'url': 'https://verystream.com/stream/c1GWQ9ngBBx/',
- 'md5': 'd3e8c5628ccb9970b65fd65269886795',
- 'info_dict': {
- 'id': 'c1GWQ9ngBBx',
- 'ext': 'mp4',
- 'title': 'Big Buck Bunny.mp4',
- 'thumbnail': r're:^https?://.*\.jpg$',
- },
- }, {
- 'url': 'https://verystream.com/e/c1GWQ9ngBBx/',
- 'only_matching': True,
- }]
-
- def _extract_decrypted_page(self, page_url, webpage, video_id):
- return webpage # for Verystream, the webpage is already decrypted
diff --git a/youtube_dl/extractor/orf.py b/youtube_dl/extractor/orf.py
index 499be0029..3425f7602 100644
--- a/youtube_dl/extractor/orf.py
+++ b/youtube_dl/extractor/orf.py
@@ -86,12 +86,13 @@ class ORFTVthekIE(InfoExtractor):
if value:
format_id_list.append(value)
format_id = '-'.join(format_id_list)
- if determine_ext(fd['src']) == 'm3u8':
+ ext = determine_ext(src)
+ if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
- fd['src'], video_id, 'mp4', m3u8_id=format_id))
- elif determine_ext(fd['src']) == 'f4m':
+ src, video_id, 'mp4', m3u8_id=format_id, fatal=False))
+ elif ext == 'f4m':
formats.extend(self._extract_f4m_formats(
- fd['src'], video_id, f4m_id=format_id))
+ src, video_id, f4m_id=format_id, fatal=False))
else:
formats.append({
'format_id': format_id,
diff --git a/youtube_dl/extractor/packtpub.py b/youtube_dl/extractor/packtpub.py
index 1324137df..11ad3b3b8 100644
--- a/youtube_dl/extractor/packtpub.py
+++ b/youtube_dl/extractor/packtpub.py
@@ -5,26 +5,27 @@ import re
from .common import InfoExtractor
from ..compat import (
- compat_str,
+ # compat_str,
compat_HTTPError,
)
from ..utils import (
clean_html,
ExtractorError,
- remove_end,
+ # remove_end,
+ str_or_none,
strip_or_none,
unified_timestamp,
- urljoin,
+ # urljoin,
)
class PacktPubBaseIE(InfoExtractor):
- _PACKT_BASE = 'https://www.packtpub.com'
- _MAPT_REST = '%s/mapt-rest' % _PACKT_BASE
+ # _PACKT_BASE = 'https://www.packtpub.com'
+ _STATIC_PRODUCTS_BASE = 'https://static.packt-cdn.com/products/'
class PacktPubIE(PacktPubBaseIE):
- _VALID_URL = r'https?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P<course_id>\d+)/(?P<chapter_id>\d+)/(?P<id>\d+)'
+ _VALID_URL = r'https?://(?:(?:www\.)?packtpub\.com/mapt|subscription\.packtpub\.com)/video/[^/]+/(?P<course_id>\d+)/(?P<chapter_id>[^/]+)/(?P<id>[^/]+)(?:/(?P<display_id>[^/?&#]+))?'
_TESTS = [{
'url': 'https://www.packtpub.com/mapt/video/web-development/9781787122215/20528/20530/Project+Intro',
@@ -40,6 +41,9 @@ class PacktPubIE(PacktPubBaseIE):
}, {
'url': 'https://subscription.packtpub.com/video/web_development/9781787122215/20528/20530/project-intro',
'only_matching': True,
+ }, {
+ 'url': 'https://subscription.packtpub.com/video/programming/9781838988906/p1/video1_1/business-card-project',
+ 'only_matching': True,
}]
_NETRC_MACHINE = 'packtpub'
_TOKEN = None
@@ -50,9 +54,9 @@ class PacktPubIE(PacktPubBaseIE):
return
try:
self._TOKEN = self._download_json(
- self._MAPT_REST + '/users/tokens', None,
+ 'https://services.packtpub.com/auth-v1/users/tokens', None,
'Downloading Authorization Token', data=json.dumps({
- 'email': username,
+ 'username': username,
'password': password,
}).encode())['data']['access']
except ExtractorError as e:
@@ -61,54 +65,40 @@ class PacktPubIE(PacktPubBaseIE):
raise ExtractorError(message, expected=True)
raise
- def _handle_error(self, response):
- if response.get('status') != 'success':
- raise ExtractorError(
- '% said: %s' % (self.IE_NAME, response['message']),
- expected=True)
-
- def _download_json(self, *args, **kwargs):
- response = super(PacktPubIE, self)._download_json(*args, **kwargs)
- self._handle_error(response)
- return response
-
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- course_id, chapter_id, video_id = mobj.group(
- 'course_id', 'chapter_id', 'id')
+ course_id, chapter_id, video_id, display_id = re.match(self._VALID_URL, url).groups()
headers = {}
if self._TOKEN:
headers['Authorization'] = 'Bearer ' + self._TOKEN
- video = self._download_json(
- '%s/users/me/products/%s/chapters/%s/sections/%s'
- % (self._MAPT_REST, course_id, chapter_id, video_id), video_id,
- 'Downloading JSON video', headers=headers)['data']
+ try:
+ video_url = self._download_json(
+ 'https://services.packtpub.com/products-v1/products/%s/%s/%s' % (course_id, chapter_id, video_id), video_id,
+ 'Downloading JSON video', headers=headers)['data']
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 400:
+ self.raise_login_required('This video is locked')
+ raise
- content = video.get('content')
- if not content:
- self.raise_login_required('This video is locked')
+ # TODO: find a better way to avoid duplicating course requests
+ # metadata = self._download_json(
+ # '%s/products/%s/chapters/%s/sections/%s/metadata'
+ # % (self._MAPT_REST, course_id, chapter_id, video_id),
+ # video_id)['data']
- video_url = content['file']
-
- metadata = self._download_json(
- '%s/products/%s/chapters/%s/sections/%s/metadata'
- % (self._MAPT_REST, course_id, chapter_id, video_id),
- video_id)['data']
-
- title = metadata['pageTitle']
- course_title = metadata.get('title')
- if course_title:
- title = remove_end(title, ' - %s' % course_title)
- timestamp = unified_timestamp(metadata.get('publicationDate'))
- thumbnail = urljoin(self._PACKT_BASE, metadata.get('filepath'))
+ # title = metadata['pageTitle']
+ # course_title = metadata.get('title')
+ # if course_title:
+ # title = remove_end(title, ' - %s' % course_title)
+ # timestamp = unified_timestamp(metadata.get('publicationDate'))
+ # thumbnail = urljoin(self._PACKT_BASE, metadata.get('filepath'))
return {
'id': video_id,
'url': video_url,
- 'title': title,
- 'thumbnail': thumbnail,
- 'timestamp': timestamp,
+ 'title': display_id or video_id, # title,
+ # 'thumbnail': thumbnail,
+ # 'timestamp': timestamp,
}
@@ -119,6 +109,7 @@ class PacktPubCourseIE(PacktPubBaseIE):
'info_dict': {
'id': '9781787122215',
'title': 'Learn Nodejs by building 12 projects [Video]',
+ 'description': 'md5:489da8d953f416e51927b60a1c7db0aa',
},
'playlist_count': 90,
}, {
@@ -136,35 +127,38 @@ class PacktPubCourseIE(PacktPubBaseIE):
url, course_id = mobj.group('url', 'id')
course = self._download_json(
- '%s/products/%s/metadata' % (self._MAPT_REST, course_id),
- course_id)['data']
+ self._STATIC_PRODUCTS_BASE + '%s/toc' % course_id, course_id)
+ metadata = self._download_json(
+ self._STATIC_PRODUCTS_BASE + '%s/summary' % course_id,
+ course_id, fatal=False) or {}
entries = []
- for chapter_num, chapter in enumerate(course['tableOfContents'], 1):
- if chapter.get('type') != 'chapter':
- continue
- children = chapter.get('children')
- if not isinstance(children, list):
+ for chapter_num, chapter in enumerate(course['chapters'], 1):
+ chapter_id = str_or_none(chapter.get('id'))
+ sections = chapter.get('sections')
+ if not chapter_id or not isinstance(sections, list):
continue
chapter_info = {
'chapter': chapter.get('title'),
'chapter_number': chapter_num,
- 'chapter_id': chapter.get('id'),
+ 'chapter_id': chapter_id,
}
- for section in children:
- if section.get('type') != 'section':
- continue
- section_url = section.get('seoUrl')
- if not isinstance(section_url, compat_str):
+ for section in sections:
+ section_id = str_or_none(section.get('id'))
+ if not section_id or section.get('contentType') != 'video':
continue
entry = {
'_type': 'url_transparent',
- 'url': urljoin(url + '/', section_url),
+ 'url': '/'.join([url, chapter_id, section_id]),
'title': strip_or_none(section.get('title')),
'description': clean_html(section.get('summary')),
+ 'thumbnail': metadata.get('coverImage'),
+ 'timestamp': unified_timestamp(metadata.get('publicationDate')),
'ie_key': PacktPubIE.ie_key(),
}
entry.update(chapter_info)
entries.append(entry)
- return self.playlist_result(entries, course_id, course.get('title'))
+ return self.playlist_result(
+ entries, course_id, metadata.get('title'),
+ clean_html(metadata.get('about')))
diff --git a/youtube_dl/extractor/patreon.py b/youtube_dl/extractor/patreon.py
index 426dd8121..761a4b1de 100644
--- a/youtube_dl/extractor/patreon.py
+++ b/youtube_dl/extractor/patreon.py
@@ -6,7 +6,11 @@ from ..utils import (
clean_html,
determine_ext,
int_or_none,
+ KNOWN_EXTENSIONS,
+ mimetype2ext,
parse_iso8601,
+ str_or_none,
+ try_get,
)
@@ -24,6 +28,7 @@ class PatreonIE(InfoExtractor):
'thumbnail': 're:^https?://.*$',
'timestamp': 1406473987,
'upload_date': '20140727',
+ 'uploader_id': '87145',
},
}, {
'url': 'http://www.patreon.com/creation?hid=754133',
@@ -90,7 +95,13 @@ class PatreonIE(InfoExtractor):
def _real_extract(self, url):
video_id = self._match_id(url)
post = self._download_json(
- 'https://www.patreon.com/api/posts/' + video_id, video_id)
+ 'https://www.patreon.com/api/posts/' + video_id, video_id, query={
+ 'fields[media]': 'download_url,mimetype,size_bytes',
+ 'fields[post]': 'comment_count,content,embed,image,like_count,post_file,published_at,title',
+ 'fields[user]': 'full_name,url',
+ 'json-api-use-default-includes': 'false',
+ 'include': 'media,user',
+ })
attributes = post['data']['attributes']
title = attributes['title'].strip()
image = attributes.get('image') or {}
@@ -104,33 +115,42 @@ class PatreonIE(InfoExtractor):
'comment_count': int_or_none(attributes.get('comment_count')),
}
- def add_file(file_data):
- file_url = file_data.get('url')
- if file_url:
- info.update({
- 'url': file_url,
- 'ext': determine_ext(file_data.get('name'), 'mp3'),
- })
-
for i in post.get('included', []):
i_type = i.get('type')
- if i_type == 'attachment':
- add_file(i.get('attributes') or {})
+ if i_type == 'media':
+ media_attributes = i.get('attributes') or {}
+ download_url = media_attributes.get('download_url')
+ ext = mimetype2ext(media_attributes.get('mimetype'))
+ if download_url and ext in KNOWN_EXTENSIONS:
+ info.update({
+ 'ext': ext,
+ 'filesize': int_or_none(media_attributes.get('size_bytes')),
+ 'url': download_url,
+ })
elif i_type == 'user':
user_attributes = i.get('attributes')
if user_attributes:
info.update({
'uploader': user_attributes.get('full_name'),
+ 'uploader_id': str_or_none(i.get('id')),
'uploader_url': user_attributes.get('url'),
})
if not info.get('url'):
- add_file(attributes.get('post_file') or {})
+ embed_url = try_get(attributes, lambda x: x['embed']['url'])
+ if embed_url:
+ info.update({
+ '_type': 'url',
+ 'url': embed_url,
+ })
if not info.get('url'):
- info.update({
- '_type': 'url',
- 'url': attributes['embed']['url'],
- })
+ post_file = attributes['post_file']
+ ext = determine_ext(post_file.get('name'))
+ if ext in KNOWN_EXTENSIONS:
+ info.update({
+ 'ext': ext,
+ 'url': post_file['url'],
+ })
return info
diff --git a/youtube_dl/extractor/peertube.py b/youtube_dl/extractor/peertube.py
index e03c3d1d3..d3a83ea2b 100644
--- a/youtube_dl/extractor/peertube.py
+++ b/youtube_dl/extractor/peertube.py
@@ -18,81 +18,385 @@ from ..utils import (
class PeerTubeIE(InfoExtractor):
_INSTANCES_RE = r'''(?:
# Taken from https://instances.joinpeertube.org/instances
+ peertube\.rainbowswingers\.net|
+ tube\.stanisic\.nl|
+ peer\.suiri\.us|
+ medias\.libox\.fr|
+ videomensoif\.ynh\.fr|
+ peertube\.travelpandas\.eu|
+ peertube\.rachetjay\.fr|
+ peertube\.montecsys\.fr|
+ tube\.eskuero\.me|
+ peer\.tube|
+ peertube\.umeahackerspace\.se|
+ tube\.nx-pod\.de|
+ video\.monsieurbidouille\.fr|
tube\.openalgeria\.org|
- peertube\.pointsecu\.fr|
+ vid\.lelux\.fi|
+ video\.anormallostpod\.ovh|
+ tube\.crapaud-fou\.org|
+ peertube\.stemy\.me|
+ lostpod\.space|
+ exode\.me|
+ peertube\.snargol\.com|
+ vis\.ion\.ovh|
+ videosdulib\.re|
+ v\.mbius\.io|
+ videos\.judrey\.eu|
+ peertube\.osureplayviewer\.xyz|
+ peertube\.mathieufamily\.ovh|
+ www\.videos-libr\.es|
+ fightforinfo\.com|
+ peertube\.fediverse\.ru|
+ peertube\.oiseauroch\.fr|
+ video\.nesven\.eu|
+ v\.bearvideo\.win|
+ video\.qoto\.org|
+ justporn\.cc|
+ video\.vny\.fr|
+ peervideo\.club|
+ tube\.taker\.fr|
+ peertube\.chantierlibre\.org|
+ tube\.ipfixe\.info|
+ tube\.kicou\.info|
+ tube\.dodsorf\.as|
+ videobit\.cc|
+ video\.yukari\.moe|
+ videos\.elbinario\.net|
+ hkvideo\.live|
+ pt\.tux\.tf|
+ www\.hkvideo\.live|
+ FIGHTFORINFO\.com|
+ pt\.765racing\.com|
+ peertube\.gnumeria\.eu\.org|
+ nordenmedia\.com|
+ peertube\.co\.uk|
+ tube\.darfweb\.eu|
+ tube\.kalah-france\.org|
+ 0ch\.in|
+ vod\.mochi\.academy|
+ film\.node9\.org|
+ peertube\.hatthieves\.es|
+ video\.fitchfamily\.org|
+ peertube\.ddns\.net|
+ video\.ifuncle\.kr|
+ video\.fdlibre\.eu|
+ tube\.22decembre\.eu|
+ peertube\.harmoniescreatives\.com|
+ tube\.fabrigli\.fr|
+ video\.thedwyers\.co|
+ video\.bruitbruit\.com|
+ peertube\.foxfam\.club|
+ peer\.philoxweb\.be|
+ videos\.bugs\.social|
+ peertube\.malbert\.xyz|
+ peertube\.bilange\.ca|
+ libretube\.net|
+ diytelevision\.com|
+ peertube\.fedilab\.app|
+ libre\.video|
+ video\.mstddntfdn\.online|
+ us\.tv|
+ peertube\.sl-network\.fr|
+ peertube\.dynlinux\.io|
+ peertube\.david\.durieux\.family|
+ peertube\.linuxrocks\.online|
+ peerwatch\.xyz|
+ v\.kretschmann\.social|
+ tube\.otter\.sh|
+ yt\.is\.nota\.live|
+ tube\.dragonpsi\.xyz|
+ peertube\.boneheadmedia\.com|
+ videos\.funkwhale\.audio|
+ watch\.44con\.com|
+ peertube\.gcaillaut\.fr|
+ peertube\.icu|
+ pony\.tube|
+ spacepub\.space|
+ tube\.stbr\.io|
+ v\.mom-gay\.faith|
+ tube\.port0\.xyz|
+ peertube\.simounet\.net|
+ play\.jergefelt\.se|
+ peertube\.zeteo\.me|
+ tube\.danq\.me|
+ peertube\.kerenon\.com|
+ tube\.fab-l3\.org|
+ tube\.calculate\.social|
+ peertube\.mckillop\.org|
+ tube\.netzspielplatz\.de|
+ vod\.ksite\.de|
+ peertube\.laas\.fr|
+ tube\.govital\.net|
+ peertube\.stephenson\.cc|
+ bistule\.nohost\.me|
+ peertube\.kajalinifi\.de|
+ video\.ploud\.jp|
+ video\.omniatv\.com|
+ peertube\.ffs2play\.fr|
+ peertube\.leboulaire\.ovh|
+ peertube\.tronic-studio\.com|
+ peertube\.public\.cat|
+ peertube\.metalbanana\.net|
+ video\.1000i100\.fr|
+ peertube\.alter-nativ-voll\.de|
+ tube\.pasa\.tf|
+ tube\.worldofhauru\.xyz|
+ pt\.kamp\.site|
+ peertube\.teleassist\.fr|
+ videos\.mleduc\.xyz|
+ conf\.tube|
+ media\.privacyinternational\.org|
+ pt\.forty-two\.nl|
+ video\.halle-leaks\.de|
+ video\.grosskopfgames\.de|
+ peertube\.schaeferit\.de|
+ peertube\.jackbot\.fr|
+ tube\.extinctionrebellion\.fr|
+ peertube\.f-si\.org|
+ video\.subak\.ovh|
+ videos\.koweb\.fr|
+ peertube\.zergy\.net|
+ peertube\.roflcopter\.fr|
+ peertube\.floss-marketing-school\.com|
+ vloggers\.social|
+ peertube\.iriseden\.eu|
+ videos\.ubuntu-paris\.org|
+ peertube\.mastodon\.host|
+ armstube\.com|
+ peertube\.s2s\.video|
+ peertube\.lol|
+ tube\.open-plug\.eu|
+ open\.tube|
+ peertube\.ch|
+ peertube\.normandie-libre\.fr|
+ peertube\.slat\.org|
+ video\.lacaveatonton\.ovh|
+ peertube\.uno|
+ peertube\.servebeer\.com|
+ peertube\.fedi\.quebec|
+ tube\.h3z\.jp|
+ tube\.plus200\.com|
+ peertube\.eric\.ovh|
+ tube\.metadocs\.cc|
+ tube\.unmondemeilleur\.eu|
+ gouttedeau\.space|
+ video\.antirep\.net|
+ nrop\.cant\.at|
+ tube\.ksl-bmx\.de|
+ tube\.plaf\.fr|
+ tube\.tchncs\.de|
+ video\.devinberg\.com|
+ hitchtube\.fr|
+ peertube\.kosebamse\.com|
+ yunopeertube\.myddns\.me|
+ peertube\.varney\.fr|
+ peertube\.anon-kenkai\.com|
+ tube\.maiti\.info|
+ tubee\.fr|
+ videos\.dinofly\.com|
+ toobnix\.org|
+ videotape\.me|
+ voca\.tube|
+ video\.heromuster\.com|
+ video\.lemediatv\.fr|
+ video\.up\.edu\.ph|
+ balafon\.video|
+ video\.ivel\.fr|
+ thickrips\.cloud|
+ pt\.laurentkruger\.fr|
+ video\.monarch-pass\.net|
+ peertube\.artica\.center|
+ video\.alternanet\.fr|
+ indymotion\.fr|
+ fanvid\.stopthatimp\.net|
+ video\.farci\.org|
+ v\.lesterpig\.com|
+ video\.okaris\.de|
+ tube\.pawelko\.net|
+ peertube\.mablr\.org|
+ tube\.fede\.re|
+ pytu\.be|
+ evertron\.tv|
+ devtube\.dev-wiki\.de|
+ raptube\.antipub\.org|
+ video\.selea\.se|
+ peertube\.mygaia\.org|
+ video\.oh14\.de|
+ peertube\.livingutopia\.org|
+ peertube\.the-penguin\.de|
+ tube\.thechangebook\.org|
+ tube\.anjara\.eu|
+ pt\.pube\.tk|
+ video\.samedi\.pm|
+ mplayer\.demouliere\.eu|
+ widemus\.de|
+ peertube\.me|
+ peertube\.zapashcanon\.fr|
+ video\.latavernedejohnjohn\.fr|
+ peertube\.pcservice46\.fr|
+ peertube\.mazzonetto\.eu|
+ video\.irem\.univ-paris-diderot\.fr|
+ video\.livecchi\.cloud|
+ alttube\.fr|
+ video\.coop\.tools|
+ video\.cabane-libre\.org|
+ peertube\.openstreetmap\.fr|
+ videos\.alolise\.org|
+ irrsinn\.video|
+ video\.antopie\.org|
+ scitech\.video|
+ tube2\.nemsia\.org|
+ video\.amic37\.fr|
+ peertube\.freeforge\.eu|
+ video\.arbitrarion\.com|
+ video\.datsemultimedia\.com|
+ stoptrackingus\.tv|
+ peertube\.ricostrongxxx\.com|
+ docker\.videos\.lecygnenoir\.info|
+ peertube\.togart\.de|
+ tube\.postblue\.info|
+ videos\.domainepublic\.net|
+ peertube\.cyber-tribal\.com|
+ video\.gresille\.org|
+ peertube\.dsmouse\.net|
+ cinema\.yunohost\.support|
+ tube\.theocevaer\.fr|
+ repro\.video|
+ tube\.4aem\.com|
+ quaziinc\.com|
+ peertube\.metawurst\.space|
+ videos\.wakapo\.com|
+ video\.ploud\.fr|
+ video\.freeradical\.zone|
+ tube\.valinor\.fr|
+ refuznik\.video|
+ pt\.kircheneuenburg\.de|
+ peertube\.asrun\.eu|
+ peertube\.lagob\.fr|
+ videos\.side-ways\.net|
+ 91video\.online|
+ video\.valme\.io|
+ video\.taboulisme\.com|
+ videos-libr\.es|
+ tv\.mooh\.fr|
+ nuage\.acostey\.fr|
+ video\.monsieur-a\.fr|
+ peertube\.librelois\.fr|
+ videos\.pair2jeux\.tube|
+ videos\.pueseso\.club|
+ peer\.mathdacloud\.ovh|
+ media\.assassinate-you\.net|
+ vidcommons\.org|
+ ptube\.rousset\.nom\.fr|
+ tube\.cyano\.at|
+ videos\.squat\.net|
+ video\.iphodase\.fr|
+ peertube\.makotoworkshop\.org|
+ peertube\.serveur\.slv-valbonne\.fr|
+ vault\.mle\.party|
+ hostyour\.tv|
+ videos\.hack2g2\.fr|
+ libre\.tube|
+ pire\.artisanlogiciel\.net|
+ videos\.numerique-en-commun\.fr|
+ video\.netsyms\.com|
+ video\.die-partei\.social|
+ video\.writeas\.org|
+ peertube\.swarm\.solvingmaz\.es|
+ tube\.pericoloso\.ovh|
+ watching\.cypherpunk\.observer|
+ videos\.adhocmusic\.com|
+ tube\.rfc1149\.net|
+ peertube\.librelabucm\.org|
+ videos\.numericoop\.fr|
+ peertube\.koehn\.com|
+ peertube\.anarchmusicall\.net|
+ tube\.kampftoast\.de|
+ vid\.y-y\.li|
+ peertube\.xtenz\.xyz|
+ diode\.zone|
+ tube\.egf\.mn|
+ peertube\.nomagic\.uk|
+ visionon\.tv|
+ videos\.koumoul\.com|
+ video\.rastapuls\.com|
+ video\.mantlepro\.com|
+ video\.deadsuperhero\.com|
+ peertube\.musicstudio\.pro|
+ peertube\.we-keys\.fr|
+ artitube\.artifaille\.fr|
+ peertube\.ethernia\.net|
+ tube\.midov\.pl|
+ peertube\.fr|
+ watch\.snoot\.tube|
+ peertube\.donnadieu\.fr|
+ argos\.aquilenet\.fr|
+ tube\.nemsia\.org|
+ tube\.bruniau\.net|
+ videos\.darckoune\.moe|
+ tube\.traydent\.info|
+ dev\.videos\.lecygnenoir\.info|
+ peertube\.nayya\.org|
+ peertube\.live|
+ peertube\.mofgao\.space|
+ video\.lequerrec\.eu|
+ peertube\.amicale\.net|
+ aperi\.tube|
+ tube\.ac-lyon\.fr|
+ video\.lw1\.at|
+ www\.yiny\.org|
+ videos\.pofilo\.fr|
+ tube\.lou\.lt|
+ choob\.h\.etbus\.ch|
+ tube\.hoga\.fr|
+ peertube\.heberge\.fr|
+ video\.obermui\.de|
+ videos\.cloudfrancois\.fr|
+ betamax\.video|
+ video\.typica\.us|
+ tube\.piweb\.be|
+ video\.blender\.org|
+ peertube\.cat|
+ tube\.kdy\.ch|
+ pe\.ertu\.be|
+ peertube\.social|
+ videos\.lescommuns\.org|
+ tv\.datamol\.org|
+ videonaute\.fr|
+ dialup\.express|
peertube\.nogafa\.org|
- peertube\.pl|
megatube\.lilomoino\.fr|
peertube\.tamanoir\.foucry\.net|
- peertube\.inapurna\.org|
- peertube\.netzspielplatz\.de|
- video\.deadsuperhero\.com|
peertube\.devosi\.org|
peertube\.1312\.media|
- tube\.worldofhauru\.xyz|
tube\.bootlicker\.party|
skeptikon\.fr|
- peertube\.geekshell\.fr|
- tube\.opportunis\.me|
- peertube\.peshane\.net|
video\.blueline\.mg|
tube\.homecomputing\.fr|
- videos\.cloudfrancois\.fr|
- peertube\.viviers-fibre\.net|
tube\.ouahpiti\.info|
video\.tedomum\.net|
video\.g3l\.org|
fontube\.fr|
peertube\.gaialabs\.ch|
- peertube\.extremely\.online|
- peertube\.public-infrastructure\.eu|
tube\.kher\.nl|
peertube\.qtg\.fr|
- tube\.22decembre\.eu|
- facegirl\.me|
video\.migennes\.net|
- janny\.moe|
tube\.p2p\.legal|
- video\.atlanti\.se|
troll\.tv|
- peertube\.geekael\.fr|
- vid\.leotindall\.com|
- video\.anormallostpod\.ovh|
- p-tube\.h3z\.jp|
- tube\.darfweb\.eu|
videos\.iut-orsay\.fr|
peertube\.solidev\.net|
- videos\.symphonie-of-code\.fr|
- testtube\.ortg\.de|
videos\.cemea\.org|
- peertube\.gwendalavir\.eu|
video\.passageenseine\.fr|
videos\.festivalparminous\.org|
peertube\.touhoppai\.moe|
- peertube\.duckdns\.org|
sikke\.fi|
- peertube\.mastodon\.host|
- firedragonvideos\.com|
- vidz\.dou\.bet|
- peertube\.koehn\.com|
peer\.hostux\.social|
share\.tube|
peertube\.walkingmountains\.fr|
- medias\.libox\.fr|
- peertube\.moe|
- peertube\.xyz|
- jp\.peertube\.network|
videos\.benpro\.fr|
- tube\.otter\.sh|
- peertube\.angristan\.xyz|
peertube\.parleur\.net|
- peer\.ecutsa\.fr|
peertube\.heraut\.eu|
- peertube\.tifox\.fr|
- peertube\.maly\.io|
- vod\.mochi\.academy|
- exode\.me|
- coste\.video|
tube\.aquilenet\.fr|
peertube\.gegeweb\.eu|
framatube\.org|
@@ -100,18 +404,11 @@ class PeerTubeIE(InfoExtractor):
tube\.conferences-gesticulees\.net|
peertube\.datagueule\.tv|
video\.lqdn\.fr|
- meilleurtube\.delire\.party|
tube\.mochi\.academy|
- peertube\.dav\.li|
media\.zat\.im|
- pytu\.be|
- peertube\.valvin\.fr|
- peertube\.nsa\.ovh|
video\.colibris-outilslibres\.org|
- video\.hispagatos\.org|
tube\.svnet\.fr|
peertube\.video|
- videos\.lecygnenoir\.info|
peertube3\.cpy\.re|
peertube2\.cpy\.re|
videos\.tcit\.fr|
@@ -126,7 +423,7 @@ class PeerTubeIE(InfoExtractor):
(?P<id>%s)
''' % (_INSTANCES_RE, _UUID_RE)
_TESTS = [{
- 'url': 'https://peertube.moe/videos/watch/2790feb0-8120-4e63-9af3-c943c69f5e6c',
+ 'url': 'https://peertube.cpy.re/videos/watch/2790feb0-8120-4e63-9af3-c943c69f5e6c',
'md5': '80f24ff364cc9d333529506a263e7feb',
'info_dict': {
'id': '2790feb0-8120-4e63-9af3-c943c69f5e6c',
@@ -168,7 +465,7 @@ class PeerTubeIE(InfoExtractor):
@staticmethod
def _extract_peertube_url(webpage, source_url):
mobj = re.match(
- r'https?://(?P<host>[^/]+)/videos/watch/(?P<id>%s)'
+ r'https?://(?P<host>[^/]+)/videos/(?:watch|embed)/(?P<id>%s)'
% PeerTubeIE._UUID_RE, source_url)
if mobj and any(p in webpage for p in (
'<title>PeerTube<',
diff --git a/youtube_dl/extractor/periscope.py b/youtube_dl/extractor/periscope.py
index b337a56c0..c02e34aba 100644
--- a/youtube_dl/extractor/periscope.py
+++ b/youtube_dl/extractor/periscope.py
@@ -17,12 +17,54 @@ class PeriscopeBaseIE(InfoExtractor):
'https://api.periscope.tv/api/v2/%s' % method,
item_id, query=query)
+ def _parse_broadcast_data(self, broadcast, video_id):
+ title = broadcast['status']
+ uploader = broadcast.get('user_display_name') or broadcast.get('username')
+ title = '%s - %s' % (uploader, title) if uploader else title
+ is_live = broadcast.get('state').lower() == 'running'
+
+ thumbnails = [{
+ 'url': broadcast[image],
+ } for image in ('image_url', 'image_url_small') if broadcast.get(image)]
+
+ return {
+ 'id': broadcast.get('id') or video_id,
+ 'title': self._live_title(title) if is_live else title,
+ 'timestamp': parse_iso8601(broadcast.get('created_at')),
+ 'uploader': uploader,
+ 'uploader_id': broadcast.get('user_id') or broadcast.get('username'),
+ 'thumbnails': thumbnails,
+ 'view_count': int_or_none(broadcast.get('total_watched')),
+ 'tags': broadcast.get('tags'),
+ 'is_live': is_live,
+ }
+
+ @staticmethod
+ def _extract_common_format_info(broadcast):
+ return broadcast.get('state').lower(), int_or_none(broadcast.get('width')), int_or_none(broadcast.get('height'))
+
+ @staticmethod
+ def _add_width_and_height(f, width, height):
+ for key, val in (('width', width), ('height', height)):
+ if not f.get(key):
+ f[key] = val
+
+ def _extract_pscp_m3u8_formats(self, m3u8_url, video_id, format_id, state, width, height, fatal=True):
+ m3u8_formats = self._extract_m3u8_formats(
+ m3u8_url, video_id, 'mp4',
+ entry_protocol='m3u8_native'
+ if state in ('ended', 'timed_out') else 'm3u8',
+ m3u8_id=format_id, fatal=fatal)
+ if len(m3u8_formats) == 1:
+ self._add_width_and_height(m3u8_formats[0], width, height)
+ return m3u8_formats
+
class PeriscopeIE(PeriscopeBaseIE):
IE_DESC = 'Periscope'
IE_NAME = 'periscope'
_VALID_URL = r'https?://(?:www\.)?(?:periscope|pscp)\.tv/[^/]+/(?P<id>[^/?#]+)'
- # Alive example URLs can be found here http://onperiscope.com/
+ # Alive example URLs can be found here https://www.periscope.tv/
_TESTS = [{
'url': 'https://www.periscope.tv/w/aJUQnjY3MjA3ODF8NTYxMDIyMDl2zCg2pECBgwTqRpQuQD352EMPTKQjT4uqlM3cgWFA-g==',
'md5': '65b57957972e503fcbbaeed8f4fa04ca',
@@ -61,21 +103,9 @@ class PeriscopeIE(PeriscopeBaseIE):
'accessVideoPublic', {'broadcast_id': token}, token)
broadcast = stream['broadcast']
- title = broadcast['status']
+ info = self._parse_broadcast_data(broadcast, token)
- uploader = broadcast.get('user_display_name') or broadcast.get('username')
- uploader_id = (broadcast.get('user_id') or broadcast.get('username'))
-
- title = '%s - %s' % (uploader, title) if uploader else title
state = broadcast.get('state').lower()
- if state == 'running':
- title = self._live_title(title)
- timestamp = parse_iso8601(broadcast.get('created_at'))
-
- thumbnails = [{
- 'url': broadcast[image],
- } for image in ('image_url', 'image_url_small') if broadcast.get(image)]
-
width = int_or_none(broadcast.get('width'))
height = int_or_none(broadcast.get('height'))
@@ -92,32 +122,20 @@ class PeriscopeIE(PeriscopeBaseIE):
continue
video_urls.add(video_url)
if format_id != 'rtmp':
- m3u8_formats = self._extract_m3u8_formats(
- video_url, token, 'mp4',
- entry_protocol='m3u8_native'
- if state in ('ended', 'timed_out') else 'm3u8',
- m3u8_id=format_id, fatal=False)
- if len(m3u8_formats) == 1:
- add_width_and_height(m3u8_formats[0])
+ m3u8_formats = self._extract_pscp_m3u8_formats(
+ video_url, token, format_id, state, width, height, False)
formats.extend(m3u8_formats)
continue
rtmp_format = {
'url': video_url,
'ext': 'flv' if format_id == 'rtmp' else 'mp4',
}
- add_width_and_height(rtmp_format)
+ self._add_width_and_height(rtmp_format)
formats.append(rtmp_format)
self._sort_formats(formats)
- return {
- 'id': broadcast.get('id') or token,
- 'title': title,
- 'timestamp': timestamp,
- 'uploader': uploader,
- 'uploader_id': uploader_id,
- 'thumbnails': thumbnails,
- 'formats': formats,
- }
+ info['formats'] = formats
+ return info
class PeriscopeUserIE(PeriscopeBaseIE):
diff --git a/youtube_dl/extractor/philharmoniedeparis.py b/youtube_dl/extractor/philharmoniedeparis.py
index f723a2b3b..03da64b11 100644
--- a/youtube_dl/extractor/philharmoniedeparis.py
+++ b/youtube_dl/extractor/philharmoniedeparis.py
@@ -14,7 +14,7 @@ class PhilharmonieDeParisIE(InfoExtractor):
_VALID_URL = r'''(?x)
https?://
(?:
- live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|misc/Playlist\.ashx\?id=)|
+ live\.philharmoniedeparis\.fr/(?:[Cc]oncert/|embed(?:app)?/|misc/Playlist\.ashx\?id=)|
pad\.philharmoniedeparis\.fr/doc/CIMU/
)
(?P<id>\d+)
@@ -40,6 +40,12 @@ class PhilharmonieDeParisIE(InfoExtractor):
}, {
'url': 'http://live.philharmoniedeparis.fr/misc/Playlist.ashx?id=1030324&track=&lang=fr',
'only_matching': True,
+ }, {
+ 'url': 'https://live.philharmoniedeparis.fr/embedapp/1098406/berlioz-fantastique-lelio-les-siecles-national-youth-choir-of.html?lang=fr-FR',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://live.philharmoniedeparis.fr/embed/1098406/berlioz-fantastique-lelio-les-siecles-national-youth-choir-of.html?lang=fr-FR',
+ 'only_matching': True,
}]
_LIVE_URL = 'https://live.philharmoniedeparis.fr'
diff --git a/youtube_dl/extractor/piksel.py b/youtube_dl/extractor/piksel.py
index c0c276a50..88b6859b0 100644
--- a/youtube_dl/extractor/piksel.py
+++ b/youtube_dl/extractor/piksel.py
@@ -15,18 +15,17 @@ from ..utils import (
class PikselIE(InfoExtractor):
- _VALID_URL = r'https?://player\.piksel\.com/v/(?P<id>[a-z0-9]+)'
+ _VALID_URL = r'https?://player\.piksel\.com/v/(?:refid/[^/]+/prefid/)?(?P<id>[a-z0-9_]+)'
_TESTS = [
{
- 'url': 'http://player.piksel.com/v/nv60p12f',
- 'md5': 'd9c17bbe9c3386344f9cfd32fad8d235',
+ 'url': 'http://player.piksel.com/v/ums2867l',
+ 'md5': '34e34c8d89dc2559976a6079db531e85',
'info_dict': {
- 'id': 'nv60p12f',
+ 'id': 'ums2867l',
'ext': 'mp4',
- 'title': 'فن الحياة - الحلقة 1',
- 'description': 'احدث برامج الداعية الاسلامي " مصطفي حسني " فى رمضان 2016علي النهار نور',
- 'timestamp': 1465231790,
- 'upload_date': '20160606',
+ 'title': 'GX-005 with Caption',
+ 'timestamp': 1481335659,
+ 'upload_date': '20161210'
}
},
{
@@ -39,8 +38,13 @@ class PikselIE(InfoExtractor):
'title': 'WAW- State of Washington vs. Donald J. Trump, et al',
'description': 'State of Washington vs. Donald J. Trump, et al, Case Number 17-CV-00141-JLR, TRO Hearing, Civil Rights Case, 02/3/2017, 1:00 PM (PST), Seattle Federal Courthouse, Seattle, WA, Judge James L. Robart presiding.',
'timestamp': 1486171129,
- 'upload_date': '20170204',
+ 'upload_date': '20170204'
}
+ },
+ {
+ # https://www3.nhk.or.jp/nhkworld/en/ondemand/video/2019240/
+ 'url': 'http://player.piksel.com/v/refid/nhkworld/prefid/nw_vod_v_en_2019_240_20190823233000_02_1566873477',
+ 'only_matching': True,
}
]
@@ -53,8 +57,11 @@ class PikselIE(InfoExtractor):
return mobj.group('url')
def _real_extract(self, url):
- video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
+ display_id = self._match_id(url)
+ webpage = self._download_webpage(url, display_id)
+ video_id = self._search_regex(
+ r'data-de-program-uuid=[\'"]([a-z0-9]+)',
+ webpage, 'program uuid', default=display_id)
app_token = self._search_regex([
r'clientAPI\s*:\s*"([^"]+)"',
r'data-de-api-key\s*=\s*"([^"]+)"'
@@ -113,6 +120,13 @@ class PikselIE(InfoExtractor):
})
self._sort_formats(formats)
+ subtitles = {}
+ for caption in video_data.get('captions', []):
+ caption_url = caption.get('url')
+ if caption_url:
+ subtitles.setdefault(caption.get('locale', 'en'), []).append({
+ 'url': caption_url})
+
return {
'id': video_id,
'title': title,
@@ -120,4 +134,5 @@ class PikselIE(InfoExtractor):
'thumbnail': video_data.get('thumbnailUrl'),
'timestamp': parse_iso8601(video_data.get('dateadd')),
'formats': formats,
+ 'subtitles': subtitles,
}
diff --git a/youtube_dl/extractor/platzi.py b/youtube_dl/extractor/platzi.py
index 557b2b5ad..602207beb 100644
--- a/youtube_dl/extractor/platzi.py
+++ b/youtube_dl/extractor/platzi.py
@@ -18,43 +18,10 @@ from ..utils import (
)
-class PlatziIE(InfoExtractor):
- _VALID_URL = r'''(?x)
- https?://
- (?:
- platzi\.com/clases| # es version
- courses\.platzi\.com/classes # en version
- )/[^/]+/(?P<id>\d+)-[^/?\#&]+
- '''
+class PlatziBaseIE(InfoExtractor):
_LOGIN_URL = 'https://platzi.com/login/'
_NETRC_MACHINE = 'platzi'
- _TESTS = [{
- 'url': 'https://platzi.com/clases/1311-next-js/12074-creando-nuestra-primera-pagina/',
- 'md5': '8f56448241005b561c10f11a595b37e3',
- 'info_dict': {
- 'id': '12074',
- 'ext': 'mp4',
- 'title': 'Creando nuestra primera página',
- 'description': 'md5:4c866e45034fc76412fbf6e60ae008bc',
- 'duration': 420,
- },
- 'skip': 'Requires platzi account credentials',
- }, {
- 'url': 'https://courses.platzi.com/classes/1367-communication-codestream/13430-background/',
- 'info_dict': {
- 'id': '13430',
- 'ext': 'mp4',
- 'title': 'Background',
- 'description': 'md5:49c83c09404b15e6e71defaf87f6b305',
- 'duration': 360,
- },
- 'skip': 'Requires platzi account credentials',
- 'params': {
- 'skip_download': True,
- },
- }]
-
def _real_initialize(self):
self._login()
@@ -97,6 +64,42 @@ class PlatziIE(InfoExtractor):
'Unable to login: %s' % error, expected=True)
raise ExtractorError('Unable to log in')
+
+class PlatziIE(PlatziBaseIE):
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:
+ platzi\.com/clases| # es version
+ courses\.platzi\.com/classes # en version
+ )/[^/]+/(?P<id>\d+)-[^/?\#&]+
+ '''
+
+ _TESTS = [{
+ 'url': 'https://platzi.com/clases/1311-next-js/12074-creando-nuestra-primera-pagina/',
+ 'md5': '8f56448241005b561c10f11a595b37e3',
+ 'info_dict': {
+ 'id': '12074',
+ 'ext': 'mp4',
+ 'title': 'Creando nuestra primera página',
+ 'description': 'md5:4c866e45034fc76412fbf6e60ae008bc',
+ 'duration': 420,
+ },
+ 'skip': 'Requires platzi account credentials',
+ }, {
+ 'url': 'https://courses.platzi.com/classes/1367-communication-codestream/13430-background/',
+ 'info_dict': {
+ 'id': '13430',
+ 'ext': 'mp4',
+ 'title': 'Background',
+ 'description': 'md5:49c83c09404b15e6e71defaf87f6b305',
+ 'duration': 360,
+ },
+ 'skip': 'Requires platzi account credentials',
+ 'params': {
+ 'skip_download': True,
+ },
+ }]
+
def _real_extract(self, url):
lecture_id = self._match_id(url)
@@ -104,7 +107,11 @@ class PlatziIE(InfoExtractor):
data = self._parse_json(
self._search_regex(
- r'client_data\s*=\s*({.+?})\s*;', webpage, 'client data'),
+ # client_data may contain "};" so that we have to try more
+ # strict regex first
+ (r'client_data\s*=\s*({.+?})\s*;\s*\n',
+ r'client_data\s*=\s*({.+?})\s*;'),
+ webpage, 'client data'),
lecture_id)
material = data['initialState']['material']
@@ -146,7 +153,7 @@ class PlatziIE(InfoExtractor):
}
-class PlatziCourseIE(InfoExtractor):
+class PlatziCourseIE(PlatziBaseIE):
_VALID_URL = r'''(?x)
https?://
(?:
diff --git a/youtube_dl/extractor/porn91.py b/youtube_dl/extractor/porn91.py
index 24c3600fe..20eac647a 100644
--- a/youtube_dl/extractor/porn91.py
+++ b/youtube_dl/extractor/porn91.py
@@ -39,7 +39,12 @@ class Porn91IE(InfoExtractor):
r'<div id="viewvideo-title">([^<]+)</div>', webpage, 'title')
title = title.replace('\n', '')
- info_dict = self._parse_html5_media_entries(url, webpage, video_id)[0]
+ video_link_url = self._search_regex(
+ r'<textarea[^>]+id=["\']fm-video_link[^>]+>([^<]+)</textarea>',
+ webpage, 'video link')
+ videopage = self._download_webpage(video_link_url, video_id)
+
+ info_dict = self._parse_html5_media_entries(url, videopage, video_id)[0]
duration = parse_duration(self._search_regex(
r'时长:\s*</span>\s*(\d+:\d+)', webpage, 'duration', fatal=False))
diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py
index 11b8cfcf7..b3251ccd9 100644
--- a/youtube_dl/extractor/pornhub.py
+++ b/youtube_dl/extractor/pornhub.py
@@ -17,6 +17,7 @@ from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
+ NO_DEFAULT,
orderedSet,
remove_quotes,
str_to_int,
@@ -227,12 +228,13 @@ class PornHubIE(PornHubBaseIE):
else:
thumbnail, duration = [None] * 2
- if not video_urls:
- tv_webpage = dl_webpage('tv')
-
+ def extract_js_vars(webpage, pattern, default=NO_DEFAULT):
assignments = self._search_regex(
- r'(var.+?mediastring.+?)</script>', tv_webpage,
- 'encoded url').split(';')
+ pattern, webpage, 'encoded url', default=default)
+ if not assignments:
+ return {}
+
+ assignments = assignments.split(';')
js_vars = {}
@@ -254,11 +256,35 @@ class PornHubIE(PornHubBaseIE):
assn = re.sub(r'var\s+', '', assn)
vname, value = assn.split('=', 1)
js_vars[vname] = parse_js_value(value)
+ return js_vars
- video_url = js_vars['mediastring']
- if video_url not in video_urls_set:
- video_urls.append((video_url, None))
- video_urls_set.add(video_url)
+ def add_video_url(video_url):
+ v_url = url_or_none(video_url)
+ if not v_url:
+ return
+ if v_url in video_urls_set:
+ return
+ video_urls.append((v_url, None))
+ video_urls_set.add(v_url)
+
+ if not video_urls:
+ FORMAT_PREFIXES = ('media', 'quality')
+ js_vars = extract_js_vars(
+ webpage, r'(var\s+(?:%s)_.+)' % '|'.join(FORMAT_PREFIXES),
+ default=None)
+ if js_vars:
+ for key, format_url in js_vars.items():
+ if any(key.startswith(p) for p in FORMAT_PREFIXES):
+ add_video_url(format_url)
+ if not video_urls and re.search(
+ r'<[^>]+\bid=["\']lockedPlayer', webpage):
+ raise ExtractorError(
+ 'Video %s is locked' % video_id, expected=True)
+
+ if not video_urls:
+ js_vars = extract_js_vars(
+ dl_webpage('tv'), r'(var.+?mediastring.+?)</script>')
+ add_video_url(js_vars['mediastring'])
for mobj in re.finditer(
r'<a[^>]+\bclass=["\']downloadBtn\b[^>]+\bhref=(["\'])(?P<url>(?:(?!\1).)+)\1',
@@ -276,10 +302,16 @@ class PornHubIE(PornHubBaseIE):
r'/(\d{6}/\d{2})/', video_url, 'upload data', default=None)
if upload_date:
upload_date = upload_date.replace('/', '')
- if determine_ext(video_url) == 'mpd':
+ ext = determine_ext(video_url)
+ if ext == 'mpd':
formats.extend(self._extract_mpd_formats(
video_url, video_id, mpd_id='dash', fatal=False))
continue
+ elif ext == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ video_url, video_id, 'mp4', entry_protocol='m3u8_native',
+ m3u8_id='hls', fatal=False))
+ continue
tbr = None
mobj = re.search(r'(?P<height>\d+)[pP]?_(?P<tbr>\d+)[kK]', video_url)
if mobj:
@@ -403,6 +435,15 @@ class PornHubUserIE(PornHubPlaylistBaseIE):
class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
+ @staticmethod
+ def _has_more(webpage):
+ return re.search(
+ r'''(?x)
+ <li[^>]+\bclass=["\']page_next|
+ <link[^>]+\brel=["\']next|
+ <button[^>]+\bid=["\']moreDataBtn
+ ''', webpage) is not None
+
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
host = mobj.group('host')
@@ -411,13 +452,11 @@ class PornHubPagedPlaylistBaseIE(PornHubPlaylistBaseIE):
page = int_or_none(self._search_regex(
r'\bpage=(\d+)', url, 'page', default=None))
- page_url = self._make_page_url(url)
-
entries = []
for page_num in (page, ) if page is not None else itertools.count(1):
try:
webpage = self._download_webpage(
- page_url, item_id, 'Downloading page %d' % page_num,
+ url, item_id, 'Downloading page %d' % page_num,
query={'page': page_num})
except ExtractorError as e:
if isinstance(e.cause, compat_HTTPError) and e.cause.code == 404:
@@ -547,18 +586,6 @@ class PornHubPagedVideoListIE(PornHubPagedPlaylistBaseIE):
if PornHubIE.suitable(url) or PornHubUserIE.suitable(url) or PornHubUserVideosUploadIE.suitable(url)
else super(PornHubPagedVideoListIE, cls).suitable(url))
- def _make_page_url(self, url):
- return url
-
- @staticmethod
- def _has_more(webpage):
- return re.search(
- r'''(?x)
- <li[^>]+\bclass=["\']page_next|
- <link[^>]+\brel=["\']next|
- <button[^>]+\bid=["\']moreDataBtn
- ''', webpage) is not None
-
class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
_VALID_URL = r'(?P<url>https?://(?:[^/]+\.)?(?P<host>pornhub\.(?:com|net))/(?:(?:user|channel)s|model|pornstar)/(?P<id>[^/]+)/videos/upload)'
@@ -572,11 +599,3 @@ class PornHubUserVideosUploadIE(PornHubPagedPlaylistBaseIE):
'url': 'https://www.pornhub.com/model/zoe_ph/videos/upload',
'only_matching': True,
}]
-
- def _make_page_url(self, url):
- mobj = re.match(self._VALID_URL, url)
- return '%s/ajax' % mobj.group('url')
-
- @staticmethod
- def _has_more(webpage):
- return True
diff --git a/youtube_dl/extractor/promptfile.py b/youtube_dl/extractor/promptfile.py
deleted file mode 100644
index 23ac93d7e..000000000
--- a/youtube_dl/extractor/promptfile.py
+++ /dev/null
@@ -1,70 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..utils import (
- determine_ext,
- ExtractorError,
- urlencode_postdata,
-)
-
-
-class PromptFileIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?promptfile\.com/l/(?P<id>[0-9A-Z\-]+)'
- _TEST = {
- 'url': 'http://www.promptfile.com/l/86D1CE8462-576CAAE416',
- 'md5': '5a7e285a26e0d66d9a263fae91bc92ce',
- 'info_dict': {
- 'id': '86D1CE8462-576CAAE416',
- 'ext': 'mp4',
- 'title': 'oceans.mp4',
- 'thumbnail': r're:^https?://.*\.jpg$',
- }
- }
-
- def _real_extract(self, url):
- video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
-
- if re.search(r'<div.+id="not_found_msg".+>(?!We are).+</div>[^-]', webpage) is not None:
- raise ExtractorError('Video %s does not exist' % video_id,
- expected=True)
-
- chash = self._search_regex(
- r'val\("([^"]*)"\s*\+\s*\$\("#chash"\)', webpage, 'chash')
- fields = self._hidden_inputs(webpage)
- keys = list(fields.keys())
- chash_key = keys[0] if len(keys) == 1 else next(
- key for key in keys if key.startswith('cha'))
- fields[chash_key] = chash + fields[chash_key]
-
- webpage = self._download_webpage(
- url, video_id, 'Downloading video page',
- data=urlencode_postdata(fields),
- headers={'Content-type': 'application/x-www-form-urlencoded'})
-
- video_url = self._search_regex(
- (r'<a[^>]+href=(["\'])(?P<url>(?:(?!\1).)+)\1[^>]*>\s*Download File',
- r'<a[^>]+href=(["\'])(?P<url>https?://(?:www\.)?promptfile\.com/file/(?:(?!\1).)+)\1'),
- webpage, 'video url', group='url')
- title = self._html_search_regex(
- r'<span.+title="([^"]+)">', webpage, 'title')
- thumbnail = self._html_search_regex(
- r'<div id="player_overlay">.*button>.*?<img src="([^"]+)"',
- webpage, 'thumbnail', fatal=False, flags=re.DOTALL)
-
- formats = [{
- 'format_id': 'sd',
- 'url': video_url,
- 'ext': determine_ext(title),
- }]
- self._sort_formats(formats)
-
- return {
- 'id': video_id,
- 'title': title,
- 'thumbnail': thumbnail,
- 'formats': formats,
- }
diff --git a/youtube_dl/extractor/prosiebensat1.py b/youtube_dl/extractor/prosiebensat1.py
index e19a470a5..1bc4f9b6b 100644
--- a/youtube_dl/extractor/prosiebensat1.py
+++ b/youtube_dl/extractor/prosiebensat1.py
@@ -16,7 +16,7 @@ from ..utils import (
class ProSiebenSat1BaseIE(InfoExtractor):
- _GEO_COUNTRIES = ['DE']
+ _GEO_BYPASS = False
_ACCESS_ID = None
_SUPPORTED_PROTOCOLS = 'dash:clear,hls:clear,progressive:clear'
_V4_BASE_URL = 'https://vas-v4.p7s1video.net/4.0/get'
@@ -39,14 +39,18 @@ class ProSiebenSat1BaseIE(InfoExtractor):
formats = []
if self._ACCESS_ID:
raw_ct = self._ENCRYPTION_KEY + clip_id + self._IV + self._ACCESS_ID
- server_token = (self._download_json(
+ protocols = self._download_json(
self._V4_BASE_URL + 'protocols', clip_id,
'Downloading protocols JSON',
headers=self.geo_verification_headers(), query={
'access_id': self._ACCESS_ID,
'client_token': sha1((raw_ct).encode()).hexdigest(),
'video_id': clip_id,
- }, fatal=False) or {}).get('server_token')
+ }, fatal=False, expected_status=(403,)) or {}
+ error = protocols.get('error') or {}
+ if error.get('title') == 'Geo check failed':
+ self.raise_geo_restricted(countries=['AT', 'CH', 'DE'])
+ server_token = protocols.get('server_token')
if server_token:
urls = (self._download_json(
self._V4_BASE_URL + 'urls', clip_id, 'Downloading urls JSON', query={
diff --git a/youtube_dl/extractor/puhutv.py b/youtube_dl/extractor/puhutv.py
index 5465e8ab7..fb704a3c4 100644
--- a/youtube_dl/extractor/puhutv.py
+++ b/youtube_dl/extractor/puhutv.py
@@ -25,21 +25,21 @@ class PuhuTVIE(InfoExtractor):
_TESTS = [{
# film
'url': 'https://puhutv.com/sut-kardesler-izle',
- 'md5': 'fbd8f2d8e7681f8bcd51b592475a6ae7',
+ 'md5': 'a347470371d56e1585d1b2c8dab01c96',
'info_dict': {
'id': '5085',
'display_id': 'sut-kardesler',
'ext': 'mp4',
'title': 'Süt Kardeşler',
- 'description': 'md5:405fd024df916ca16731114eb18e511a',
+ 'description': 'md5:ca09da25b7e57cbb5a9280d6e48d17aa',
'thumbnail': r're:^https?://.*\.jpg$',
'duration': 4832.44,
'creator': 'Arzu Film',
- 'timestamp': 1469778212,
- 'upload_date': '20160729',
+ 'timestamp': 1561062602,
+ 'upload_date': '20190620',
'release_year': 1976,
'view_count': int,
- 'tags': ['Aile', 'Komedi', 'Klasikler'],
+ 'tags': list,
},
}, {
# episode, geo restricted, bypassable with --geo-verification-proxy
@@ -64,9 +64,10 @@ class PuhuTVIE(InfoExtractor):
display_id)['data']
video_id = compat_str(info['id'])
- title = info.get('name') or info['title']['name']
+ show = info.get('title') or {}
+ title = info.get('name') or show['name']
if info.get('display_name'):
- title = '%s %s' % (title, info.get('display_name'))
+ title = '%s %s' % (title, info['display_name'])
try:
videos = self._download_json(
@@ -78,17 +79,36 @@ class PuhuTVIE(InfoExtractor):
self.raise_geo_restricted()
raise
+ urls = []
formats = []
+
+ def add_http_from_hls(m3u8_f):
+ http_url = m3u8_f['url'].replace('/hls/', '/mp4/').replace('/chunklist.m3u8', '.mp4')
+ if http_url != m3u8_f['url']:
+ f = m3u8_f.copy()
+ f.update({
+ 'format_id': f['format_id'].replace('hls', 'http'),
+ 'protocol': 'http',
+ 'url': http_url,
+ })
+ formats.append(f)
+
for video in videos['data']['videos']:
media_url = url_or_none(video.get('url'))
- if not media_url:
+ if not media_url or media_url in urls:
continue
+ urls.append(media_url)
+
playlist = video.get('is_playlist')
- if video.get('stream_type') == 'hls' and playlist is True:
- formats.extend(self._extract_m3u8_formats(
+ if (video.get('stream_type') == 'hls' and playlist is True) or 'playlist.m3u8' in media_url:
+ m3u8_formats = self._extract_m3u8_formats(
media_url, video_id, 'mp4', entry_protocol='m3u8_native',
- m3u8_id='hls', fatal=False))
+ m3u8_id='hls', fatal=False)
+ for m3u8_f in m3u8_formats:
+ formats.append(m3u8_f)
+ add_http_from_hls(m3u8_f)
continue
+
quality = int_or_none(video.get('quality'))
f = {
'url': media_url,
@@ -96,34 +116,29 @@ class PuhuTVIE(InfoExtractor):
'height': quality
}
video_format = video.get('video_format')
- if video_format == 'hls' and playlist is False:
+ is_hls = (video_format == 'hls' or '/hls/' in media_url or '/chunklist.m3u8' in media_url) and playlist is False
+ if is_hls:
format_id = 'hls'
f['protocol'] = 'm3u8_native'
elif video_format == 'mp4':
format_id = 'http'
-
else:
continue
if quality:
format_id += '-%sp' % quality
f['format_id'] = format_id
formats.append(f)
+ if is_hls:
+ add_http_from_hls(f)
self._sort_formats(formats)
- description = try_get(
- info, lambda x: x['title']['description'],
- compat_str) or info.get('description')
- timestamp = unified_timestamp(info.get('created_at'))
creator = try_get(
- info, lambda x: x['title']['producer']['name'], compat_str)
+ show, lambda x: x['producer']['name'], compat_str)
- duration = float_or_none(
- try_get(info, lambda x: x['content']['duration_in_ms'], int),
- scale=1000)
- view_count = try_get(info, lambda x: x['content']['watch_count'], int)
+ content = info.get('content') or {}
images = try_get(
- info, lambda x: x['content']['images']['wide'], dict) or {}
+ content, lambda x: x['images']['wide'], dict) or {}
thumbnails = []
for image_id, image_url in images.items():
if not isinstance(image_url, compat_str):
@@ -137,14 +152,8 @@ class PuhuTVIE(InfoExtractor):
})
thumbnails.append(t)
- release_year = try_get(info, lambda x: x['title']['released_at'], int)
-
- season_number = int_or_none(info.get('season_number'))
- season_id = str_or_none(info.get('season_id'))
- episode_number = int_or_none(info.get('episode_number'))
-
tags = []
- for genre in try_get(info, lambda x: x['title']['genres'], list) or []:
+ for genre in show.get('genres') or []:
if not isinstance(genre, dict):
continue
genre_name = genre.get('name')
@@ -152,12 +161,11 @@ class PuhuTVIE(InfoExtractor):
tags.append(genre_name)
subtitles = {}
- for subtitle in try_get(
- info, lambda x: x['content']['subtitles'], list) or []:
+ for subtitle in content.get('subtitles') or []:
if not isinstance(subtitle, dict):
continue
lang = subtitle.get('language')
- sub_url = url_or_none(subtitle.get('url'))
+ sub_url = url_or_none(subtitle.get('url') or subtitle.get('file'))
if not lang or not isinstance(lang, compat_str) or not sub_url:
continue
subtitles[self._SUBTITLE_LANGS.get(lang, lang)] = [{
@@ -168,15 +176,15 @@ class PuhuTVIE(InfoExtractor):
'id': video_id,
'display_id': display_id,
'title': title,
- 'description': description,
- 'season_id': season_id,
- 'season_number': season_number,
- 'episode_number': episode_number,
- 'release_year': release_year,
- 'timestamp': timestamp,
+ 'description': info.get('description') or show.get('description'),
+ 'season_id': str_or_none(info.get('season_id')),
+ 'season_number': int_or_none(info.get('season_number')),
+ 'episode_number': int_or_none(info.get('episode_number')),
+ 'release_year': int_or_none(show.get('released_at')),
+ 'timestamp': unified_timestamp(info.get('created_at')),
'creator': creator,
- 'view_count': view_count,
- 'duration': duration,
+ 'view_count': int_or_none(content.get('watch_count')),
+ 'duration': float_or_none(content.get('duration_in_ms'), 1000),
'tags': tags,
'subtitles': subtitles,
'thumbnails': thumbnails,
diff --git a/youtube_dl/extractor/redtube.py b/youtube_dl/extractor/redtube.py
index 10311a81a..5c84028ef 100644
--- a/youtube_dl/extractor/redtube.py
+++ b/youtube_dl/extractor/redtube.py
@@ -6,6 +6,7 @@ from .common import InfoExtractor
from ..utils import (
ExtractorError,
int_or_none,
+ merge_dicts,
str_to_int,
unified_strdate,
url_or_none,
@@ -45,11 +46,14 @@ class RedTubeIE(InfoExtractor):
if any(s in webpage for s in ['video-deleted-info', '>This video has been removed']):
raise ExtractorError('Video %s has been removed' % video_id, expected=True)
- title = self._html_search_regex(
- (r'<h(\d)[^>]+class="(?:video_title_text|videoTitle)[^"]*">(?P<title>(?:(?!\1).)+)</h\1>',
- r'(?:videoTitle|title)\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1',),
- webpage, 'title', group='title',
- default=None) or self._og_search_title(webpage)
+ info = self._search_json_ld(webpage, video_id, default={})
+
+ if not info.get('title'):
+ info['title'] = self._html_search_regex(
+ (r'<h(\d)[^>]+class="(?:video_title_text|videoTitle)[^"]*">(?P<title>(?:(?!\1).)+)</h\1>',
+ r'(?:videoTitle|title)\s*:\s*(["\'])(?P<title>(?:(?!\1).)+)\1',),
+ webpage, 'title', group='title',
+ default=None) or self._og_search_title(webpage)
formats = []
sources = self._parse_json(
@@ -88,28 +92,28 @@ class RedTubeIE(InfoExtractor):
thumbnail = self._og_search_thumbnail(webpage)
upload_date = unified_strdate(self._search_regex(
- r'<span[^>]+>ADDED ([^<]+)<',
- webpage, 'upload date', fatal=False))
+ r'<span[^>]+>(?:ADDED|Published on) ([^<]+)<',
+ webpage, 'upload date', default=None))
duration = int_or_none(self._og_search_property(
'video:duration', webpage, default=None) or self._search_regex(
r'videoDuration\s*:\s*(\d+)', webpage, 'duration', default=None))
view_count = str_to_int(self._search_regex(
(r'<div[^>]*>Views</div>\s*<div[^>]*>\s*([\d,.]+)',
- r'<span[^>]*>VIEWS</span>\s*</td>\s*<td>\s*([\d,.]+)'),
- webpage, 'view count', fatal=False))
+ r'<span[^>]*>VIEWS</span>\s*</td>\s*<td>\s*([\d,.]+)',
+ r'<span[^>]+\bclass=["\']video_view_count[^>]*>\s*([\d,.]+)'),
+ webpage, 'view count', default=None))
# No self-labeling, but they describe themselves as
# "Home of Videos Porno"
age_limit = 18
- return {
+ return merge_dicts(info, {
'id': video_id,
'ext': 'mp4',
- 'title': title,
'thumbnail': thumbnail,
'upload_date': upload_date,
'duration': duration,
'view_count': view_count,
'age_limit': age_limit,
'formats': formats,
- }
+ })
diff --git a/youtube_dl/extractor/revision3.py b/youtube_dl/extractor/revision3.py
deleted file mode 100644
index 833d8a2f0..000000000
--- a/youtube_dl/extractor/revision3.py
+++ /dev/null
@@ -1,170 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..compat import compat_str
-from ..utils import (
- int_or_none,
- parse_iso8601,
- unescapeHTML,
- qualities,
-)
-
-
-class Revision3EmbedIE(InfoExtractor):
- IE_NAME = 'revision3:embed'
- _VALID_URL = r'(?:revision3:(?:(?P<playlist_type>[^:]+):)?|https?://(?:(?:(?:www|embed)\.)?(?:revision3|animalist)|(?:(?:api|embed)\.)?seekernetwork)\.com/player/embed\?videoId=)(?P<playlist_id>\d+)'
- _TEST = {
- 'url': 'http://api.seekernetwork.com/player/embed?videoId=67558',
- 'md5': '83bcd157cab89ad7318dd7b8c9cf1306',
- 'info_dict': {
- 'id': '67558',
- 'ext': 'mp4',
- 'title': 'The Pros & Cons Of Zoos',
- 'description': 'Zoos are often depicted as a terrible place for animals to live, but is there any truth to this?',
- 'uploader_id': 'dnews',
- 'uploader': 'DNews',
- }
- }
- _API_KEY = 'ba9c741bce1b9d8e3defcc22193f3651b8867e62'
-
- def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- playlist_id = mobj.group('playlist_id')
- playlist_type = mobj.group('playlist_type') or 'video_id'
- video_data = self._download_json(
- 'http://revision3.com/api/getPlaylist.json', playlist_id, query={
- 'api_key': self._API_KEY,
- 'codecs': 'h264,vp8,theora',
- playlist_type: playlist_id,
- })['items'][0]
-
- formats = []
- for vcodec, media in video_data['media'].items():
- for quality_id, quality in media.items():
- if quality_id == 'hls':
- formats.extend(self._extract_m3u8_formats(
- quality['url'], playlist_id, 'mp4',
- 'm3u8_native', m3u8_id='hls', fatal=False))
- else:
- formats.append({
- 'url': quality['url'],
- 'format_id': '%s-%s' % (vcodec, quality_id),
- 'tbr': int_or_none(quality.get('bitrate')),
- 'vcodec': vcodec,
- })
- self._sort_formats(formats)
-
- return {
- 'id': playlist_id,
- 'title': unescapeHTML(video_data['title']),
- 'description': unescapeHTML(video_data.get('summary')),
- 'uploader': video_data.get('show', {}).get('name'),
- 'uploader_id': video_data.get('show', {}).get('slug'),
- 'duration': int_or_none(video_data.get('duration')),
- 'formats': formats,
- }
-
-
-class Revision3IE(InfoExtractor):
- IE_NAME = 'revision'
- _VALID_URL = r'https?://(?:www\.)?(?P<domain>(?:revision3|animalist)\.com)/(?P<id>[^/]+(?:/[^/?#]+)?)'
- _TESTS = [{
- 'url': 'http://www.revision3.com/technobuffalo/5-google-predictions-for-2016',
- 'md5': 'd94a72d85d0a829766de4deb8daaf7df',
- 'info_dict': {
- 'id': '71089',
- 'display_id': 'technobuffalo/5-google-predictions-for-2016',
- 'ext': 'webm',
- 'title': '5 Google Predictions for 2016',
- 'description': 'Google had a great 2015, but it\'s already time to look ahead. Here are our five predictions for 2016.',
- 'upload_date': '20151228',
- 'timestamp': 1451325600,
- 'duration': 187,
- 'uploader': 'TechnoBuffalo',
- 'uploader_id': 'technobuffalo',
- }
- }, {
- # Show
- 'url': 'http://revision3.com/variant',
- 'only_matching': True,
- }, {
- # Tag
- 'url': 'http://revision3.com/vr',
- 'only_matching': True,
- }]
- _PAGE_DATA_TEMPLATE = 'http://www.%s/apiProxy/ddn/%s?domain=%s'
-
- def _real_extract(self, url):
- domain, display_id = re.match(self._VALID_URL, url).groups()
- site = domain.split('.')[0]
- page_info = self._download_json(
- self._PAGE_DATA_TEMPLATE % (domain, display_id, domain), display_id)
-
- page_data = page_info['data']
- page_type = page_data['type']
- if page_type in ('episode', 'embed'):
- show_data = page_data['show']['data']
- page_id = compat_str(page_data['id'])
- video_id = compat_str(page_data['video']['data']['id'])
-
- preference = qualities(['mini', 'small', 'medium', 'large'])
- thumbnails = [{
- 'url': image_url,
- 'id': image_id,
- 'preference': preference(image_id)
- } for image_id, image_url in page_data.get('images', {}).items()]
-
- info = {
- 'id': page_id,
- 'display_id': display_id,
- 'title': unescapeHTML(page_data['name']),
- 'description': unescapeHTML(page_data.get('summary')),
- 'timestamp': parse_iso8601(page_data.get('publishTime'), ' '),
- 'author': page_data.get('author'),
- 'uploader': show_data.get('name'),
- 'uploader_id': show_data.get('slug'),
- 'thumbnails': thumbnails,
- 'extractor_key': site,
- }
-
- if page_type == 'embed':
- info.update({
- '_type': 'url_transparent',
- 'url': page_data['video']['data']['embed'],
- })
- return info
-
- info.update({
- '_type': 'url_transparent',
- 'url': 'revision3:%s' % video_id,
- })
- return info
- else:
- list_data = page_info[page_type]['data']
- episodes_data = page_info['episodes']['data']
- num_episodes = page_info['meta']['totalEpisodes']
- processed_episodes = 0
- entries = []
- page_num = 1
- while True:
- entries.extend([{
- '_type': 'url',
- 'url': 'http://%s%s' % (domain, episode['path']),
- 'id': compat_str(episode['id']),
- 'ie_key': 'Revision3',
- 'extractor_key': site,
- } for episode in episodes_data])
- processed_episodes += len(episodes_data)
- if processed_episodes == num_episodes:
- break
- page_num += 1
- episodes_data = self._download_json(self._PAGE_DATA_TEMPLATE % (
- domain, display_id + '/' + compat_str(page_num), domain),
- display_id)['episodes']['data']
-
- return self.playlist_result(
- entries, compat_str(list_data['id']),
- list_data.get('name'), list_data.get('summary'))
diff --git a/youtube_dl/extractor/roosterteeth.py b/youtube_dl/extractor/roosterteeth.py
index 857434540..8883639b2 100644
--- a/youtube_dl/extractor/roosterteeth.py
+++ b/youtube_dl/extractor/roosterteeth.py
@@ -1,35 +1,34 @@
# coding: utf-8
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
+from ..compat import (
+ compat_HTTPError,
+ compat_str,
+)
from ..utils import (
ExtractorError,
int_or_none,
- strip_or_none,
- unescapeHTML,
+ str_or_none,
urlencode_postdata,
)
class RoosterTeethIE(InfoExtractor):
- _VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/episode/(?P<id>[^/?#&]+)'
- _LOGIN_URL = 'https://roosterteeth.com/login'
+ _VALID_URL = r'https?://(?:.+?\.)?roosterteeth\.com/(?:episode|watch)/(?P<id>[^/?#&]+)'
_NETRC_MACHINE = 'roosterteeth'
_TESTS = [{
'url': 'http://roosterteeth.com/episode/million-dollars-but-season-2-million-dollars-but-the-game-announcement',
'md5': 'e2bd7764732d785ef797700a2489f212',
'info_dict': {
- 'id': '26576',
+ 'id': '9156',
'display_id': 'million-dollars-but-season-2-million-dollars-but-the-game-announcement',
'ext': 'mp4',
- 'title': 'Million Dollars, But...: Million Dollars, But... The Game Announcement',
- 'description': 'md5:0cc3b21986d54ed815f5faeccd9a9ca5',
+ 'title': 'Million Dollars, But... The Game Announcement',
+ 'description': 'md5:168a54b40e228e79f4ddb141e89fe4f5',
'thumbnail': r're:^https?://.*\.png$',
'series': 'Million Dollars, But...',
'episode': 'Million Dollars, But... The Game Announcement',
- 'comment_count': int,
},
}, {
'url': 'http://achievementhunter.roosterteeth.com/episode/off-topic-the-achievement-hunter-podcast-2016-i-didn-t-think-it-would-pass-31',
@@ -47,102 +46,92 @@ class RoosterTeethIE(InfoExtractor):
# only available for FIRST members
'url': 'http://roosterteeth.com/episode/rt-docs-the-world-s-greatest-head-massage-the-world-s-greatest-head-massage-an-asmr-journey-part-one',
'only_matching': True,
+ }, {
+ 'url': 'https://roosterteeth.com/watch/million-dollars-but-season-2-million-dollars-but-the-game-announcement',
+ 'only_matching': True,
}]
+ _EPISODE_BASE_URL = 'https://svod-be.roosterteeth.com/api/v1/episodes/'
def _login(self):
username, password = self._get_login_info()
if username is None:
return
- login_page = self._download_webpage(
- self._LOGIN_URL, None,
- note='Downloading login page',
- errnote='Unable to download login page')
-
- login_form = self._hidden_inputs(login_page)
-
- login_form.update({
- 'username': username,
- 'password': password,
- })
-
- login_request = self._download_webpage(
- self._LOGIN_URL, None,
- note='Logging in',
- data=urlencode_postdata(login_form),
- headers={
- 'Referer': self._LOGIN_URL,
- })
-
- if not any(re.search(p, login_request) for p in (
- r'href=["\']https?://(?:www\.)?roosterteeth\.com/logout"',
- r'>Sign Out<')):
- error = self._html_search_regex(
- r'(?s)<div[^>]+class=(["\']).*?\balert-danger\b.*?\1[^>]*>(?:\s*<button[^>]*>.*?</button>)?(?P<error>.+?)</div>',
- login_request, 'alert', default=None, group='error')
- if error:
- raise ExtractorError('Unable to login: %s' % error, expected=True)
- raise ExtractorError('Unable to log in')
+ try:
+ self._download_json(
+ 'https://auth.roosterteeth.com/oauth/token',
+ None, 'Logging in', data=urlencode_postdata({
+ 'client_id': '4338d2b4bdc8db1239360f28e72f0d9ddb1fd01e7a38fbb07b4b1f4ba4564cc5',
+ 'grant_type': 'password',
+ 'username': username,
+ 'password': password,
+ }))
+ except ExtractorError as e:
+ msg = 'Unable to login'
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+ resp = self._parse_json(e.cause.read().decode(), None, fatal=False)
+ if resp:
+ error = resp.get('extra_info') or resp.get('error_description') or resp.get('error')
+ if error:
+ msg += ': ' + error
+ self.report_warning(msg)
def _real_initialize(self):
+ if self._get_cookies(self._EPISODE_BASE_URL).get('rt_access_token'):
+ return
self._login()
def _real_extract(self, url):
display_id = self._match_id(url)
+ api_episode_url = self._EPISODE_BASE_URL + display_id
- webpage = self._download_webpage(url, display_id)
-
- episode = strip_or_none(unescapeHTML(self._search_regex(
- (r'videoTitle\s*=\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
- r'<title>(?P<title>[^<]+)'), webpage, 'title',
- default=None, group='title')))
-
- title = strip_or_none(self._og_search_title(
- webpage, default=None)) or episode
-
- m3u8_url = self._search_regex(
- r'file\s*:\s*(["\'])(?Phttp.+?\.m3u8.*?)\1',
- webpage, 'm3u8 url', default=None, group='url')
-
- if not m3u8_url:
- if re.search(r']+class=["\']non-sponsor', webpage):
- self.raise_login_required(
- '%s is only available for FIRST members' % display_id)
-
- if re.search(r']+class=["\']golive-gate', webpage):
- self.raise_login_required('%s is not available yet' % display_id)
-
- raise ExtractorError('Unable to extract m3u8 URL')
+ try:
+ m3u8_url = self._download_json(
+ api_episode_url + '/videos', display_id,
+ 'Downloading video JSON metadata')['data'][0]['attributes']['url']
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
+ if self._parse_json(e.cause.read().decode(), display_id).get('access') is False:
+ self.raise_login_required(
+ '%s is only available for FIRST members' % display_id)
+ raise
formats = self._extract_m3u8_formats(
- m3u8_url, display_id, ext='mp4',
- entry_protocol='m3u8_native', m3u8_id='hls')
+ m3u8_url, display_id, 'mp4', 'm3u8_native', m3u8_id='hls')
self._sort_formats(formats)
- description = strip_or_none(self._og_search_description(webpage))
- thumbnail = self._proto_relative_url(self._og_search_thumbnail(webpage))
+ episode = self._download_json(
+ api_episode_url, display_id,
+ 'Downloading episode JSON metadata')['data'][0]
+ attributes = episode['attributes']
+ title = attributes.get('title') or attributes['display_title']
+ video_id = compat_str(episode['id'])
- series = self._search_regex(
- (r'More ([^<]+)
', r']+>See All ([^<]+) Videos<'),
- webpage, 'series', fatal=False)
-
- comment_count = int_or_none(self._search_regex(
- r'>Comments \((\d+)\)<', webpage,
- 'comment count', fatal=False))
-
- video_id = self._search_regex(
- (r'containerId\s*=\s*["\']episode-(\d+)\1',
- r'[0-9a-zA-Z]+)'
-
- _TEST = {
- 'url': 'http://rudo.video/vod/oTzw0MGnyG',
- 'md5': '2a03a5b32dd90a04c83b6d391cf7b415',
- 'info_dict': {
- 'id': 'oTzw0MGnyG',
- 'ext': 'mp4',
- 'title': 'Comentario Tomás Mosciatti',
- 'upload_date': '20160617',
- },
- }
-
- @classmethod
- def _extract_url(cls, webpage):
- mobj = re.search(
- r']+src=(?P[\'"])(?P(?:https?:)?//rudo\.video/vod/[0-9a-zA-Z]+)(?P=q1)',
- webpage)
- if mobj:
- return mobj.group('url')
-
- def _real_extract(self, url):
- video_id = self._match_id(url)
-
- webpage = self._download_webpage(url, video_id, encoding='iso-8859-1')
-
- jwplayer_data = self._parse_json(self._search_regex(
- r'(?s)playerInstance\.setup\(({.+?})\)', webpage, 'jwplayer data'), video_id,
- transform_source=lambda s: js_to_json(re.sub(r'encodeURI\([^)]+\)', '""', s)))
-
- info_dict = self._parse_jwplayer_data(
- jwplayer_data, video_id, require_title=False, m3u8_id='hls', mpd_id='dash')
-
- info_dict.update({
- 'title': self._og_search_title(webpage),
- 'upload_date': unified_strdate(get_element_by_class('date', webpage)),
- })
-
- return info_dict
diff --git a/youtube_dl/extractor/safari.py b/youtube_dl/extractor/safari.py
index 8d4806794..bd9ee1647 100644
--- a/youtube_dl/extractor/safari.py
+++ b/youtube_dl/extractor/safari.py
@@ -68,9 +68,10 @@ class SafariBaseIE(InfoExtractor):
raise ExtractorError(
'Unable to login: %s' % credentials, expected=True)
- # oreilly serves two same groot_sessionid cookies in Set-Cookie header
- # and expects first one to be actually set
- self._apply_first_set_cookie_header(urlh, 'groot_sessionid')
+ # oreilly serves two same instances of the following cookies
+ # in Set-Cookie header and expects first one to be actually set
+ for cookie in ('groot_sessionid', 'orm-jwt', 'orm-rt'):
+ self._apply_first_set_cookie_header(urlh, cookie)
_, urlh = self._download_webpage_handle(
auth.get('redirect_uri') or next_uri, None, 'Completing login',)
diff --git a/youtube_dl/extractor/scrippsnetworks.py b/youtube_dl/extractor/scrippsnetworks.py
index 8b3275735..afab9591d 100644
--- a/youtube_dl/extractor/scrippsnetworks.py
+++ b/youtube_dl/extractor/scrippsnetworks.py
@@ -7,6 +7,7 @@ import re
from .aws import AWSIE
from .anvato import AnvatoIE
+from .common import InfoExtractor
from ..utils import (
smuggle_url,
urlencode_postdata,
@@ -102,3 +103,46 @@ class ScrippsNetworksWatchIE(AWSIE):
'anvato:anvato_scripps_app_web_prod_0837996dbe373629133857ae9eb72e740424d80a:%s' % mcp_id,
{'geo_countries': ['US']}),
AnvatoIE.ie_key(), video_id=mcp_id)
+
+
+class ScrippsNetworksIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?(?Pcookingchanneltv|(?:diy|food)network|hgtv|travelchannel)\.com/videos/[0-9a-z-]+-(?P\d+)'
+ _TESTS = [{
+ 'url': 'https://www.cookingchanneltv.com/videos/the-best-of-the-best-0260338',
+ 'info_dict': {
+ 'id': '0260338',
+ 'ext': 'mp4',
+ 'title': 'The Best of the Best',
+ 'description': 'Catch a new episode of MasterChef Canada Tuedsay at 9/8c.',
+ 'timestamp': 1475678834,
+ 'upload_date': '20161005',
+ 'uploader': 'SCNI-SCND',
+ },
+ 'add_ie': ['ThePlatform'],
+ }, {
+ 'url': 'https://www.diynetwork.com/videos/diy-barnwood-tablet-stand-0265790',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.foodnetwork.com/videos/chocolate-strawberry-cake-roll-7524591',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.hgtv.com/videos/cookie-decorating-101-0301929',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.travelchannel.com/videos/two-climates-one-bag-5302184',
+ 'only_matching': True,
+ }]
+ _ACCOUNT_MAP = {
+ 'cookingchanneltv': 2433005105,
+ 'diynetwork': 2433004575,
+ 'foodnetwork': 2433005105,
+ 'hgtv': 2433004575,
+ 'travelchannel': 2433005739,
+ }
+ _TP_TEMPL = 'https://link.theplatform.com/s/ip77QC/media/guid/%d/%s?mbr=true'
+
+ def _real_extract(self, url):
+ site, guid = re.match(self._VALID_URL, url).groups()
+ return self.url_result(smuggle_url(
+ self._TP_TEMPL % (self._ACCOUNT_MAP[site], guid),
+ {'force_smil_url': True}), 'ThePlatform', guid)
diff --git a/youtube_dl/extractor/scte.py b/youtube_dl/extractor/scte.py
new file mode 100644
index 000000000..ca1de63b6
--- /dev/null
+++ b/youtube_dl/extractor/scte.py
@@ -0,0 +1,144 @@
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ decode_packed_codes,
+ ExtractorError,
+ urlencode_postdata,
+)
+
+
+class SCTEBaseIE(InfoExtractor):
+ _LOGIN_URL = 'https://www.scte.org/SCTE/Sign_In.aspx'
+ _NETRC_MACHINE = 'scte'
+
+ def _real_initialize(self):
+ self._login()
+
+ def _login(self):
+ username, password = self._get_login_info()
+ if username is None:
+ return
+
+ login_popup = self._download_webpage(
+ self._LOGIN_URL, None, 'Downloading login popup')
+
+ def is_logged(webpage):
+ return any(re.search(p, webpage) for p in (
+ r'class=["\']welcome\b', r'>Sign Out<'))
+
+ # already logged in
+ if is_logged(login_popup):
+ return
+
+ login_form = self._hidden_inputs(login_popup)
+
+ login_form.update({
+ 'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$signInUserName': username,
+ 'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$signInPassword': password,
+ 'ctl01$TemplateBody$WebPartManager1$gwpciNewContactSignInCommon$ciNewContactSignInCommon$RememberMe': 'on',
+ })
+
+ response = self._download_webpage(
+ self._LOGIN_URL, None, 'Logging in',
+ data=urlencode_postdata(login_form))
+
+ if '|pageRedirect|' not in response and not is_logged(response):
+ error = self._html_search_regex(
+ r'(?s)<[^>]+class=["\']AsiError["\'][^>]*>(.+?)\d+)'
+ _TESTS = [{
+ 'url': 'https://learning.scte.org/mod/scorm/view.php?id=31484',
+ 'info_dict': {
+ 'title': 'Introduction to DOCSIS Engineering Professional',
+ 'id': '31484',
+ },
+ 'playlist_count': 5,
+ 'skip': 'Requires account credentials',
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ title = self._search_regex(r'(.+?)
', webpage, 'title')
+
+ context_id = self._search_regex(r'context-(\d+)', webpage, video_id)
+ content_base = 'https://learning.scte.org/pluginfile.php/%s/mod_scorm/content/8/' % context_id
+ context = decode_packed_codes(self._download_webpage(
+ '%smobile/data.js' % content_base, video_id))
+
+ data = self._parse_xml(
+ self._search_regex(
+ r'CreateData\(\s*"(.+?)"', context, 'data').replace(r"\'", "'"),
+ video_id)
+
+ entries = []
+ for asset in data.findall('.//asset'):
+ asset_url = asset.get('url')
+ if not asset_url or not asset_url.endswith('.mp4'):
+ continue
+ asset_id = self._search_regex(
+ r'video_([^_]+)_', asset_url, 'asset id', default=None)
+ if not asset_id:
+ continue
+ entries.append({
+ 'id': asset_id,
+ 'title': title,
+ 'url': content_base + asset_url,
+ })
+
+ return self.playlist_result(entries, video_id, title)
+
+
+class SCTECourseIE(SCTEBaseIE):
+ _VALID_URL = r'https?://learning\.scte\.org/(?:mod/sub)?course/view\.php?.*?\bid=(?P\d+)'
+ _TESTS = [{
+ 'url': 'https://learning.scte.org/mod/subcourse/view.php?id=31491',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://learning.scte.org/course/view.php?id=3639',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://learning.scte.org/course/view.php?id=3073',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ course_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, course_id)
+
+ title = self._search_regex(
+ r'(.+?)
', webpage, 'title', default=None)
+
+ entries = []
+ for mobj in re.finditer(
+ r'''(?x)
+ ]+
+ href=(["\'])
+ (?P
+ https?://learning\.scte\.org/mod/
+ (?Pscorm|subcourse)/view\.php?(?:(?!\1).)*?
+ \bid=\d+
+ )
+ ''',
+ webpage):
+ item_url = mobj.group('url')
+ if item_url == url:
+ continue
+ ie = (SCTEIE.ie_key() if mobj.group('kind') == 'scorm'
+ else SCTECourseIE.ie_key())
+ entries.append(self.url_result(item_url, ie=ie))
+
+ return self.playlist_result(entries, course_id, title)
diff --git a/youtube_dl/extractor/seeker.py b/youtube_dl/extractor/seeker.py
index 3b9c65e7e..7872dc80d 100644
--- a/youtube_dl/extractor/seeker.py
+++ b/youtube_dl/extractor/seeker.py
@@ -4,34 +4,37 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
+from ..utils import (
+ get_element_by_class,
+ strip_or_none,
+)
class SeekerIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?seeker\.com/(?P.*)-(?P\d+)\.html'
_TESTS = [{
- # player.loadRevision3Item
'url': 'http://www.seeker.com/should-trump-be-required-to-release-his-tax-returns-1833805621.html',
- 'md5': '30c1dc4030cc715cf05b423d0947ac18',
+ 'md5': '897d44bbe0d8986a2ead96de565a92db',
'info_dict': {
- 'id': '76243',
- 'ext': 'webm',
+ 'id': 'Elrn3gnY',
+ 'ext': 'mp4',
'title': 'Should Trump Be Required To Release His Tax Returns?',
- 'description': 'Donald Trump has been secretive about his "big," "beautiful" tax returns. So what can we learn if he decides to release them?',
- 'uploader': 'Seeker Daily',
- 'uploader_id': 'seekerdaily',
+ 'description': 'md5:41efa8cfa8d627841045eec7b018eb45',
+ 'timestamp': 1490090165,
+ 'upload_date': '20170321',
}
}, {
'url': 'http://www.seeker.com/changes-expected-at-zoos-following-recent-gorilla-lion-shootings-1834116536.html',
'playlist': [
{
- 'md5': '83bcd157cab89ad7318dd7b8c9cf1306',
+ 'md5': '0497b9f20495174be73ae136949707d2',
'info_dict': {
- 'id': '67558',
+ 'id': 'FihYQ8AE',
'ext': 'mp4',
'title': 'The Pros & Cons Of Zoos',
- 'description': 'Zoos are often depicted as a terrible place for animals to live, but is there any truth to this?',
- 'uploader': 'DNews',
- 'uploader_id': 'dnews',
+ 'description': 'md5:d88f99a8ea8e7d25e6ff77f271b1271c',
+ 'timestamp': 1490039133,
+ 'upload_date': '20170320',
},
}
],
@@ -45,13 +48,11 @@ class SeekerIE(InfoExtractor):
def _real_extract(self, url):
display_id, article_id = re.match(self._VALID_URL, url).groups()
webpage = self._download_webpage(url, display_id)
- mobj = re.search(r"player\.loadRevision3Item\('([^']+)'\s*,\s*(\d+)\);", webpage)
- if mobj:
- playlist_type, playlist_id = mobj.groups()
- return self.url_result(
- 'revision3:%s:%s' % (playlist_type, playlist_id), 'Revision3Embed', playlist_id)
- else:
- entries = [self.url_result('revision3:video_id:%s' % video_id, 'Revision3Embed', video_id) for video_id in re.findall(
- r']+src=[\'"](?:https?:)?//api\.seekernetwork\.com/player/embed\?videoId=(\d+)', webpage)]
- return self.playlist_result(
- entries, article_id, self._og_search_title(webpage), self._og_search_description(webpage))
+ entries = []
+ for jwp_id in re.findall(r'data-video-id="([a-zA-Z0-9]{8})"', webpage):
+ entries.append(self.url_result(
+ 'jwplatform:' + jwp_id, 'JWPlatform', jwp_id))
+ return self.playlist_result(
+ entries, article_id,
+ self._og_search_title(webpage),
+ strip_or_none(get_element_by_class('subtitle__text', webpage)) or self._og_search_description(webpage))
diff --git a/youtube_dl/extractor/servingsys.py b/youtube_dl/extractor/servingsys.py
deleted file mode 100644
index c013d678f..000000000
--- a/youtube_dl/extractor/servingsys.py
+++ /dev/null
@@ -1,72 +0,0 @@
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..utils import (
- int_or_none,
-)
-
-
-class ServingSysIE(InfoExtractor):
- _VALID_URL = r'https?://(?:[^.]+\.)?serving-sys\.com/BurstingPipe/adServer\.bs\?.*?&pli=(?P[0-9]+)'
-
- _TEST = {
- 'url': 'http://bs.serving-sys.com/BurstingPipe/adServer.bs?cn=is&c=23&pl=VAST&pli=5349193&PluID=0&pos=7135&ord=[timestamp]&cim=1?',
- 'info_dict': {
- 'id': '5349193',
- 'title': 'AdAPPter_Hyundai_demo',
- },
- 'playlist': [{
- 'md5': 'baed851342df6846eb8677a60a011a0f',
- 'info_dict': {
- 'id': '29955898',
- 'ext': 'flv',
- 'title': 'AdAPPter_Hyundai_demo (1)',
- 'duration': 74,
- 'tbr': 1378,
- 'width': 640,
- 'height': 400,
- },
- }, {
- 'md5': '979b4da2655c4bc2d81aeb915a8c5014',
- 'info_dict': {
- 'id': '29907998',
- 'ext': 'flv',
- 'title': 'AdAPPter_Hyundai_demo (2)',
- 'duration': 34,
- 'width': 854,
- 'height': 480,
- 'tbr': 516,
- },
- }],
- 'params': {
- 'playlistend': 2,
- },
- '_skip': 'Blocked in the US [sic]',
- }
-
- def _real_extract(self, url):
- pl_id = self._match_id(url)
- vast_doc = self._download_xml(url, pl_id)
-
- title = vast_doc.find('.//AdTitle').text
- media = vast_doc.find('.//MediaFile').text
- info_url = self._search_regex(r'&adData=([^&]+)&', media, 'info URL')
-
- doc = self._download_xml(info_url, pl_id, 'Downloading video info')
- entries = [{
- '_type': 'video',
- 'id': a.attrib['id'],
- 'title': '%s (%s)' % (title, a.attrib['assetID']),
- 'url': a.attrib['URL'],
- 'duration': int_or_none(a.attrib.get('length')),
- 'tbr': int_or_none(a.attrib.get('bitrate')),
- 'height': int_or_none(a.attrib.get('height')),
- 'width': int_or_none(a.attrib.get('width')),
- } for a in doc.findall('.//AdditionalAssets/asset')]
-
- return {
- '_type': 'playlist',
- 'id': pl_id,
- 'title': title,
- 'entries': entries,
- }
diff --git a/youtube_dl/extractor/shared.py b/youtube_dl/extractor/shared.py
index ff575f592..02295d1a4 100644
--- a/youtube_dl/extractor/shared.py
+++ b/youtube_dl/extractor/shared.py
@@ -1,13 +1,18 @@
from __future__ import unicode_literals
from .common import InfoExtractor
-from ..compat import compat_b64decode
+from ..compat import (
+ compat_b64decode,
+ compat_urllib_parse_unquote_plus,
+)
from ..utils import (
determine_ext,
ExtractorError,
int_or_none,
+ js_to_json,
KNOWN_EXTENSIONS,
parse_filesize,
+ rot47,
url_or_none,
urlencode_postdata,
)
@@ -112,16 +117,22 @@ class VivoIE(SharedBaseIE):
webpage, 'filesize', fatal=False))
def _extract_video_url(self, webpage, video_id, url):
- def decode_url(encoded_url):
+ def decode_url_old(encoded_url):
return compat_b64decode(encoded_url).decode('utf-8')
- stream_url = url_or_none(decode_url(self._search_regex(
+ stream_url = self._search_regex(
r'data-stream\s*=\s*(["\'])(?P(?:(?!\1).)+)\1', webpage,
- 'stream url', default=None, group='url')))
+ 'stream url', default=None, group='url')
+ if stream_url:
+ stream_url = url_or_none(decode_url_old(stream_url))
if stream_url:
return stream_url
- return self._parse_json(
+
+ def decode_url(encoded_url):
+ return rot47(compat_urllib_parse_unquote_plus(encoded_url))
+
+ return decode_url(self._parse_json(
self._search_regex(
- r'InitializeStream\s*\(\s*(["\'])(?P(?:(?!\1).)+)\1',
- webpage, 'stream', group='url'),
- video_id, transform_source=decode_url)[0]
+ r'(?s)InitializeStream\s*\(\s*({.+?})\s*\)\s*;', webpage,
+ 'stream'),
+ video_id, transform_source=js_to_json)['source'])
diff --git a/youtube_dl/extractor/slideslive.py b/youtube_dl/extractor/slideslive.py
index ed84322c5..d9ea76831 100644
--- a/youtube_dl/extractor/slideslive.py
+++ b/youtube_dl/extractor/slideslive.py
@@ -2,7 +2,7 @@
from __future__ import unicode_literals
from .common import InfoExtractor
-from ..utils import ExtractorError
+from ..utils import smuggle_url
class SlidesLiveIE(InfoExtractor):
@@ -14,9 +14,9 @@ class SlidesLiveIE(InfoExtractor):
'info_dict': {
'id': 'LMtgR8ba0b0',
'ext': 'mp4',
- 'title': '38902413: external video',
- 'description': '3890241320170925-9-1yd6ech.mp4',
- 'uploader': 'SlidesLive Administrator',
+ 'title': 'GCC IA16 backend',
+ 'description': 'Watch full version of this video at https://slideslive.com/38902413.',
+ 'uploader': 'SlidesLive Videos - A',
'uploader_id': 'UC62SdArr41t_-_fX40QCLRw',
'upload_date': '20170925',
}
@@ -24,16 +24,38 @@ class SlidesLiveIE(InfoExtractor):
# video_service_name = youtube
'url': 'https://slideslive.com/38903721/magic-a-scientific-resurrection-of-an-esoteric-legend',
'only_matching': True,
+ }, {
+ # video_service_name = url
+ 'url': 'https://slideslive.com/38922070/learning-transferable-skills-1',
+ 'only_matching': True,
+ }, {
+ # video_service_name = vimeo
+ 'url': 'https://slideslive.com/38921896/retrospectives-a-venue-for-selfreflection-in-ml-research-3',
+ 'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
video_data = self._download_json(
- url, video_id, headers={'Accept': 'application/json'})
+ 'https://ben.slideslive.com/player/' + video_id, video_id)
service_name = video_data['video_service_name'].lower()
- if service_name == 'youtube':
- yt_video_id = video_data['video_service_id']
- return self.url_result(yt_video_id, 'Youtube', video_id=yt_video_id)
+ assert service_name in ('url', 'vimeo', 'youtube')
+ service_id = video_data['video_service_id']
+ info = {
+ 'id': video_id,
+ 'thumbnail': video_data.get('thumbnail'),
+ 'url': service_id,
+ }
+ if service_name == 'url':
+ info['title'] = video_data['title']
else:
- raise ExtractorError(
- 'Unsupported service name: {0}'.format(service_name), expected=True)
+ info.update({
+ '_type': 'url_transparent',
+ 'ie_key': service_name.capitalize(),
+ 'title': video_data.get('title'),
+ })
+ if service_name == 'vimeo':
+ info['url'] = smuggle_url(
+ 'https://player.vimeo.com/video/' + service_id,
+ {'http_headers': {'Referer': url}})
+ return info
diff --git a/youtube_dl/extractor/soundcloud.py b/youtube_dl/extractor/soundcloud.py
index 3a8626e02..b3ffef8df 100644
--- a/youtube_dl/extractor/soundcloud.py
+++ b/youtube_dl/extractor/soundcloud.py
@@ -9,16 +9,17 @@ from .common import (
SearchInfoExtractor
)
from ..compat import (
+ compat_HTTPError,
+ compat_kwargs,
compat_str,
compat_urlparse,
- compat_urllib_parse_urlencode,
)
from ..utils import (
ExtractorError,
float_or_none,
+ HEADRequest,
int_or_none,
KNOWN_EXTENSIONS,
- merge_dicts,
mimetype2ext,
str_or_none,
try_get,
@@ -28,6 +29,30 @@ from ..utils import (
)
+class SoundcloudEmbedIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:w|player|p)\.soundcloud\.com/player/?.*?\burl=(?P.+)'
+ _TEST = {
+ # from https://www.soundi.fi/uutiset/ennakkokuuntelussa-timo-kaukolammen-station-to-station-to-station-julkaisua-juhlitaan-tanaan-g-livelabissa/
+ 'url': 'https://w.soundcloud.com/player/?visual=true&url=https%3A%2F%2Fapi.soundcloud.com%2Fplaylists%2F922213810&show_artwork=true&maxwidth=640&maxheight=960&dnt=1&secret_token=s-ziYey',
+ 'only_matching': True,
+ }
+
+ @staticmethod
+ def _extract_urls(webpage):
+ return [m.group('url') for m in re.finditer(
+ r']+src=(["\'])(?P(?:https?://)?(?:w\.)?soundcloud\.com/player.+?)\1',
+ webpage)]
+
+ def _real_extract(self, url):
+ query = compat_urlparse.parse_qs(
+ compat_urlparse.urlparse(url).query)
+ api_url = query['url'][0]
+ secret_token = query.get('secret_token')
+ if secret_token:
+ api_url = update_url_query(api_url, {'secret_token': secret_token[0]})
+ return self.url_result(api_url)
+
+
class SoundcloudIE(InfoExtractor):
"""Information extractor for soundcloud.com
To access the media, the uid of the song and a stream token
@@ -44,9 +69,8 @@ class SoundcloudIE(InfoExtractor):
(?!(?:tracks|albums|sets(?:/.+?)?|reposts|likes|spotlight)/?(?:$|[?#]))
(?P[\w\d-]+)/?
(?P<token>[^?]+?)?(?:[?].*)?$)
- |(?:api\.soundcloud\.com/tracks/(?P<track_id>\d+)
+ |(?:api(?:-v2)?\.soundcloud\.com/tracks/(?P<track_id>\d+)
(?:/?\?secret_token=(?P<secret_token>[^&]+))?)
- |(?P<player>(?:w|player|p.)\.soundcloud\.com/player/?.*?url=.*)
)
'''
IE_NAME = 'soundcloud'
@@ -60,6 +84,7 @@ class SoundcloudIE(InfoExtractor):
'title': 'Lostin Powers - She so Heavy (SneakPreview) Adrian Ackers Blueprint 1',
'description': 'No Downloads untill we record the finished version this weekend, i was too pumped n i had to post it , earl is prolly gonna b hella p.o\'d',
'uploader': 'E.T. ExTerrestrial Music',
+ 'uploader_id': '1571244',
'timestamp': 1349920598,
'upload_date': '20121011',
'duration': 143.216,
@@ -79,6 +104,7 @@ class SoundcloudIE(InfoExtractor):
'title': 'Goldrushed',
'description': 'From Stockholm Sweden\r\nPovel / Magnus / Filip / David\r\nwww.theroyalconcept.com',
'uploader': 'The Royal Concept',
+ 'uploader_id': '9615865',
'timestamp': 1337635207,
'upload_date': '20120521',
'duration': 30,
@@ -92,6 +118,7 @@ class SoundcloudIE(InfoExtractor):
# rtmp
'skip_download': True,
},
+ 'skip': 'Preview',
},
# private link
{
@@ -103,6 +130,7 @@ class SoundcloudIE(InfoExtractor):
'title': 'Youtube - Dl Test Video \'\' Ä↭',
'description': 'test chars: \"\'/\\ä↭',
'uploader': 'jaimeMF',
+ 'uploader_id': '69767071',
'timestamp': 1386604920,
'upload_date': '20131209',
'duration': 9.927,
@@ -123,6 +151,7 @@ class SoundcloudIE(InfoExtractor):
'title': 'Youtube - Dl Test Video \'\' Ä↭',
'description': 'test chars: \"\'/\\ä↭',
'uploader': 'jaimeMF',
+ 'uploader_id': '69767071',
'timestamp': 1386604920,
'upload_date': '20131209',
'duration': 9.927,
@@ -143,6 +172,7 @@ class SoundcloudIE(InfoExtractor):
'title': 'Bus Brakes',
'description': 'md5:0053ca6396e8d2fd7b7e1595ef12ab66',
'uploader': 'oddsamples',
+ 'uploader_id': '73680509',
'timestamp': 1389232924,
'upload_date': '20140109',
'duration': 17.346,
@@ -163,6 +193,7 @@ class SoundcloudIE(InfoExtractor):
'title': 'Uplifting Only 238 [No Talking] (incl. Alex Feed Guestmix) (Aug 31, 2017) [wav]',
'description': 'md5:fa20ee0fca76a3d6df8c7e57f3715366',
'uploader': 'Ori Uplift Music',
+ 'uploader_id': '12563093',
'timestamp': 1504206263,
'upload_date': '20170831',
'duration': 7449.096,
@@ -183,6 +214,7 @@ class SoundcloudIE(InfoExtractor):
'title': 'Sideways (Prod. Mad Real)',
'description': 'md5:d41d8cd98f00b204e9800998ecf8427e',
'uploader': 'garyvee',
+ 'uploader_id': '2366352',
'timestamp': 1488152409,
'upload_date': '20170226',
'duration': 207.012,
@@ -197,7 +229,7 @@ class SoundcloudIE(InfoExtractor):
'skip_download': True,
},
},
- # not avaialble via api.soundcloud.com/i1/tracks/id/streams
+ # not available via api.soundcloud.com/i1/tracks/id/streams
{
'url': 'https://soundcloud.com/giovannisarani/mezzo-valzer',
'md5': 'e22aecd2bc88e0e4e432d7dcc0a1abf7',
@@ -207,6 +239,7 @@ class SoundcloudIE(InfoExtractor):
'title': 'Mezzo Valzer',
'description': 'md5:4138d582f81866a530317bae316e8b61',
'uploader': 'Giovanni Sarani',
+ 'uploader_id': '3352531',
'timestamp': 1551394171,
'upload_date': '20190228',
'duration': 180.157,
@@ -221,114 +254,110 @@ class SoundcloudIE(InfoExtractor):
}
]
- _CLIENT_ID = 'BeGVhOrGmfboy1LtiHTQF6Ejpt9ULJCI'
+ _API_BASE = 'https://api.soundcloud.com/'
+ _API_V2_BASE = 'https://api-v2.soundcloud.com/'
+ _BASE_URL = 'https://soundcloud.com/'
+ _IMAGE_REPL_RE = r'-([0-9a-z]+)\.jpg'
- @staticmethod
- def _extract_urls(webpage):
- return [m.group('url') for m in re.finditer(
- r'<iframe[^>]+src=(["\'])(?P<url>(?:https?://)?(?:w\.)?soundcloud\.com/player.+?)\1',
- webpage)]
+ _ARTWORK_MAP = {
+ 'mini': 16,
+ 'tiny': 20,
+ 'small': 32,
+ 'badge': 47,
+ 't67x67': 67,
+ 'large': 100,
+ 't300x300': 300,
+ 'crop': 400,
+ 't500x500': 500,
+ 'original': 0,
+ }
+
+ def _update_client_id(self):
+ webpage = self._download_webpage('https://soundcloud.com/', None)
+ for src in reversed(re.findall(r'<script[^>]+src="([^"]+)"', webpage)):
+ script = self._download_webpage(src, None, fatal=False)
+ if script:
+ client_id = self._search_regex(
+ r'client_id\s*:\s*"([0-9a-zA-Z]{32})"',
+ script, 'client id', default=None)
+ if client_id:
+ self._CLIENT_ID = client_id
+ self._downloader.cache.store('soundcloud', 'client_id', client_id)
+ return
+ raise ExtractorError('Unable to extract client id')
+
+ def _download_json(self, *args, **kwargs):
+ query = kwargs.get('query', {}).copy()
+ for _ in range(2):
+ query['client_id'] = self._CLIENT_ID
+ kwargs['query'] = query
+ try:
+ return super(SoundcloudIE, self)._download_json(*args, **compat_kwargs(kwargs))
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+ self._update_client_id()
+ continue
+ raise
+
+ def _real_initialize(self):
+ self._CLIENT_ID = self._downloader.cache.load('soundcloud', 'client_id') or 'YUKXoArFcqrlQn9tfNHvvyfnDISj04zk'
@classmethod
def _resolv_url(cls, url):
- return 'https://api.soundcloud.com/resolve.json?url=' + url + '&client_id=' + cls._CLIENT_ID
+ return SoundcloudIE._API_V2_BASE + 'resolve?url=' + url
- def _extract_info_dict(self, info, full_title=None, quiet=False, secret_token=None):
+ def _extract_info_dict(self, info, full_title=None, secret_token=None, version=2):
track_id = compat_str(info['id'])
title = info['title']
- name = full_title or track_id
- if quiet:
- self.report_extraction(name)
- thumbnail = info.get('artwork_url') or info.get('user', {}).get('avatar_url')
- if isinstance(thumbnail, compat_str):
- thumbnail = thumbnail.replace('-large', '-t500x500')
- username = try_get(info, lambda x: x['user']['username'], compat_str)
-
- def extract_count(key):
- return int_or_none(info.get('%s_count' % key))
-
- like_count = extract_count('favoritings')
- if like_count is None:
- like_count = extract_count('likes')
-
- result = {
- 'id': track_id,
- 'uploader': username,
- 'timestamp': unified_timestamp(info.get('created_at')),
- 'title': title,
- 'description': info.get('description'),
- 'thumbnail': thumbnail,
- 'duration': float_or_none(info.get('duration'), 1000),
- 'webpage_url': info.get('permalink_url'),
- 'license': info.get('license'),
- 'view_count': extract_count('playback'),
- 'like_count': like_count,
- 'comment_count': extract_count('comment'),
- 'repost_count': extract_count('reposts'),
- 'genre': info.get('genre'),
- }
+ track_base_url = self._API_BASE + 'tracks/%s' % track_id
format_urls = set()
formats = []
query = {'client_id': self._CLIENT_ID}
- if secret_token is not None:
+ if secret_token:
query['secret_token'] = secret_token
- if info.get('downloadable', False):
- # We can build a direct link to the song
+
+ if info.get('downloadable') and info.get('has_downloads_left'):
format_url = update_url_query(
- 'https://api.soundcloud.com/tracks/%s/download' % track_id, query)
+ info.get('download_url') or track_base_url + '/download', query)
format_urls.add(format_url)
+ if version == 2:
+ v1_info = self._download_json(
+ track_base_url, track_id, query=query, fatal=False) or {}
+ else:
+ v1_info = info
formats.append({
'format_id': 'download',
- 'ext': info.get('original_format', 'mp3'),
+ 'ext': v1_info.get('original_format') or 'mp3',
+ 'filesize': int_or_none(v1_info.get('original_content_size')),
'url': format_url,
- 'vcodec': 'none',
'preference': 10,
})
- # Old API, does not work for some tracks (e.g.
- # https://soundcloud.com/giovannisarani/mezzo-valzer)
- format_dict = self._download_json(
- 'https://api.soundcloud.com/i1/tracks/%s/streams' % track_id,
- track_id, 'Downloading track url', query=query, fatal=False)
+ def invalid_url(url):
+ return not url or url in format_urls or re.search(r'/(?:preview|playlist)/0/30/', url)
- if format_dict:
- for key, stream_url in format_dict.items():
- if stream_url in format_urls:
- continue
- format_urls.add(stream_url)
- ext, abr = 'mp3', None
- mobj = re.search(r'_([^_]+)_(\d+)_url', key)
- if mobj:
- ext, abr = mobj.groups()
- abr = int(abr)
- if key.startswith('http'):
- stream_formats = [{
- 'format_id': key,
- 'ext': ext,
- 'url': stream_url,
- }]
- elif key.startswith('rtmp'):
- # The url doesn't have an rtmp app, we have to extract the playpath
- url, path = stream_url.split('mp3:', 1)
- stream_formats = [{
- 'format_id': key,
- 'url': url,
- 'play_path': 'mp3:' + path,
- 'ext': 'flv',
- }]
- elif key.startswith('hls'):
- stream_formats = self._extract_m3u8_formats(
- stream_url, track_id, ext, entry_protocol='m3u8_native',
- m3u8_id=key, fatal=False)
- else:
- continue
-
- if abr:
- for f in stream_formats:
- f['abr'] = abr
-
- formats.extend(stream_formats)
+ def add_format(f, protocol):
+ mobj = re.search(r'\.(?P<abr>\d+)\.(?P<ext>[0-9a-z]{3,4})(?=[/?])', stream_url)
+ if mobj:
+ for k, v in mobj.groupdict().items():
+ if not f.get(k):
+ f[k] = v
+ format_id_list = []
+ if protocol:
+ format_id_list.append(protocol)
+ for k in ('ext', 'abr'):
+ v = f.get(k)
+ if v:
+ format_id_list.append(v)
+ abr = f.get('abr')
+ if abr:
+ f['abr'] = int(abr)
+ f.update({
+ 'format_id': '_'.join(format_id_list),
+ 'protocol': 'm3u8_native' if protocol == 'hls' else 'http',
+ })
+ formats.append(f)
# New API
transcodings = try_get(
@@ -337,129 +366,163 @@ class SoundcloudIE(InfoExtractor):
if not isinstance(t, dict):
continue
format_url = url_or_none(t.get('url'))
- if not format_url:
+ if not format_url or t.get('snipped') or '/preview/' in format_url:
continue
stream = self._download_json(
- update_url_query(format_url, query), track_id, fatal=False)
+ format_url, track_id, query=query, fatal=False)
if not isinstance(stream, dict):
continue
stream_url = url_or_none(stream.get('url'))
- if not stream_url:
- continue
- if stream_url in format_urls:
+ if invalid_url(stream_url):
continue
format_urls.add(stream_url)
- protocol = try_get(t, lambda x: x['format']['protocol'], compat_str)
+ stream_format = t.get('format') or {}
+ protocol = stream_format.get('protocol')
if protocol != 'hls' and '/hls' in format_url:
protocol = 'hls'
ext = None
preset = str_or_none(t.get('preset'))
if preset:
ext = preset.split('_')[0]
- if ext not in KNOWN_EXTENSIONS:
- mimetype = try_get(
- t, lambda x: x['format']['mime_type'], compat_str)
- ext = mimetype2ext(mimetype) or 'mp3'
- format_id_list = []
- if protocol:
- format_id_list.append(protocol)
- format_id_list.append(ext)
- format_id = '_'.join(format_id_list)
- formats.append({
+ if ext not in KNOWN_EXTENSIONS:
+ ext = mimetype2ext(stream_format.get('mime_type'))
+ add_format({
'url': stream_url,
- 'format_id': format_id,
'ext': ext,
- 'protocol': 'm3u8_native' if protocol == 'hls' else 'http',
- })
+ }, 'http' if protocol == 'progressive' else protocol)
+
+ if not formats:
+ # Old API, does not work for some tracks (e.g.
+ # https://soundcloud.com/giovannisarani/mezzo-valzer)
+ # and might serve preview URLs (e.g.
+ # http://www.soundcloud.com/snbrn/ele)
+ format_dict = self._download_json(
+ track_base_url + '/streams', track_id,
+ 'Downloading track url', query=query, fatal=False) or {}
+
+ for key, stream_url in format_dict.items():
+ if invalid_url(stream_url):
+ continue
+ format_urls.add(stream_url)
+ mobj = re.search(r'(http|hls)_([^_]+)_(\d+)_url', key)
+ if mobj:
+ protocol, ext, abr = mobj.groups()
+ add_format({
+ 'abr': abr,
+ 'ext': ext,
+ 'url': stream_url,
+ }, protocol)
if not formats:
# We fallback to the stream_url in the original info, this
# cannot be always used, sometimes it can give an HTTP 404 error
- formats.append({
- 'format_id': 'fallback',
- 'url': update_url_query(info['stream_url'], query),
- 'ext': 'mp3',
- })
- self._check_formats(formats, track_id)
+ urlh = self._request_webpage(
+ HEADRequest(info.get('stream_url') or track_base_url + '/stream'),
+ track_id, query=query, fatal=False)
+ if urlh:
+ stream_url = urlh.geturl()
+ if not invalid_url(stream_url):
+ add_format({'url': stream_url}, 'http')
for f in formats:
f['vcodec'] = 'none'
self._sort_formats(formats)
- result['formats'] = formats
- return result
+ user = info.get('user') or {}
+
+ thumbnails = []
+ artwork_url = info.get('artwork_url')
+ thumbnail = artwork_url or user.get('avatar_url')
+ if isinstance(thumbnail, compat_str):
+ if re.search(self._IMAGE_REPL_RE, thumbnail):
+ for image_id, size in self._ARTWORK_MAP.items():
+ i = {
+ 'id': image_id,
+ 'url': re.sub(self._IMAGE_REPL_RE, '-%s.jpg' % image_id, thumbnail),
+ }
+ if image_id == 'tiny' and not artwork_url:
+ size = 18
+ elif image_id == 'original':
+ i['preference'] = 10
+ if size:
+ i.update({
+ 'width': size,
+ 'height': size,
+ })
+ thumbnails.append(i)
+ else:
+ thumbnails = [{'url': thumbnail}]
+
+ def extract_count(key):
+ return int_or_none(info.get('%s_count' % key))
+
+ return {
+ 'id': track_id,
+ 'uploader': user.get('username'),
+ 'uploader_id': str_or_none(user.get('id')) or user.get('permalink'),
+ 'uploader_url': user.get('permalink_url'),
+ 'timestamp': unified_timestamp(info.get('created_at')),
+ 'title': title,
+ 'description': info.get('description'),
+ 'thumbnails': thumbnails,
+ 'duration': float_or_none(info.get('duration'), 1000),
+ 'webpage_url': info.get('permalink_url'),
+ 'license': info.get('license'),
+ 'view_count': extract_count('playback'),
+ 'like_count': extract_count('favoritings') or extract_count('likes'),
+ 'comment_count': extract_count('comment'),
+ 'repost_count': extract_count('reposts'),
+ 'genre': info.get('genre'),
+ 'formats': formats
+ }
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url, flags=re.VERBOSE)
- if mobj is None:
- raise ExtractorError('Invalid URL: %s' % url)
+ mobj = re.match(self._VALID_URL, url)
track_id = mobj.group('track_id')
- new_info = {}
- if track_id is not None:
- info_json_url = 'https://api.soundcloud.com/tracks/' + track_id + '.json?client_id=' + self._CLIENT_ID
+ query = {}
+ if track_id:
+ info_json_url = self._API_V2_BASE + 'tracks/' + track_id
full_title = track_id
token = mobj.group('secret_token')
if token:
- info_json_url += '&secret_token=' + token
- elif mobj.group('player'):
- query = compat_urlparse.parse_qs(compat_urlparse.urlparse(url).query)
- real_url = query['url'][0]
- # If the token is in the query of the original url we have to
- # manually add it
- if 'secret_token' in query:
- real_url += '?secret_token=' + query['secret_token'][0]
- return self.url_result(real_url)
+ query['secret_token'] = token
else:
- # extract uploader (which is in the url)
- uploader = mobj.group('uploader')
- # extract simple title (uploader + slug of song title)
- slug_title = mobj.group('title')
+ full_title = resolve_title = '%s/%s' % mobj.group('uploader', 'title')
token = mobj.group('token')
- full_title = resolve_title = '%s/%s' % (uploader, slug_title)
if token:
resolve_title += '/%s' % token
+ info_json_url = self._resolv_url(self._BASE_URL + resolve_title)
- webpage = self._download_webpage(url, full_title, fatal=False)
- if webpage:
- entries = self._parse_json(
- self._search_regex(
- r'var\s+c\s*=\s*(\[.+?\])\s*,\s*o\s*=Date\b', webpage,
- 'data', default='[]'), full_title, fatal=False)
- if entries:
- for e in entries:
- if not isinstance(e, dict):
- continue
- if e.get('id') != 67:
- continue
- data = try_get(e, lambda x: x['data'][0], dict)
- if data:
- new_info = data
- break
- info_json_url = self._resolv_url(
- 'https://soundcloud.com/%s' % resolve_title)
-
- # Contains some additional info missing from new_info
+ version = 2
info = self._download_json(
- info_json_url, full_title, 'Downloading info JSON')
+ info_json_url, full_title, 'Downloading info JSON', query=query, fatal=False)
+ if not info:
+ info = self._download_json(
+ info_json_url.replace(self._API_V2_BASE, self._API_BASE),
+ full_title, 'Downloading info JSON', query=query)
+ version = 1
- return self._extract_info_dict(
- merge_dicts(info, new_info), full_title, secret_token=token)
+ return self._extract_info_dict(info, full_title, token, version)
class SoundcloudPlaylistBaseIE(SoundcloudIE):
- @staticmethod
- def _extract_id(e):
- return compat_str(e['id']) if e.get('id') else None
-
- def _extract_track_entries(self, tracks):
- return [
- self.url_result(
- track['permalink_url'], SoundcloudIE.ie_key(),
- video_id=self._extract_id(track))
- for track in tracks if track.get('permalink_url')]
+ def _extract_track_entries(self, tracks, token=None):
+ entries = []
+ for track in tracks:
+ track_id = str_or_none(track.get('id'))
+ url = track.get('permalink_url')
+ if not url:
+ if not track_id:
+ continue
+ url = self._API_V2_BASE + 'tracks/' + track_id
+ if token:
+ url += '?secret_token=' + token
+ entries.append(self.url_result(
+ url, SoundcloudIE.ie_key(), track_id))
+ return entries
class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
@@ -480,54 +543,41 @@ class SoundcloudSetIE(SoundcloudPlaylistBaseIE):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
- # extract uploader (which is in the url)
- uploader = mobj.group('uploader')
- # extract simple title (uploader + slug of song title)
- slug_title = mobj.group('slug_title')
- full_title = '%s/sets/%s' % (uploader, slug_title)
- url = 'https://soundcloud.com/%s/sets/%s' % (uploader, slug_title)
-
+ full_title = '%s/sets/%s' % mobj.group('uploader', 'slug_title')
token = mobj.group('token')
if token:
full_title += '/' + token
- url += '/' + token
- resolv_url = self._resolv_url(url)
- info = self._download_json(resolv_url, full_title)
+ info = self._download_json(self._resolv_url(
+ self._BASE_URL + full_title), full_title)
if 'errors' in info:
msgs = (compat_str(err['error_message']) for err in info['errors'])
raise ExtractorError('unable to download video webpage: %s' % ','.join(msgs))
- entries = self._extract_track_entries(info['tracks'])
+ entries = self._extract_track_entries(info['tracks'], token)
- return {
- '_type': 'playlist',
- 'entries': entries,
- 'id': '%s' % info['id'],
- 'title': info['title'],
- }
+ return self.playlist_result(
+ entries, str_or_none(info.get('id')), info.get('title'))
class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE):
- _API_V2_BASE = 'https://api-v2.soundcloud.com'
-
def _extract_playlist(self, base_url, playlist_id, playlist_title):
COMMON_QUERY = {
- 'limit': 50,
- 'client_id': self._CLIENT_ID,
+ 'limit': 2000000000,
'linked_partitioning': '1',
}
query = COMMON_QUERY.copy()
query['offset'] = 0
- next_href = base_url + '?' + compat_urllib_parse_urlencode(query)
+ next_href = base_url
entries = []
for i in itertools.count():
response = self._download_json(
- next_href, playlist_id, 'Downloading track page %s' % (i + 1))
+ next_href, playlist_id,
+ 'Downloading track page %s' % (i + 1), query=query)
collection = response['collection']
@@ -546,9 +596,8 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE):
continue
return self.url_result(
permalink_url,
- ie=SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None,
- video_id=self._extract_id(cand),
- video_title=cand.get('title'))
+ SoundcloudIE.ie_key() if SoundcloudIE.suitable(permalink_url) else None,
+ str_or_none(cand.get('id')), cand.get('title'))
for e in collection:
entry = resolve_entry((e, e.get('track'), e.get('playlist')))
@@ -559,11 +608,10 @@ class SoundcloudPagedPlaylistBaseIE(SoundcloudPlaylistBaseIE):
if not next_href:
break
- parsed_next_href = compat_urlparse.urlparse(response['next_href'])
- qs = compat_urlparse.parse_qs(parsed_next_href.query)
- qs.update(COMMON_QUERY)
- next_href = compat_urlparse.urlunparse(
- parsed_next_href._replace(query=compat_urllib_parse_urlencode(qs, True)))
+ next_href = response['next_href']
+ parsed_next_href = compat_urlparse.urlparse(next_href)
+ query = compat_urlparse.parse_qs(parsed_next_href.query)
+ query.update(COMMON_QUERY)
return {
'_type': 'playlist',
@@ -609,7 +657,7 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE):
'url': 'https://soundcloud.com/jcv246/sets',
'info_dict': {
'id': '12982173',
- 'title': 'Jordi / cv (Playlists)',
+ 'title': 'Jordi / cv (Sets)',
},
'playlist_mincount': 2,
}, {
@@ -636,39 +684,29 @@ class SoundcloudUserIE(SoundcloudPagedPlaylistBaseIE):
}]
_BASE_URL_MAP = {
- 'all': '%s/stream/users/%%s' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
- 'tracks': '%s/users/%%s/tracks' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
- 'albums': '%s/users/%%s/albums' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
- 'sets': '%s/users/%%s/playlists' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
- 'reposts': '%s/stream/users/%%s/reposts' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
- 'likes': '%s/users/%%s/likes' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
- 'spotlight': '%s/users/%%s/spotlight' % SoundcloudPagedPlaylistBaseIE._API_V2_BASE,
- }
-
- _TITLE_MAP = {
- 'all': 'All',
- 'tracks': 'Tracks',
- 'albums': 'Albums',
- 'sets': 'Playlists',
- 'reposts': 'Reposts',
- 'likes': 'Likes',
- 'spotlight': 'Spotlight',
+ 'all': 'stream/users/%s',
+ 'tracks': 'users/%s/tracks',
+ 'albums': 'users/%s/albums',
+ 'sets': 'users/%s/playlists',
+ 'reposts': 'stream/users/%s/reposts',
+ 'likes': 'users/%s/likes',
+ 'spotlight': 'users/%s/spotlight',
}
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
uploader = mobj.group('user')
- url = 'https://soundcloud.com/%s/' % uploader
- resolv_url = self._resolv_url(url)
user = self._download_json(
- resolv_url, uploader, 'Downloading user info')
+ self._resolv_url(self._BASE_URL + uploader),
+ uploader, 'Downloading user info')
resource = mobj.group('rsrc') or 'all'
return self._extract_playlist(
- self._BASE_URL_MAP[resource] % user['id'], compat_str(user['id']),
- '%s (%s)' % (user['username'], self._TITLE_MAP[resource]))
+ self._API_V2_BASE + self._BASE_URL_MAP[resource] % user['id'],
+ str_or_none(user.get('id')),
+ '%s (%s)' % (user['username'], resource.capitalize()))
class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE):
@@ -678,7 +716,7 @@ class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE):
'url': 'https://soundcloud.com/stations/track/officialsundial/your-text',
'info_dict': {
'id': '286017854',
- 'title': 'Track station: your-text',
+ 'title': 'Track station: your text',
},
'playlist_mincount': 47,
}]
@@ -686,19 +724,17 @@ class SoundcloudTrackStationIE(SoundcloudPagedPlaylistBaseIE):
def _real_extract(self, url):
track_name = self._match_id(url)
- webpage = self._download_webpage(url, track_name)
-
+ track = self._download_json(self._resolv_url(url), track_name)
track_id = self._search_regex(
- r'soundcloud:track-stations:(\d+)', webpage, 'track id')
+ r'soundcloud:track-stations:(\d+)', track['id'], 'track id')
return self._extract_playlist(
- '%s/stations/soundcloud:track-stations:%s/tracks'
- % (self._API_V2_BASE, track_id),
- track_id, 'Track station: %s' % track_name)
+ self._API_V2_BASE + 'stations/%s/tracks' % track['id'],
+ track_id, 'Track station: %s' % track['title'])
class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE):
- _VALID_URL = r'https?://api\.soundcloud\.com/playlists/(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$'
+ _VALID_URL = r'https?://api(?:-v2)?\.soundcloud\.com/playlists/(?P<id>[0-9]+)(?:/?\?secret_token=(?P<token>[^&]+?))?$'
IE_NAME = 'soundcloud:playlist'
_TESTS = [{
'url': 'https://api.soundcloud.com/playlists/4110309',
@@ -713,29 +749,20 @@ class SoundcloudPlaylistIE(SoundcloudPlaylistBaseIE):
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
playlist_id = mobj.group('id')
- base_url = '%s//api.soundcloud.com/playlists/%s.json?' % (self.http_scheme(), playlist_id)
- data_dict = {
- 'client_id': self._CLIENT_ID,
- }
+ query = {}
token = mobj.group('token')
-
if token:
- data_dict['secret_token'] = token
+ query['secret_token'] = token
- data = compat_urllib_parse_urlencode(data_dict)
data = self._download_json(
- base_url + data, playlist_id, 'Downloading playlist')
+ self._API_V2_BASE + 'playlists/' + playlist_id,
+ playlist_id, 'Downloading playlist', query=query)
- entries = self._extract_track_entries(data['tracks'])
+ entries = self._extract_track_entries(data['tracks'], token)
- return {
- '_type': 'playlist',
- 'id': playlist_id,
- 'title': data.get('title'),
- 'description': data.get('description'),
- 'entries': entries,
- }
+ return self.playlist_result(
+ entries, playlist_id, data.get('title'), data.get('description'))
class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE):
@@ -753,18 +780,17 @@ class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE):
_SEARCH_KEY = 'scsearch'
_MAX_RESULTS_PER_PAGE = 200
_DEFAULT_RESULTS_PER_PAGE = 50
- _API_V2_BASE = 'https://api-v2.soundcloud.com'
def _get_collection(self, endpoint, collection_id, **query):
limit = min(
query.get('limit', self._DEFAULT_RESULTS_PER_PAGE),
self._MAX_RESULTS_PER_PAGE)
- query['limit'] = limit
- query['client_id'] = self._CLIENT_ID
- query['linked_partitioning'] = '1'
- query['offset'] = 0
- data = compat_urllib_parse_urlencode(query)
- next_url = '{0}{1}?{2}'.format(self._API_V2_BASE, endpoint, data)
+ query.update({
+ 'limit': limit,
+ 'linked_partitioning': 1,
+ 'offset': 0,
+ })
+ next_url = update_url_query(self._API_V2_BASE + endpoint, query)
collected_results = 0
@@ -791,5 +817,5 @@ class SoundcloudSearchIE(SearchInfoExtractor, SoundcloudIE):
break
def _get_n_results(self, query, n):
- tracks = self._get_collection('/search/tracks', query, limit=n, q=query)
+ tracks = self._get_collection('search/tracks', query, limit=n, q=query)
return self.playlist_result(tracks, playlist_title=query)
diff --git a/youtube_dl/extractor/spankbang.py b/youtube_dl/extractor/spankbang.py
index f11d728ca..61ca902ce 100644
--- a/youtube_dl/extractor/spankbang.py
+++ b/youtube_dl/extractor/spankbang.py
@@ -4,7 +4,9 @@ import re
from .common import InfoExtractor
from ..utils import (
+ determine_ext,
ExtractorError,
+ merge_dicts,
orderedSet,
parse_duration,
parse_resolution,
@@ -26,6 +28,8 @@ class SpankBangIE(InfoExtractor):
'description': 'dillion harper masturbates on a bed',
'thumbnail': r're:^https?://.*\.jpg$',
'uploader': 'silly2587',
+ 'timestamp': 1422571989,
+ 'upload_date': '20150129',
'age_limit': 18,
}
}, {
@@ -61,7 +65,7 @@ class SpankBangIE(InfoExtractor):
url.replace('/%s/embed' % video_id, '/%s/video' % video_id),
video_id, headers={'Cookie': 'country=US'})
- if re.search(r'<[^>]+\bid=["\']video_removed', webpage):
+ if re.search(r'<[^>]+\b(?:id|class)=["\']video_removed', webpage):
raise ExtractorError(
'Video %s is not available' % video_id, expected=True)
@@ -72,11 +76,20 @@ class SpankBangIE(InfoExtractor):
if not f_url:
return
f = parse_resolution(format_id)
- f.update({
- 'url': f_url,
- 'format_id': format_id,
- })
- formats.append(f)
+ ext = determine_ext(f_url)
+ if format_id.startswith('m3u8') or ext == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ f_url, video_id, 'mp4', entry_protocol='m3u8_native',
+ m3u8_id='hls', fatal=False))
+ elif format_id.startswith('mpd') or ext == 'mpd':
+ formats.extend(self._extract_mpd_formats(
+ f_url, video_id, mpd_id='dash', fatal=False))
+ elif ext == 'mp4' or f.get('width') or f.get('height'):
+ f.update({
+ 'url': f_url,
+ 'format_id': format_id,
+ })
+ formats.append(f)
STREAM_URL_PREFIX = 'stream_url_'
@@ -90,47 +103,46 @@ class SpankBangIE(InfoExtractor):
r'data-streamkey\s*=\s*(["\'])(?P<value>(?:(?!\1).)+)\1',
webpage, 'stream key', group='value')
- sb_csrf_session = self._get_cookies(
- 'https://spankbang.com')['sb_csrf_session'].value
-
stream = self._download_json(
'https://spankbang.com/api/videos/stream', video_id,
'Downloading stream JSON', data=urlencode_postdata({
'id': stream_key,
'data': 0,
- 'sb_csrf_session': sb_csrf_session,
}), headers={
'Referer': url,
- 'X-CSRFToken': sb_csrf_session,
+ 'X-Requested-With': 'XMLHttpRequest',
})
for format_id, format_url in stream.items():
- if format_id.startswith(STREAM_URL_PREFIX):
- extract_format(
- format_id[len(STREAM_URL_PREFIX):], format_url)
+ if format_url and isinstance(format_url, list):
+ format_url = format_url[0]
+ extract_format(format_id, format_url)
- self._sort_formats(formats)
+ self._sort_formats(formats, field_preference=('preference', 'height', 'width', 'fps', 'tbr', 'format_id'))
+
+ info = self._search_json_ld(webpage, video_id, default={})
title = self._html_search_regex(
- r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title')
+ r'(?s)<h1[^>]*>(.+?)</h1>', webpage, 'title', default=None)
description = self._search_regex(
r'<div[^>]+\bclass=["\']bottom[^>]+>\s*<p>[^<]*</p>\s*<p>([^<]+)',
- webpage, 'description', fatal=False)
- thumbnail = self._og_search_thumbnail(webpage)
- uploader = self._search_regex(
- r'class="user"[^>]*><img[^>]+>([^<]+)',
+ webpage, 'description', default=None)
+ thumbnail = self._og_search_thumbnail(webpage, default=None)
+ uploader = self._html_search_regex(
+ (r'(?s)<li[^>]+class=["\']profile[^>]+>(.+?)</a>',
+ r'class="user"[^>]*><img[^>]+>([^<]+)'),
webpage, 'uploader', default=None)
duration = parse_duration(self._search_regex(
r'<div[^>]+\bclass=["\']right_side[^>]+>\s*<span>([^<]+)',
- webpage, 'duration', fatal=False))
+ webpage, 'duration', default=None))
view_count = str_to_int(self._search_regex(
- r'([\d,.]+)\s+plays', webpage, 'view count', fatal=False))
+ r'([\d,.]+)\s+plays', webpage, 'view count', default=None))
age_limit = self._rta_search(webpage)
- return {
+ return merge_dicts({
'id': video_id,
- 'title': title,
+ 'title': title or video_id,
'description': description,
'thumbnail': thumbnail,
'uploader': uploader,
@@ -138,7 +150,8 @@ class SpankBangIE(InfoExtractor):
'view_count': view_count,
'formats': formats,
'age_limit': age_limit,
- }
+ }, info
+ )
class SpankBangPlaylistIE(InfoExtractor):
diff --git a/youtube_dl/extractor/spike.py b/youtube_dl/extractor/spike.py
index 21b93a5b3..7c11ea7aa 100644
--- a/youtube_dl/extractor/spike.py
+++ b/youtube_dl/extractor/spike.py
@@ -22,7 +22,7 @@ class BellatorIE(MTVServicesInfoExtractor):
'only_matching': True,
}]
- _FEED_URL = 'http://www.spike.com/feeds/mrss/'
+ _FEED_URL = 'http://www.bellator.com/feeds/mrss/'
_GEO_COUNTRIES = ['US']
diff --git a/youtube_dl/extractor/streamango.py b/youtube_dl/extractor/streamango.py
deleted file mode 100644
index f1e17dd88..000000000
--- a/youtube_dl/extractor/streamango.py
+++ /dev/null
@@ -1,128 +0,0 @@
-# coding: utf-8
-from __future__ import unicode_literals
-
-import re
-
-from .common import InfoExtractor
-from ..compat import compat_chr
-from ..utils import (
- determine_ext,
- ExtractorError,
- int_or_none,
- js_to_json,
-)
-
-
-class StreamangoIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?(?:streamango\.com|fruithosts\.net|streamcherry\.com)/(?:f|embed)/(?P<id>[^/?#&]+)'
- _TESTS = [{
- 'url': 'https://streamango.com/f/clapasobsptpkdfe/20170315_150006_mp4',
- 'md5': 'e992787515a182f55e38fc97588d802a',
- 'info_dict': {
- 'id': 'clapasobsptpkdfe',
- 'ext': 'mp4',
- 'title': '20170315_150006.mp4',
- }
- }, {
- # no og:title
- 'url': 'https://streamango.com/embed/foqebrpftarclpob/asdf_asd_2_mp4',
- 'info_dict': {
- 'id': 'foqebrpftarclpob',
- 'ext': 'mp4',
- 'title': 'foqebrpftarclpob',
- },
- 'params': {
- 'skip_download': True,
- },
- 'skip': 'gone',
- }, {
- 'url': 'https://streamango.com/embed/clapasobsptpkdfe/20170315_150006_mp4',
- 'only_matching': True,
- }, {
- 'url': 'https://fruithosts.net/f/mreodparcdcmspsm/w1f1_r4lph_2018_brrs_720p_latino_mp4',
- 'only_matching': True,
- }, {
- 'url': 'https://streamcherry.com/f/clapasobsptpkdfe/',
- 'only_matching': True,
- }]
-
- def _real_extract(self, url):
- def decrypt_src(encoded, val):
- ALPHABET = '=/+9876543210zyxwvutsrqponmlkjihgfedcbaZYXWVUTSRQPONMLKJIHGFEDCBA'
- encoded = re.sub(r'[^A-Za-z0-9+/=]', '', encoded)
- decoded = ''
- sm = [None] * 4
- i = 0
- str_len = len(encoded)
- while i < str_len:
- for j in range(4):
- sm[j % 4] = ALPHABET.index(encoded[i])
- i += 1
- char_code = ((sm[0] << 0x2) | (sm[1] >> 0x4)) ^ val
- decoded += compat_chr(char_code)
- if sm[2] != 0x40:
- char_code = ((sm[1] & 0xf) << 0x4) | (sm[2] >> 0x2)
- decoded += compat_chr(char_code)
- if sm[3] != 0x40:
- char_code = ((sm[2] & 0x3) << 0x6) | sm[3]
- decoded += compat_chr(char_code)
- return decoded
-
- video_id = self._match_id(url)
-
- webpage = self._download_webpage(url, video_id)
-
- title = self._og_search_title(webpage, default=video_id)
-
- formats = []
- for format_ in re.findall(r'({[^}]*\bsrc\s*:\s*[^}]*})', webpage):
- mobj = re.search(r'(src\s*:\s*[^(]+\(([^)]*)\)[\s,]*)', format_)
- if mobj is None:
- continue
-
- format_ = format_.replace(mobj.group(0), '')
-
- video = self._parse_json(
- format_, video_id, transform_source=js_to_json,
- fatal=False) or {}
-
- mobj = re.search(
- r'([\'"])(?P<src>(?:(?!\1).)+)\1\s*,\s*(?P<val>\d+)',
- mobj.group(1))
- if mobj is None:
- continue
-
- src = decrypt_src(mobj.group('src'), int_or_none(mobj.group('val')))
- if not src:
- continue
-
- ext = determine_ext(src, default_ext=None)
- if video.get('type') == 'application/dash+xml' or ext == 'mpd':
- formats.extend(self._extract_mpd_formats(
- src, video_id, mpd_id='dash', fatal=False))
- else:
- formats.append({
- 'url': src,
- 'ext': ext or 'mp4',
- 'width': int_or_none(video.get('width')),
- 'height': int_or_none(video.get('height')),
- 'tbr': int_or_none(video.get('bitrate')),
- })
-
- if not formats:
- error = self._search_regex(
- r'<p[^>]+\bclass=["\']lead[^>]+>(.+?)</p>', webpage,
- 'error', default=None)
- if not error and '>Sorry' in webpage:
- error = 'Video %s is not available' % video_id
- if error:
- raise ExtractorError(error, expected=True)
-
- self._sort_formats(formats)
-
- return {
- 'id': video_id,
- 'url': url,
- 'title': title,
- 'formats': formats,
- }
diff --git a/youtube_dl/extractor/stv.py b/youtube_dl/extractor/stv.py
index ccb074cd4..bae8b71f4 100644
--- a/youtube_dl/extractor/stv.py
+++ b/youtube_dl/extractor/stv.py
@@ -4,15 +4,10 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..compat import (
- compat_parse_qs,
- compat_urllib_parse_urlparse
-)
from ..utils import (
- extract_attributes,
+ compat_str,
float_or_none,
int_or_none,
- str_or_none,
)
@@ -20,20 +15,20 @@ class STVPlayerIE(InfoExtractor):
IE_NAME = 'stv:player'
_VALID_URL = r'https?://player\.stv\.tv/(?P<type>episode|video)/(?P<id>[a-z0-9]{4})'
_TEST = {
- 'url': 'https://player.stv.tv/video/7srz/victoria/interview-with-the-cast-ahead-of-new-victoria/',
- 'md5': '2ad867d4afd641fa14187596e0fbc91b',
+ 'url': 'https://player.stv.tv/video/4gwd/emmerdale/60-seconds-on-set-with-laura-norton/',
+ 'md5': '5adf9439c31d554f8be0707c7abe7e0a',
'info_dict': {
- 'id': '6016487034001',
+ 'id': '5333973339001',
'ext': 'mp4',
- 'upload_date': '20190321',
- 'title': 'Interview with the cast ahead of new Victoria',
- 'description': 'Nell Hudson and Lily Travers tell us what to expect in the new season of Victoria.',
- 'timestamp': 1553179628,
+ 'upload_date': '20170301',
+ 'title': '60 seconds on set with Laura Norton',
+ 'description': "How many questions can Laura - a.k.a Kerry Wyatt - answer in 60 seconds? Let\'s find out!",
+ 'timestamp': 1488388054,
'uploader_id': '1486976045',
},
'skip': 'this resource is unavailable outside of the UK',
}
- _PUBLISHER_ID = '1486976045'
+ BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/1486976045/default_default/index.html?videoId=%s'
_PTYPE_MAP = {
'episode': 'episodes',
'video': 'shortform',
@@ -41,54 +36,32 @@ class STVPlayerIE(InfoExtractor):
def _real_extract(self, url):
ptype, video_id = re.match(self._VALID_URL, url).groups()
- webpage = self._download_webpage(url, video_id)
+ resp = self._download_json(
+ 'https://player.api.stv.tv/v1/%s/%s' % (self._PTYPE_MAP[ptype], video_id),
+ video_id)
- qs = compat_parse_qs(compat_urllib_parse_urlparse(self._search_regex(
- r'itemprop="embedURL"[^>]+href="([^"]+)',
- webpage, 'embed URL', default=None)).query)
- publisher_id = qs.get('publisherID', [None])[0] or self._PUBLISHER_ID
+ result = resp['results']
+ video = result['video']
+ video_id = compat_str(video['id'])
- player_attr = extract_attributes(self._search_regex(
- r'(<[^>]+class="bcplayer"[^>]+>)', webpage, 'player', default=None)) or {}
+ subtitles = {}
+ _subtitles = result.get('_subtitles') or {}
+ for ext, sub_url in _subtitles.items():
+ subtitles.setdefault('en', []).append({
+ 'ext': 'vtt' if ext == 'webvtt' else ext,
+ 'url': sub_url,
+ })
- info = {}
- duration = ref_id = series = video_id = None
- api_ref_id = player_attr.get('data-player-api-refid')
- if api_ref_id:
- resp = self._download_json(
- 'https://player.api.stv.tv/v1/%s/%s' % (self._PTYPE_MAP[ptype], api_ref_id),
- api_ref_id, fatal=False)
- if resp:
- result = resp.get('results') or {}
- video = result.get('video') or {}
- video_id = str_or_none(video.get('id'))
- ref_id = video.get('guid')
- duration = video.get('length')
- programme = result.get('programme') or {}
- series = programme.get('name') or programme.get('shortName')
- subtitles = {}
- _subtitles = result.get('_subtitles') or {}
- for ext, sub_url in _subtitles.items():
- subtitles.setdefault('en', []).append({
- 'ext': 'vtt' if ext == 'webvtt' else ext,
- 'url': sub_url,
- })
- info.update({
- 'description': result.get('summary'),
- 'subtitles': subtitles,
- 'view_count': int_or_none(result.get('views')),
- })
- if not video_id:
- video_id = qs.get('videoId', [None])[0] or self._search_regex(
- r'<link\s+itemprop="url"\s+href="(\d+)"',
- webpage, 'video id', default=None) or 'ref:' + (ref_id or player_attr['data-refid'])
+ programme = result.get('programme') or {}
- info.update({
+ return {
'_type': 'url_transparent',
- 'duration': float_or_none(duration or player_attr.get('data-duration'), 1000),
'id': video_id,
+ 'url': self.BRIGHTCOVE_URL_TEMPLATE % video_id,
+ 'description': result.get('summary'),
+ 'duration': float_or_none(video.get('length'), 1000),
+ 'subtitles': subtitles,
+ 'view_count': int_or_none(result.get('views')),
+ 'series': programme.get('name') or programme.get('shortName'),
'ie_key': 'BrightcoveNew',
- 'series': series or player_attr.get('data-programme-name'),
- 'url': 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s' % (publisher_id, video_id),
- })
- return info
+ }
diff --git a/youtube_dl/extractor/teachable.py b/youtube_dl/extractor/teachable.py
index c1a9deafe..6b7f13b43 100644
--- a/youtube_dl/extractor/teachable.py
+++ b/youtube_dl/extractor/teachable.py
@@ -48,6 +48,16 @@ class TeachableBaseIE(InfoExtractor):
'https://%s/sign_in' % site, None,
'Downloading %s login page' % site)
+ def is_logged(webpage):
+ return any(re.search(p, webpage) for p in (
+ r'class=["\']user-signout',
+ r'<a[^>]+\bhref=["\']/sign_out',
+ r'Log\s+[Oo]ut\s*<'))
+
+ if is_logged(login_page):
+ self._logged_in = True
+ return
+
login_url = compat_str(urlh.geturl())
login_form = self._hidden_inputs(login_page)
@@ -78,10 +88,7 @@ class TeachableBaseIE(InfoExtractor):
'Go to https://%s/ and accept.' % (site, site), expected=True)
# Successful login
- if any(re.search(p, response) for p in (
- r'class=["\']user-signout',
- r'<a[^>]+\bhref=["\']/sign_out',
- r'>\s*Log out\s*<')):
+ if is_logged(response):
self._logged_in = True
return
@@ -158,8 +165,12 @@ class TeachableIE(TeachableBaseIE):
if any(re.search(p, webpage) for p in (
r'class=["\']lecture-contents-locked',
r'>\s*Lecture contents locked',
- r'id=["\']lecture-locked')):
+ r'id=["\']lecture-locked',
+ # https://academy.tailoredtutors.co.uk/courses/108779/lectures/1955313
+ r'class=["\'](?:inner-)?lesson-locked',
+ r'>LESSON LOCKED<')):
self.raise_login_required('Lecture contents locked')
+ raise ExtractorError('Unable to find video URL')
title = self._og_search_title(webpage, default=None)
diff --git a/youtube_dl/extractor/teachingchannel.py b/youtube_dl/extractor/teachingchannel.py
index e89759714..624cdb3ad 100644
--- a/youtube_dl/extractor/teachingchannel.py
+++ b/youtube_dl/extractor/teachingchannel.py
@@ -1,35 +1,33 @@
from __future__ import unicode_literals
-import re
-
from .common import InfoExtractor
-from .ooyala import OoyalaIE
class TeachingChannelIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?teachingchannel\.org/videos/(?P<title>.+)'
+ _VALID_URL = r'https?://(?:www\.)?teachingchannel\.org/videos?/(?P<id>[^/?&#]+)'
_TEST = {
'url': 'https://www.teachingchannel.org/videos/teacher-teaming-evolution',
- 'md5': '3d6361864d7cac20b57c8784da17166f',
'info_dict': {
- 'id': 'F3bnlzbToeI6pLEfRyrlfooIILUjz4nM',
+ 'id': '3swwlzkT',
'ext': 'mp4',
'title': 'A History of Teaming',
'description': 'md5:2a9033db8da81f2edffa4c99888140b3',
- 'duration': 422.255,
+ 'duration': 422,
+ 'upload_date': '20170316',
+ 'timestamp': 1489691297,
},
'params': {
'skip_download': True,
},
- 'add_ie': ['Ooyala'],
+ 'add_ie': ['JWPlatform'],
}
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- title = mobj.group('title')
- webpage = self._download_webpage(url, title)
- ooyala_code = self._search_regex(
- r'data-embed-code=\'(.+?)\'', webpage, 'ooyala code')
+ display_id = self._match_id(url)
+ webpage = self._download_webpage(url, display_id)
+ mid = self._search_regex(
+ r'(?:data-mid=["\']|id=["\']jw-video-player-)([a-zA-Z0-9]{8})',
+ webpage, 'media id')
- return OoyalaIE._build_url_result(ooyala_code)
+ return self.url_result('jwplatform:' + mid, 'JWPlatform', mid)
diff --git a/youtube_dl/extractor/teamcoco.py b/youtube_dl/extractor/teamcoco.py
index 7640cf00a..5793b711f 100644
--- a/youtube_dl/extractor/teamcoco.py
+++ b/youtube_dl/extractor/teamcoco.py
@@ -84,6 +84,19 @@ class TeamcocoIE(TurnerBaseIE):
'only_matching': True,
}
]
+ _RECORD_TEMPL = '''id
+ title
+ teaser
+ publishOn
+ thumb {
+ preview
+ }
+ tags {
+ name
+ }
+ duration
+ turnerMediaId
+ turnerMediaAuthToken'''
def _graphql_call(self, query_template, object_type, object_id):
find_object = 'find' + object_type
@@ -98,36 +111,36 @@ class TeamcocoIE(TurnerBaseIE):
display_id = self._match_id(url)
response = self._graphql_call('''{
- %s(slug: "%s") {
+ %%s(slug: "%%s") {
... on RecordSlug {
record {
+ %s
+ }
+ }
+ ... on PageSlug {
+ child {
id
- title
- teaser
- publishOn
- thumb {
- preview
- }
- file {
- url
- }
- tags {
- name
- }
- duration
- turnerMediaId
- turnerMediaAuthToken
}
}
... on NotFoundSlug {
status
}
}
-}''', 'Slug', display_id)
+}''' % self._RECORD_TEMPL, 'Slug', display_id)
if response.get('status'):
raise ExtractorError('This video is no longer available.', expected=True)
- record = response['record']
+ child = response.get('child')
+ if child:
+ record = self._graphql_call('''{
+ %%s(id: "%%s") {
+ ... on Video {
+ %s
+ }
+ }
+}''' % self._RECORD_TEMPL, 'Record', child['id'])
+ else:
+ record = response['record']
video_id = record['id']
info = {
@@ -150,25 +163,21 @@ class TeamcocoIE(TurnerBaseIE):
'accessTokenType': 'jws',
}))
else:
- d = self._download_json(
+ video_sources = self._download_json(
'https://teamcoco.com/_truman/d/' + video_id,
- video_id, fatal=False) or {}
- video_sources = d.get('meta') or {}
- if not video_sources:
- video_sources = self._graphql_call('''{
- %s(id: "%s") {
- src
- }
-}''', 'RecordVideoSource', video_id) or {}
+ video_id)['meta']['src']
+ if isinstance(video_sources, dict):
+ video_sources = video_sources.values()
formats = []
get_quality = qualities(['low', 'sd', 'hd', 'uhd'])
- for format_id, src in video_sources.get('src', {}).items():
+ for src in video_sources:
if not isinstance(src, dict):
continue
src_url = src.get('src')
if not src_url:
continue
+ format_id = src.get('label')
ext = determine_ext(src_url, mimetype2ext(src.get('type')))
if format_id == 'hls' or ext == 'm3u8':
# compat_urllib_parse.urljoin does not work here
@@ -190,9 +199,6 @@ class TeamcocoIE(TurnerBaseIE):
'format_id': format_id,
'quality': get_quality(format_id),
})
- if not formats:
- formats = self._extract_m3u8_formats(
- record['file']['url'], video_id, 'mp4', fatal=False)
self._sort_formats(formats)
info['formats'] = formats
diff --git a/youtube_dl/extractor/ted.py b/youtube_dl/extractor/ted.py
index 9b60cc462..63e2455b2 100644
--- a/youtube_dl/extractor/ted.py
+++ b/youtube_dl/extractor/ted.py
@@ -133,7 +133,7 @@ class TEDIE(InfoExtractor):
def _extract_info(self, webpage):
info_json = self._search_regex(
- r'(?s)q\(\s*"\w+.init"\s*,\s*({.+})\)\s*</script>',
+ r'(?s)q\(\s*"\w+.init"\s*,\s*({.+?})\)\s*</script>',
webpage, 'info json')
return json.loads(info_json)
@@ -182,20 +182,29 @@ class TEDIE(InfoExtractor):
title = talk_info['title'].strip()
- native_downloads = try_get(
- talk_info,
- (lambda x: x['downloads']['nativeDownloads'],
- lambda x: x['nativeDownloads']),
- dict) or {}
+ downloads = talk_info.get('downloads') or {}
+ native_downloads = downloads.get('nativeDownloads') or talk_info.get('nativeDownloads') or {}
formats = [{
'url': format_url,
'format_id': format_id,
- 'format': format_id,
} for (format_id, format_url) in native_downloads.items() if format_url is not None]
+
+ subtitled_downloads = downloads.get('subtitledDownloads') or {}
+ for lang, subtitled_download in subtitled_downloads.items():
+ for q in self._NATIVE_FORMATS:
+ q_url = subtitled_download.get(q)
+ if not q_url:
+ continue
+ formats.append({
+ 'url': q_url,
+ 'format_id': '%s-%s' % (q, lang),
+ 'language': lang,
+ })
+
if formats:
for f in formats:
- finfo = self._NATIVE_FORMATS.get(f['format_id'])
+ finfo = self._NATIVE_FORMATS.get(f['format_id'].split('-')[0])
if finfo:
f.update(finfo)
@@ -215,34 +224,7 @@ class TEDIE(InfoExtractor):
http_url = None
for format_id, resources in resources_.items():
- if format_id == 'h264':
- for resource in resources:
- h264_url = resource.get('file')
- if not h264_url:
- continue
- bitrate = int_or_none(resource.get('bitrate'))
- formats.append({
- 'url': h264_url,
- 'format_id': '%s-%sk' % (format_id, bitrate),
- 'tbr': bitrate,
- })
- if re.search(r'\d+k', h264_url):
- http_url = h264_url
- elif format_id == 'rtmp':
- streamer = talk_info.get('streamer')
- if not streamer:
- continue
- for resource in resources:
- formats.append({
- 'format_id': '%s-%s' % (format_id, resource.get('name')),
- 'url': streamer,
- 'play_path': resource['file'],
- 'ext': 'flv',
- 'width': int_or_none(resource.get('width')),
- 'height': int_or_none(resource.get('height')),
- 'tbr': int_or_none(resource.get('bitrate')),
- })
- elif format_id == 'hls':
+ if format_id == 'hls':
if not isinstance(resources, dict):
continue
stream_url = url_or_none(resources.get('stream'))
@@ -251,6 +233,36 @@ class TEDIE(InfoExtractor):
formats.extend(self._extract_m3u8_formats(
stream_url, video_name, 'mp4', m3u8_id=format_id,
fatal=False))
+ else:
+ if not isinstance(resources, list):
+ continue
+ if format_id == 'h264':
+ for resource in resources:
+ h264_url = resource.get('file')
+ if not h264_url:
+ continue
+ bitrate = int_or_none(resource.get('bitrate'))
+ formats.append({
+ 'url': h264_url,
+ 'format_id': '%s-%sk' % (format_id, bitrate),
+ 'tbr': bitrate,
+ })
+ if re.search(r'\d+k', h264_url):
+ http_url = h264_url
+ elif format_id == 'rtmp':
+ streamer = talk_info.get('streamer')
+ if not streamer:
+ continue
+ for resource in resources:
+ formats.append({
+ 'format_id': '%s-%s' % (format_id, resource.get('name')),
+ 'url': streamer,
+ 'play_path': resource['file'],
+ 'ext': 'flv',
+ 'width': int_or_none(resource.get('width')),
+ 'height': int_or_none(resource.get('height')),
+ 'tbr': int_or_none(resource.get('bitrate')),
+ })
m3u8_formats = list(filter(
lambda f: f.get('protocol') == 'm3u8' and f.get('vcodec') != 'none',
diff --git a/youtube_dl/extractor/telegraaf.py b/youtube_dl/extractor/telegraaf.py
index 0f576c1ab..2dc020537 100644
--- a/youtube_dl/extractor/telegraaf.py
+++ b/youtube_dl/extractor/telegraaf.py
@@ -4,21 +4,25 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
determine_ext,
- remove_end,
+ int_or_none,
+ parse_iso8601,
+ try_get,
)
class TelegraafIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?telegraaf\.nl/tv/(?:[^/]+/)+(?P<id>\d+)/[^/]+\.html'
+ _VALID_URL = r'https?://(?:www\.)?telegraaf\.nl/video/(?P<id>\d+)'
_TEST = {
- 'url': 'http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html',
+ 'url': 'https://www.telegraaf.nl/video/734366489/historisch-scheepswrak-slaat-na-100-jaar-los',
'info_dict': {
- 'id': '24353229',
+ 'id': 'gaMItuoSeUg2',
'ext': 'mp4',
- 'title': 'Tikibad ontruimd wegens brand',
- 'description': 'md5:05ca046ff47b931f9b04855015e163a4',
- 'thumbnail': r're:^https?://.*\.jpg$',
- 'duration': 33,
+ 'title': 'Historisch scheepswrak slaat na 100 jaar los',
+ 'description': 'md5:6f53b7c4f55596722ac24d6c0ec00cfb',
+ 'thumbnail': r're:^https?://.*\.jpg',
+ 'duration': 55,
+ 'timestamp': 1572805527,
+ 'upload_date': '20191103',
},
'params': {
# m3u8 download
@@ -27,23 +31,30 @@ class TelegraafIE(InfoExtractor):
}
def _real_extract(self, url):
- video_id = self._match_id(url)
+ article_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
+ video_id = self._download_json(
+ 'https://www.telegraaf.nl/graphql', article_id, query={
+ 'query': '''{
+ article(uid: %s) {
+ videos {
+ videoId
+ }
+ }
+}''' % article_id,
+ })['data']['article']['videos'][0]['videoId']
- player_url = self._html_search_regex(
- r'<iframe[^>]+src="([^"]+")', webpage, 'player URL')
- player_page = self._download_webpage(
- player_url, video_id, note='Download player webpage')
- playlist_url = self._search_regex(
- r'playlist\s*:\s*"([^"]+)"', player_page, 'playlist URL')
- playlist_data = self._download_json(playlist_url, video_id)
+ item = self._download_json(
+ 'https://content.tmgvideo.nl/playlist/item=%s/playlist.json' % video_id,
+ video_id)['items'][0]
+ title = item['title']
- item = playlist_data['items'][0]
formats = []
- locations = item['locations']
+ locations = item.get('locations') or {}
for location in locations.get('adaptive', []):
- manifest_url = location['src']
+ manifest_url = location.get('src')
+ if not manifest_url:
+ continue
ext = determine_ext(manifest_url)
if ext == 'm3u8':
formats.extend(self._extract_m3u8_formats(
@@ -54,25 +65,25 @@ class TelegraafIE(InfoExtractor):
else:
self.report_warning('Unknown adaptive format %s' % ext)
for location in locations.get('progressive', []):
+ src = try_get(location, lambda x: x['sources'][0]['src'])
+ if not src:
+ continue
+ label = location.get('label')
formats.append({
- 'url': location['sources'][0]['src'],
- 'width': location.get('width'),
- 'height': location.get('height'),
- 'format_id': 'http-%s' % location['label'],
+ 'url': src,
+ 'width': int_or_none(location.get('width')),
+ 'height': int_or_none(location.get('height')),
+ 'format_id': 'http' + ('-%s' % label if label else ''),
})
self._sort_formats(formats)
- title = remove_end(self._og_search_title(webpage), ' - VIDEO')
- description = self._og_search_description(webpage)
- duration = item.get('duration')
- thumbnail = item.get('poster')
-
return {
'id': video_id,
'title': title,
- 'description': description,
+ 'description': item.get('description'),
'formats': formats,
- 'duration': duration,
- 'thumbnail': thumbnail,
+ 'duration': int_or_none(item.get('duration')),
+ 'thumbnail': item.get('poster'),
+ 'timestamp': parse_iso8601(item.get('datecreated'), ' '),
}
diff --git a/youtube_dl/extractor/telequebec.py b/youtube_dl/extractor/telequebec.py
index 6965c127b..ae9f66787 100644
--- a/youtube_dl/extractor/telequebec.py
+++ b/youtube_dl/extractor/telequebec.py
@@ -7,6 +7,7 @@ from ..utils import (
int_or_none,
smuggle_url,
try_get,
+ unified_timestamp,
)
@@ -22,7 +23,13 @@ class TeleQuebecBaseIE(InfoExtractor):
class TeleQuebecIE(TeleQuebecBaseIE):
- _VALID_URL = r'https?://zonevideo\.telequebec\.tv/media/(?P<id>\d+)'
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:
+ zonevideo\.telequebec\.tv/media|
+ coucou\.telequebec\.tv/videos
+ )/(?P<id>\d+)
+ '''
_TESTS = [{
# available till 01.01.2023
'url': 'http://zonevideo.telequebec.tv/media/37578/un-petit-choc-et-puis-repart/un-chef-a-la-cabane',
@@ -41,6 +48,9 @@ class TeleQuebecIE(TeleQuebecBaseIE):
# no description
'url': 'http://zonevideo.telequebec.tv/media/30261',
'only_matching': True,
+ }, {
+ 'url': 'https://coucou.telequebec.tv/videos/41788/idee-de-genie/l-heure-du-bain',
+ 'only_matching': True,
}]
def _real_extract(self, url):
@@ -61,6 +71,52 @@ class TeleQuebecIE(TeleQuebecBaseIE):
return info
+class TeleQuebecSquatIE(InfoExtractor):
+ _VALID_URL = r'https://squat\.telequebec\.tv/videos/(?P<id>\d+)'
+ _TESTS = [{
+ 'url': 'https://squat.telequebec.tv/videos/9314',
+ 'info_dict': {
+ 'id': 'd59ae78112d542e793d83cc9d3a5b530',
+ 'ext': 'mp4',
+ 'title': 'Poupeflekta',
+ 'description': 'md5:2f0718f8d2f8fece1646ee25fb7bce75',
+ 'duration': 1351,
+ 'timestamp': 1569057600,
+ 'upload_date': '20190921',
+ 'series': 'Miraculous : Les Aventures de Ladybug et Chat Noir',
+ 'season': 'Saison 3',
+ 'season_number': 3,
+ 'episode_number': 57,
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ video = self._download_json(
+ 'https://squat.api.telequebec.tv/v1/videos/%s' % video_id,
+ video_id)
+
+ media_id = video['sourceId']
+
+ return {
+ '_type': 'url_transparent',
+ 'url': 'http://zonevideo.telequebec.tv/media/%s' % media_id,
+ 'ie_key': TeleQuebecIE.ie_key(),
+ 'id': media_id,
+ 'title': video.get('titre'),
+ 'description': video.get('description'),
+ 'timestamp': unified_timestamp(video.get('datePublication')),
+ 'series': video.get('container'),
+ 'season': video.get('saison'),
+ 'season_number': int_or_none(video.get('noSaison')),
+ 'episode_number': int_or_none(video.get('episode')),
+ }
+
+
class TeleQuebecEmissionIE(TeleQuebecBaseIE):
_VALID_URL = r'''(?x)
https?://
diff --git a/youtube_dl/extractor/tenplay.py b/youtube_dl/extractor/tenplay.py
new file mode 100644
index 000000000..dff44a4e2
--- /dev/null
+++ b/youtube_dl/extractor/tenplay.py
@@ -0,0 +1,55 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import (
+ parse_age_limit,
+ parse_iso8601,
+ smuggle_url,
+)
+
+
+class TenPlayIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?10play\.com\.au/[^/]+/episodes/[^/]+/[^/]+/(?P<id>tpv\d{6}[a-z]{5})'
+ _TEST = {
+ 'url': 'https://10play.com.au/masterchef/episodes/season-1/masterchef-s1-ep-1/tpv190718kwzga',
+ 'info_dict': {
+ 'id': '6060533435001',
+ 'ext': 'mp4',
+ 'title': 'MasterChef - S1 Ep. 1',
+ 'description': 'md5:4fe7b78e28af8f2d900cd20d900ef95c',
+ 'age_limit': 10,
+ 'timestamp': 1240828200,
+ 'upload_date': '20090427',
+ 'uploader_id': '2199827728001',
+ },
+ 'params': {
+ 'format': 'bestvideo',
+ 'skip_download': True,
+ }
+ }
+ BRIGHTCOVE_URL_TEMPLATE = 'https://players.brightcove.net/2199827728001/cN6vRtRQt_default/index.html?videoId=%s'
+
+ def _real_extract(self, url):
+ content_id = self._match_id(url)
+ data = self._download_json(
+ 'https://10play.com.au/api/video/' + content_id, content_id)
+ video = data.get('video') or {}
+ metadata = data.get('metaData') or {}
+ brightcove_id = video.get('videoId') or metadata['showContentVideoId']
+ brightcove_url = smuggle_url(
+ self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
+ {'geo_countries': ['AU']})
+
+ return {
+ '_type': 'url_transparent',
+ 'url': brightcove_url,
+ 'id': content_id,
+ 'title': video.get('title') or metadata.get('pageContentName') or metadata.get('showContentName'),
+ 'description': video.get('description'),
+ 'age_limit': parse_age_limit(video.get('showRatingClassification') or metadata.get('showProgramClassification')),
+ 'series': metadata.get('showName'),
+ 'season': metadata.get('showContentSeason'),
+ 'timestamp': parse_iso8601(metadata.get('contentPublishDate') or metadata.get('pageContentPublishDate')),
+ 'ie_key': 'BrightcoveNew',
+ }
diff --git a/youtube_dl/extractor/thesun.py b/youtube_dl/extractor/thesun.py
index 22d003776..15d4a6932 100644
--- a/youtube_dl/extractor/thesun.py
+++ b/youtube_dl/extractor/thesun.py
@@ -3,7 +3,7 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from .ooyala import OoyalaIE
+from ..utils import extract_attributes
class TheSunIE(InfoExtractor):
@@ -16,6 +16,7 @@ class TheSunIE(InfoExtractor):
},
'playlist_count': 2,
}
+ BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/default_default/index.html?videoId=%s'
def _real_extract(self, url):
article_id = self._match_id(url)
@@ -23,10 +24,15 @@ class TheSunIE(InfoExtractor):
webpage = self._download_webpage(url, article_id)
entries = []
- for ooyala_id in re.findall(
- r'<[^>]+\b(?:id\s*=\s*"thesun-ooyala-player-|data-content-id\s*=\s*")([^"]+)',
+ for video in re.findall(
+ r'<video[^>]+data-video-id-pending=[^>]+>',
webpage):
- entries.append(OoyalaIE._build_url_result(ooyala_id))
+ attrs = extract_attributes(video)
+ video_id = attrs['data-video-id-pending']
+ account_id = attrs.get('data-account', '5067014667001')
+ entries.append(self.url_result(
+ self.BRIGHTCOVE_URL_TEMPLATE % (account_id, video_id),
+ 'BrightcoveNew', video_id))
return self.playlist_result(
entries, article_id, self._og_search_title(webpage, fatal=False))
diff --git a/youtube_dl/extractor/tutv.py b/youtube_dl/extractor/tutv.py
deleted file mode 100644
index 362318b24..000000000
--- a/youtube_dl/extractor/tutv.py
+++ /dev/null
@@ -1,36 +0,0 @@
-from __future__ import unicode_literals
-
-from .common import InfoExtractor
-from ..compat import (
- compat_b64decode,
- compat_parse_qs,
-)
-
-
-class TutvIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?tu\.tv/videos/(?P<id>[^/?]+)'
- _TEST = {
- 'url': 'http://tu.tv/videos/robots-futbolistas',
- 'md5': '0cd9e28ad270488911b0d2a72323395d',
- 'info_dict': {
- 'id': '2973058',
- 'ext': 'mp4',
- 'title': 'Robots futbolistas',
- },
- }
-
- def _real_extract(self, url):
- video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
-
- internal_id = self._search_regex(r'codVideo=([0-9]+)', webpage, 'internal video ID')
-
- data_content = self._download_webpage(
- 'http://tu.tv/flvurl.php?codVideo=%s' % internal_id, video_id, 'Downloading video info')
- video_url = compat_b64decode(compat_parse_qs(data_content)['kpt'][0]).decode('utf-8')
-
- return {
- 'id': internal_id,
- 'url': video_url,
- 'title': self._og_search_title(webpage),
- }
diff --git a/youtube_dl/extractor/tv2.py b/youtube_dl/extractor/tv2.py
index d5071e8a5..4a19b9be6 100644
--- a/youtube_dl/extractor/tv2.py
+++ b/youtube_dl/extractor/tv2.py
@@ -4,13 +4,17 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
+from ..compat import compat_HTTPError
from ..utils import (
determine_ext,
+ ExtractorError,
int_or_none,
float_or_none,
js_to_json,
parse_iso8601,
remove_end,
+ strip_or_none,
+ try_get,
)
@@ -20,7 +24,7 @@ class TV2IE(InfoExtractor):
'url': 'http://www.tv2.no/v/916509/',
'info_dict': {
'id': '916509',
- 'ext': 'mp4',
+ 'ext': 'flv',
'title': 'Se Frode Gryttens hyllest av Steven Gerrard',
'description': 'TV 2 Sportens huspoet tar avskjed med Liverpools kaptein Steven Gerrard.',
'timestamp': 1431715610,
@@ -29,22 +33,40 @@ class TV2IE(InfoExtractor):
'view_count': int,
'categories': list,
},
- 'params': {
- # m3u8 download
- 'skip_download': True,
- },
}
+ _API_DOMAIN = 'sumo.tv2.no'
+ _PROTOCOLS = ('HDS', 'HLS', 'DASH')
+ _GEO_COUNTRIES = ['NO']
def _real_extract(self, url):
video_id = self._match_id(url)
+ api_base = 'http://%s/api/web/asset/%s' % (self._API_DOMAIN, video_id)
formats = []
format_urls = []
- for protocol in ('HDS', 'HLS'):
- data = self._download_json(
- 'http://sumo.tv2.no/api/web/asset/%s/play.json?protocol=%s&videoFormat=SMIL+ISMUSP' % (video_id, protocol),
- video_id, 'Downloading play JSON')['playback']
- for item in data['items']['item']:
+ for protocol in self._PROTOCOLS:
+ try:
+ data = self._download_json(
+ api_base + '/play.json?protocol=%s&videoFormat=SMIL+ISMUSP' % protocol,
+ video_id, 'Downloading play JSON')['playback']
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+ error = self._parse_json(e.cause.read().decode(), video_id)['error']
+ error_code = error.get('code')
+ if error_code == 'ASSET_PLAYBACK_INVALID_GEO_LOCATION':
+ self.raise_geo_restricted(countries=self._GEO_COUNTRIES)
+ elif error_code == 'SESSION_NOT_AUTHENTICATED':
+ self.raise_login_required()
+ raise ExtractorError(error['description'])
+ raise
+ items = try_get(data, lambda x: x['items']['item'])
+ if not items:
+ continue
+ if not isinstance(items, list):
+ items = [items]
+ for item in items:
+ if not isinstance(item, dict):
+ continue
video_url = item.get('url')
if not video_url or video_url in format_urls:
continue
@@ -57,9 +79,13 @@ class TV2IE(InfoExtractor):
formats.extend(self._extract_f4m_formats(
video_url, video_id, f4m_id=format_id, fatal=False))
elif ext == 'm3u8':
- formats.extend(self._extract_m3u8_formats(
- video_url, video_id, 'mp4', entry_protocol='m3u8_native',
- m3u8_id=format_id, fatal=False))
+ if not data.get('drmProtected'):
+ formats.extend(self._extract_m3u8_formats(
+ video_url, video_id, 'mp4', entry_protocol='m3u8_native',
+ m3u8_id=format_id, fatal=False))
+ elif ext == 'mpd':
+ formats.extend(self._extract_mpd_formats(
+ video_url, video_id, format_id, fatal=False))
elif ext == 'ism' or video_url.endswith('.ism/Manifest'):
pass
else:
@@ -69,34 +95,30 @@ class TV2IE(InfoExtractor):
'tbr': int_or_none(item.get('bitrate')),
'filesize': int_or_none(item.get('fileSize')),
})
+ if not formats and data.get('drmProtected'):
+ raise ExtractorError('This video is DRM protected.', expected=True)
self._sort_formats(formats)
asset = self._download_json(
- 'http://sumo.tv2.no/api/web/asset/%s.json' % video_id,
- video_id, 'Downloading metadata JSON')['asset']
-
+ api_base + '.json', video_id,
+ 'Downloading metadata JSON')['asset']
title = asset['title']
- description = asset.get('description')
- timestamp = parse_iso8601(asset.get('createTime'))
- duration = float_or_none(asset.get('accurateDuration') or asset.get('duration'))
- view_count = int_or_none(asset.get('views'))
- categories = asset.get('keywords', '').split(',')
thumbnails = [{
'id': thumbnail.get('@type'),
'url': thumbnail.get('url'),
- } for _, thumbnail in asset.get('imageVersions', {}).items()]
+ } for _, thumbnail in (asset.get('imageVersions') or {}).items()]
return {
'id': video_id,
'url': video_url,
'title': title,
- 'description': description,
+ 'description': strip_or_none(asset.get('description')),
'thumbnails': thumbnails,
- 'timestamp': timestamp,
- 'duration': duration,
- 'view_count': view_count,
- 'categories': categories,
+ 'timestamp': parse_iso8601(asset.get('createTime')),
+ 'duration': float_or_none(asset.get('accurateDuration') or asset.get('duration')),
+ 'view_count': int_or_none(asset.get('views')),
+ 'categories': asset.get('keywords', '').split(','),
'formats': formats,
}
@@ -108,7 +130,7 @@ class TV2ArticleIE(InfoExtractor):
'info_dict': {
'id': '6930542',
'title': 'Russen hetses etter pingvintyveri - innrømmer å ha åpnet luken på buret',
- 'description': 'md5:339573779d3eea3542ffe12006190954',
+ 'description': 'De fire siktede nekter fortsatt for å ha stjålet pingvinbabyene, men innrømmer å ha åpnet luken til de små kyllingene.',
},
'playlist_count': 2,
}, {
@@ -126,7 +148,7 @@ class TV2ArticleIE(InfoExtractor):
if not assets:
# New embed pattern
- for v in re.findall(r'TV2ContentboxVideo\(({.+?})\)', webpage):
+ for v in re.findall(r'(?s)TV2ContentboxVideo\(({.+?})\)', webpage):
video = self._parse_json(
v, playlist_id, transform_source=js_to_json, fatal=False)
if not video:
@@ -143,3 +165,28 @@ class TV2ArticleIE(InfoExtractor):
description = remove_end(self._og_search_description(webpage), ' - TV2.no')
return self.playlist_result(entries, playlist_id, title, description)
+
+
+class KatsomoIE(TV2IE):
+ _VALID_URL = r'https?://(?:www\.)?(?:katsomo|mtv)\.fi/(?:#!/)?(?:[^/]+/[0-9a-z-]+-\d+/[0-9a-z-]+-|[^/]+/\d+/[^/]+/)(?P<id>\d+)'
+ _TEST = {
+ 'url': 'https://www.mtv.fi/sarja/mtv-uutiset-live-33001002003/lahden-pelicans-teki-kovan-ratkaisun-ville-nieminen-pihalle-1181321',
+ 'info_dict': {
+ 'id': '1181321',
+ 'ext': 'mp4',
+ 'title': 'MTV Uutiset Live',
+ 'description': 'Päätöksen teki Pelicansin hallitus.',
+ 'timestamp': 1575116484,
+ 'upload_date': '20191130',
+ 'duration': 37.12,
+ 'view_count': int,
+ 'categories': list,
+ },
+ 'params': {
+ # m3u8 download
+ 'skip_download': True,
+ },
+ }
+ _API_DOMAIN = 'api.katsomo.fi'
+ _PROTOCOLS = ('HLS', 'MPD')
+ _GEO_COUNTRIES = ['FI']
diff --git a/youtube_dl/extractor/tv2dk.py b/youtube_dl/extractor/tv2dk.py
new file mode 100644
index 000000000..611fdc0c6
--- /dev/null
+++ b/youtube_dl/extractor/tv2dk.py
@@ -0,0 +1,154 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import json
+import re
+
+from .common import InfoExtractor
+from ..utils import (
+ determine_ext,
+ extract_attributes,
+ js_to_json,
+ url_or_none,
+)
+
+
+class TV2DKIE(InfoExtractor):
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:www\.)?
+ (?:
+ tvsyd|
+ tv2ostjylland|
+ tvmidtvest|
+ tv2fyn|
+ tv2east|
+ tv2lorry|
+ tv2nord
+ )\.dk/
+ (:[^/]+/)*
+ (?P<id>[^/?\#&]+)
+ '''
+ _TESTS = [{
+ 'url': 'https://www.tvsyd.dk/nyheder/28-10-2019/1930/1930-28-okt-2019?autoplay=1#player',
+ 'info_dict': {
+ 'id': '0_52jmwa0p',
+ 'ext': 'mp4',
+ 'title': '19:30 - 28. okt. 2019',
+ 'timestamp': 1572290248,
+ 'upload_date': '20191028',
+ 'uploader_id': 'tvsyd',
+ 'duration': 1347,
+ 'view_count': int,
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ 'add_ie': ['Kaltura'],
+ }, {
+ 'url': 'https://www.tv2ostjylland.dk/artikel/minister-gaar-ind-i-sag-om-diabetes-teknologi',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.tv2ostjylland.dk/nyheder/28-10-2019/22/2200-nyhederne-mandag-d-28-oktober-2019?autoplay=1#player',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.tvmidtvest.dk/nyheder/27-10-2019/1930/1930-27-okt-2019',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.tv2fyn.dk/artikel/fyn-kan-faa-landets-foerste-fabrik-til-groent-jetbraendstof',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.tv2east.dk/artikel/gods-faar-indleveret-tonsvis-af-aebler-100-kilo-aebler-gaar-til-en-aeblebrandy',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.tv2lorry.dk/koebenhavn/rasmus-paludan-evakueret-til-egen-demonstration#player',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://www.tv2nord.dk/artikel/dybt-uacceptabelt',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ webpage = self._download_webpage(url, video_id)
+
+ entries = []
+ for video_el in re.findall(r'(?s)<[^>]+\bdata-entryid\s*=[^>]*>', webpage):
+ video = extract_attributes(video_el)
+ kaltura_id = video.get('data-entryid')
+ if not kaltura_id:
+ continue
+ partner_id = video.get('data-partnerid')
+ if not partner_id:
+ continue
+ entries.append(self.url_result(
+ 'kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura',
+ video_id=kaltura_id))
+ return self.playlist_result(entries)
+
+
+class TV2DKBornholmPlayIE(InfoExtractor):
+ _VALID_URL = r'https?://play\.tv2bornholm\.dk/\?.*?\bid=(?P<id>\d+)'
+ _TEST = {
+ 'url': 'http://play.tv2bornholm.dk/?area=specifikTV&id=781021',
+ 'info_dict': {
+ 'id': '781021',
+ 'ext': 'mp4',
+ 'title': '12Nyheder-27.11.19',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+
+ video = self._download_json(
+ 'http://play.tv2bornholm.dk/controls/AJAX.aspx/specifikVideo', video_id,
+ data=json.dumps({
+ 'playlist_id': video_id,
+ 'serienavn': '',
+ }).encode(), headers={
+ 'X-Requested-With': 'XMLHttpRequest',
+ 'Content-Type': 'application/json; charset=UTF-8',
+ })['d']
+
+ # TODO: generalize flowplayer
+ title = self._search_regex(
+ r'title\s*:\s*(["\'])(?P<value>(?:(?!\1).)+)\1', video, 'title',
+ group='value')
+ sources = self._parse_json(self._search_regex(
+ r'(?s)sources:\s*(\[.+?\]),', video, 'sources'),
+ video_id, js_to_json)
+
+ formats = []
+ srcs = set()
+ for source in sources:
+ src = url_or_none(source.get('src'))
+ if not src:
+ continue
+ if src in srcs:
+ continue
+ srcs.add(src)
+ ext = determine_ext(src)
+ src_type = source.get('type')
+ if src_type == 'application/x-mpegurl' or ext == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ src, video_id, ext='mp4', entry_protocol='m3u8_native',
+ m3u8_id='hls', fatal=False))
+ elif src_type == 'application/dash+xml' or ext == 'mpd':
+ formats.extend(self._extract_mpd_formats(
+ src, video_id, mpd_id='dash', fatal=False))
+ else:
+ formats.append({
+ 'url': src,
+ })
+ self._sort_formats(formats)
+
+ return {
+ 'id': video_id,
+ 'title': title,
+ 'formats': formats,
+ }
diff --git a/youtube_dl/extractor/tv4.py b/youtube_dl/extractor/tv4.py
index 51923e44a..a819d048c 100644
--- a/youtube_dl/extractor/tv4.py
+++ b/youtube_dl/extractor/tv4.py
@@ -72,8 +72,13 @@ class TV4IE(InfoExtractor):
video_id = self._match_id(url)
info = self._download_json(
- 'http://www.tv4play.se/player/assets/%s.json' % video_id,
- video_id, 'Downloading video info JSON')
+ 'https://playback-api.b17g.net/asset/%s' % video_id,
+ video_id, 'Downloading video info JSON', query={
+ 'service': 'tv4',
+ 'device': 'browser',
+ 'protocol': 'hls,dash',
+ 'drm': 'widevine',
+ })['metadata']
title = info['title']
@@ -111,5 +116,9 @@ class TV4IE(InfoExtractor):
'timestamp': parse_iso8601(info.get('broadcast_date_time')),
'duration': int_or_none(info.get('duration')),
'thumbnail': info.get('image'),
- 'is_live': info.get('is_live') is True,
+ 'is_live': info.get('isLive') is True,
+ 'series': info.get('seriesTitle'),
+ 'season_number': int_or_none(info.get('seasonNumber')),
+ 'episode': info.get('episodeTitle'),
+ 'episode_number': int_or_none(info.get('episodeNumber')),
}
diff --git a/youtube_dl/extractor/tvigle.py b/youtube_dl/extractor/tvigle.py
index 3475ef4c3..180259aba 100644
--- a/youtube_dl/extractor/tvigle.py
+++ b/youtube_dl/extractor/tvigle.py
@@ -9,6 +9,8 @@ from ..utils import (
float_or_none,
int_or_none,
parse_age_limit,
+ try_get,
+ url_or_none,
)
@@ -23,11 +25,10 @@ class TvigleIE(InfoExtractor):
_TESTS = [
{
'url': 'http://www.tvigle.ru/video/sokrat/',
- 'md5': '36514aed3657d4f70b4b2cef8eb520cd',
'info_dict': {
'id': '1848932',
'display_id': 'sokrat',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'Сократ',
'description': 'md5:d6b92ffb7217b4b8ebad2e7665253c17',
'duration': 6586,
@@ -37,7 +38,6 @@ class TvigleIE(InfoExtractor):
},
{
'url': 'http://www.tvigle.ru/video/vladimir-vysotskii/vedushchii-teleprogrammy-60-minut-ssha-o-vladimire-vysotskom/',
- 'md5': 'e7efe5350dd5011d0de6550b53c3ba7b',
'info_dict': {
'id': '5142516',
'ext': 'flv',
@@ -62,7 +62,7 @@ class TvigleIE(InfoExtractor):
webpage = self._download_webpage(url, display_id)
video_id = self._html_search_regex(
(r'<div[^>]+class=["\']player["\'][^>]+id=["\'](\d+)',
- r'var\s+cloudId\s*=\s*["\'](\d+)',
+ r'cloudId\s*=\s*["\'](\d+)',
r'class="video-preview current_playing" id="(\d+)"'),
webpage, 'video id')
@@ -90,21 +90,40 @@ class TvigleIE(InfoExtractor):
age_limit = parse_age_limit(item.get('ageRestrictions'))
formats = []
- for vcodec, fmts in item['videos'].items():
+ for vcodec, url_or_fmts in item['videos'].items():
if vcodec == 'hls':
- continue
- for format_id, video_url in fmts.items():
- if format_id == 'm3u8':
+ m3u8_url = url_or_none(url_or_fmts)
+ if not m3u8_url:
continue
- height = self._search_regex(
- r'^(\d+)[pP]$', format_id, 'height', default=None)
- formats.append({
- 'url': video_url,
- 'format_id': '%s-%s' % (vcodec, format_id),
- 'vcodec': vcodec,
- 'height': int_or_none(height),
- 'filesize': int_or_none(item.get('video_files_size', {}).get(vcodec, {}).get(format_id)),
- })
+ formats.extend(self._extract_m3u8_formats(
+ m3u8_url, video_id, ext='mp4', entry_protocol='m3u8_native',
+ m3u8_id='hls', fatal=False))
+ elif vcodec == 'dash':
+ mpd_url = url_or_none(url_or_fmts)
+ if not mpd_url:
+ continue
+ formats.extend(self._extract_mpd_formats(
+ mpd_url, video_id, mpd_id='dash', fatal=False))
+ else:
+ if not isinstance(url_or_fmts, dict):
+ continue
+ for format_id, video_url in url_or_fmts.items():
+ if format_id == 'm3u8':
+ continue
+ video_url = url_or_none(video_url)
+ if not video_url:
+ continue
+ height = self._search_regex(
+ r'^(\d+)[pP]$', format_id, 'height', default=None)
+ filesize = int_or_none(try_get(
+ item, lambda x: x['video_files_size'][vcodec][format_id]))
+ formats.append({
+ 'url': video_url,
+ 'format_id': '%s-%s' % (vcodec, format_id),
+ 'vcodec': vcodec,
+ 'height': int_or_none(height),
+ 'filesize': filesize,
+ })
self._sort_formats(formats)
return {
diff --git a/youtube_dl/extractor/tvland.py b/youtube_dl/extractor/tvland.py
index 957cf1ea2..791144128 100644
--- a/youtube_dl/extractor/tvland.py
+++ b/youtube_dl/extractor/tvland.py
@@ -1,32 +1,35 @@
# coding: utf-8
from __future__ import unicode_literals
-from .mtv import MTVServicesInfoExtractor
+from .spike import ParamountNetworkIE
-class TVLandIE(MTVServicesInfoExtractor):
+class TVLandIE(ParamountNetworkIE):
IE_NAME = 'tvland.com'
_VALID_URL = r'https?://(?:www\.)?tvland\.com/(?:video-clips|(?:full-)?episodes)/(?P<id>[^/?#.]+)'
_FEED_URL = 'http://www.tvland.com/feeds/mrss/'
_TESTS = [{
# Geo-restricted. Without a proxy metadata are still there. With a
# proxy it redirects to http://m.tvland.com/app/
- 'url': 'http://www.tvland.com/episodes/hqhps2/everybody-loves-raymond-the-invasion-ep-048',
+ 'url': 'https://www.tvland.com/episodes/s04pzf/everybody-loves-raymond-the-dog-season-1-ep-19',
'info_dict': {
- 'description': 'md5:80973e81b916a324e05c14a3fb506d29',
- 'title': 'The Invasion',
+ 'description': 'md5:84928e7a8ad6649371fbf5da5e1ad75a',
+ 'title': 'The Dog',
},
- 'playlist': [],
+ 'playlist_mincount': 5,
}, {
- 'url': 'http://www.tvland.com/video-clips/zea2ev/younger-younger--hilary-duff---little-lies',
+ 'url': 'https://www.tvland.com/video-clips/4n87f2/younger-a-first-look-at-younger-season-6',
'md5': 'e2c6389401cf485df26c79c247b08713',
'info_dict': {
- 'id': 'b8697515-4bbe-4e01-83d5-fa705ce5fa88',
+ 'id': '891f7d3c-5b5b-4753-b879-b7ba1a601757',
'ext': 'mp4',
- 'title': 'Younger|December 28, 2015|2|NO-EPISODE#|Younger: Hilary Duff - Little Lies',
- 'description': 'md5:7d192f56ca8d958645c83f0de8ef0269',
- 'upload_date': '20151228',
- 'timestamp': 1451289600,
+ 'title': 'Younger|April 30, 2019|6|NO-EPISODE#|A First Look at Younger Season 6',
+ 'description': 'md5:595ea74578d3a888ae878dfd1c7d4ab2',
+ 'upload_date': '20190430',
+ 'timestamp': 1556658000,
+ },
+ 'params': {
+ 'skip_download': True,
},
}, {
'url': 'http://www.tvland.com/full-episodes/iu0hz6/younger-a-kiss-is-just-a-kiss-season-3-ep-301',
diff --git a/youtube_dl/extractor/tvn24.py b/youtube_dl/extractor/tvn24.py
index 6590e1fd0..de0fb5063 100644
--- a/youtube_dl/extractor/tvn24.py
+++ b/youtube_dl/extractor/tvn24.py
@@ -4,6 +4,7 @@ from __future__ import unicode_literals
from .common import InfoExtractor
from ..utils import (
int_or_none,
+ NO_DEFAULT,
unescapeHTML,
)
@@ -17,9 +18,21 @@ class TVN24IE(InfoExtractor):
'id': '1584444',
'ext': 'mp4',
'title': '"Święta mają być wesołe, dlatego, ludziska, wszyscy pod jemiołę"',
- 'description': 'Wyjątkowe orędzie Artura Andrusa, jednego z gości "Szkła kontaktowego".',
+ 'description': 'Wyjątkowe orędzie Artura Andrusa, jednego z gości Szkła kontaktowego.',
'thumbnail': 're:https?://.*[.]jpeg',
}
+ }, {
+ # different layout
+ 'url': 'https://tvnmeteo.tvn24.pl/magazyny/maja-w-ogrodzie,13/odcinki-online,1,4,1,0/pnacza-ptaki-i-iglaki-odc-691-hgtv-odc-29,1771763.html',
+ 'info_dict': {
+ 'id': '1771763',
+ 'ext': 'mp4',
+ 'title': 'Pnącza, ptaki i iglaki (odc. 691 /HGTV odc. 29)',
+ 'thumbnail': 're:https?://.*',
+ },
+ 'params': {
+ 'skip_download': True,
+ },
}, {
'url': 'http://fakty.tvn24.pl/ogladaj-online,60/53-konferencja-bezpieczenstwa-w-monachium,716431.html',
'only_matching': True,
@@ -35,18 +48,21 @@ class TVN24IE(InfoExtractor):
}]
def _real_extract(self, url):
- video_id = self._match_id(url)
+ display_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
+ webpage = self._download_webpage(url, display_id)
- title = self._og_search_title(webpage)
+ title = self._og_search_title(
+ webpage, default=None) or self._search_regex(
+ r'<h\d+[^>]+class=["\']magazineItemHeader[^>]+>(.+?)</h',
+ webpage, 'title')
- def extract_json(attr, name, fatal=True):
+ def extract_json(attr, name, default=NO_DEFAULT, fatal=True):
return self._parse_json(
self._search_regex(
r'\b%s=(["\'])(?P<json>(?!\1).+?)\1' % attr, webpage,
- name, group='json', fatal=fatal) or '{}',
- video_id, transform_source=unescapeHTML, fatal=fatal)
+ name, group='json', default=default, fatal=fatal) or '{}',
+ display_id, transform_source=unescapeHTML, fatal=fatal)
quality_data = extract_json('data-quality', 'formats')
@@ -59,16 +75,24 @@ class TVN24IE(InfoExtractor):
})
self._sort_formats(formats)
- description = self._og_search_description(webpage)
+ description = self._og_search_description(webpage, default=None)
thumbnail = self._og_search_thumbnail(
webpage, default=None) or self._html_search_regex(
r'\bdata-poster=(["\'])(?P<url>(?!\1).+?)\1', webpage,
'thumbnail', group='url')
+ video_id = None
+
share_params = extract_json(
- 'data-share-params', 'share params', fatal=False)
+ 'data-share-params', 'share params', default=None)
if isinstance(share_params, dict):
- video_id = share_params.get('id') or video_id
+ video_id = share_params.get('id')
+
+ if not video_id:
+ video_id = self._search_regex(
+ r'data-vid-id=["\'](\d+)', webpage, 'video id',
+ default=None) or self._search_regex(
+ r',(\d+)\.html', url, 'video id', default=display_id)
return {
'id': video_id,
diff --git a/youtube_dl/extractor/twitch.py b/youtube_dl/extractor/twitch.py
index dc5ff29c3..a8c2502af 100644
--- a/youtube_dl/extractor/twitch.py
+++ b/youtube_dl/extractor/twitch.py
@@ -17,12 +17,10 @@ from ..compat import (
from ..utils import (
clean_html,
ExtractorError,
- float_or_none,
int_or_none,
orderedSet,
parse_duration,
parse_iso8601,
- qualities,
try_get,
unified_timestamp,
update_url_query,
@@ -248,7 +246,7 @@ class TwitchVodIE(TwitchItemBaseIE):
https?://
(?:
(?:(?:www|go|m)\.)?twitch\.tv/(?:[^/]+/v(?:ideo)?|videos)/|
- player\.twitch\.tv/\?.*?\bvideo=v
+ player\.twitch\.tv/\?.*?\bvideo=v?
)
(?P<id>\d+)
'''
@@ -306,6 +304,9 @@ class TwitchVodIE(TwitchItemBaseIE):
}, {
'url': 'https://www.twitch.tv/northernlion/video/291940395',
'only_matching': True,
+ }, {
+ 'url': 'https://player.twitch.tv/?video=480452374',
+ 'only_matching': True,
}]
def _real_extract(self, url):
@@ -317,13 +318,14 @@ class TwitchVodIE(TwitchItemBaseIE):
'Downloading %s access token' % self._ITEM_TYPE)
formats = self._extract_m3u8_formats(
- '%s/vod/%s?%s' % (
+ '%s/vod/%s.m3u8?%s' % (
self._USHER_BASE, item_id,
compat_urllib_parse_urlencode({
'allow_source': 'true',
'allow_audio_only': 'true',
'allow_spectre': 'true',
'player': 'twitchweb',
+ 'playlist_include_framerate': 'true',
'nauth': access_token['token'],
'nauthsig': access_token['sig'],
})),
@@ -341,9 +343,8 @@ class TwitchVodIE(TwitchItemBaseIE):
info['subtitles'] = {
'rechat': [{
'url': update_url_query(
- 'https://rechat.twitch.tv/rechat-messages', {
- 'video_id': 'v%s' % item_id,
- 'start': info['timestamp'],
+ 'https://api.twitch.tv/v5/videos/%s/comments' % item_id, {
+ 'client_id': self._CLIENT_ID,
}),
'ext': 'json',
}],
@@ -596,6 +597,7 @@ class TwitchStreamIE(TwitchBaseIE):
'allow_spectre': 'true',
'p': random.randint(1000000, 10000000),
'player': 'twitchweb',
+ 'playlist_include_framerate': 'true',
'segment_preference': '4',
'sig': access_token['sig'].encode('utf-8'),
'token': access_token['token'].encode('utf-8'),
@@ -641,7 +643,7 @@ class TwitchStreamIE(TwitchBaseIE):
class TwitchClipsIE(TwitchBaseIE):
IE_NAME = 'twitch:clips'
- _VALID_URL = r'https?://(?:clips\.twitch\.tv/(?:[^/]+/)*|(?:www\.)?twitch\.tv/[^/]+/clip/)(?P<id>[^/?#&]+)'
+ _VALID_URL = r'https?://(?:clips\.twitch\.tv/(?:embed\?.*?\bclip=|(?:[^/]+/)*)|(?:www\.)?twitch\.tv/[^/]+/clip/)(?P<id>[^/?#&]+)'
_TESTS = [{
'url': 'https://clips.twitch.tv/FaintLightGullWholeWheat',
@@ -664,68 +666,89 @@ class TwitchClipsIE(TwitchBaseIE):
}, {
'url': 'https://www.twitch.tv/sergeynixon/clip/StormyThankfulSproutFutureMan',
'only_matching': True,
+ }, {
+ 'url': 'https://clips.twitch.tv/embed?clip=InquisitiveBreakableYogurtJebaited',
+ 'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
- status = self._download_json(
- 'https://clips.twitch.tv/api/v2/clips/%s/status' % video_id,
- video_id)
+ clip = self._download_json(
+ 'https://gql.twitch.tv/gql', video_id, data=json.dumps({
+ 'query': '''{
+ clip(slug: "%s") {
+ broadcaster {
+ displayName
+ }
+ createdAt
+ curator {
+ displayName
+ id
+ }
+ durationSeconds
+ id
+ tiny: thumbnailURL(width: 86, height: 45)
+ small: thumbnailURL(width: 260, height: 147)
+ medium: thumbnailURL(width: 480, height: 272)
+ title
+ videoQualities {
+ frameRate
+ quality
+ sourceURL
+ }
+ viewCount
+ }
+}''' % video_id,
+ }).encode(), headers={
+ 'Client-ID': self._CLIENT_ID,
+ })['data']['clip']
+
+ if not clip:
+ raise ExtractorError(
+ 'This clip is no longer available', expected=True)
formats = []
-
- for option in status['quality_options']:
+ for option in clip.get('videoQualities', []):
if not isinstance(option, dict):
continue
- source = url_or_none(option.get('source'))
+ source = url_or_none(option.get('sourceURL'))
if not source:
continue
formats.append({
'url': source,
'format_id': option.get('quality'),
'height': int_or_none(option.get('quality')),
- 'fps': int_or_none(option.get('frame_rate')),
+ 'fps': int_or_none(option.get('frameRate')),
})
-
self._sort_formats(formats)
- info = {
+ thumbnails = []
+ for thumbnail_id in ('tiny', 'small', 'medium'):
+ thumbnail_url = clip.get(thumbnail_id)
+ if not thumbnail_url:
+ continue
+ thumb = {
+ 'id': thumbnail_id,
+ 'url': thumbnail_url,
+ }
+ mobj = re.search(r'-(\d+)x(\d+)\.', thumbnail_url)
+ if mobj:
+ thumb.update({
+ 'height': int(mobj.group(2)),
+ 'width': int(mobj.group(1)),
+ })
+ thumbnails.append(thumb)
+
+ return {
+ 'id': clip.get('id') or video_id,
+ 'title': clip.get('title') or video_id,
'formats': formats,
+ 'duration': int_or_none(clip.get('durationSeconds')),
+ 'views': int_or_none(clip.get('viewCount')),
+ 'timestamp': unified_timestamp(clip.get('createdAt')),
+ 'thumbnails': thumbnails,
+ 'creator': try_get(clip, lambda x: x['broadcaster']['displayName'], compat_str),
+ 'uploader': try_get(clip, lambda x: x['curator']['displayName'], compat_str),
+ 'uploader_id': try_get(clip, lambda x: x['curator']['id'], compat_str),
}
-
- clip = self._call_api(
- 'kraken/clips/%s' % video_id, video_id, fatal=False, headers={
- 'Accept': 'application/vnd.twitchtv.v5+json',
- })
-
- if clip:
- quality_key = qualities(('tiny', 'small', 'medium'))
- thumbnails = []
- thumbnails_dict = clip.get('thumbnails')
- if isinstance(thumbnails_dict, dict):
- for thumbnail_id, thumbnail_url in thumbnails_dict.items():
- thumbnails.append({
- 'id': thumbnail_id,
- 'url': thumbnail_url,
- 'preference': quality_key(thumbnail_id),
- })
-
- info.update({
- 'id': clip.get('tracking_id') or video_id,
- 'title': clip.get('title') or video_id,
- 'duration': float_or_none(clip.get('duration')),
- 'views': int_or_none(clip.get('views')),
- 'timestamp': unified_timestamp(clip.get('created_at')),
- 'thumbnails': thumbnails,
- 'creator': try_get(clip, lambda x: x['broadcaster']['display_name'], compat_str),
- 'uploader': try_get(clip, lambda x: x['curator']['display_name'], compat_str),
- 'uploader_id': try_get(clip, lambda x: x['curator']['id'], compat_str),
- })
- else:
- info.update({
- 'title': video_id,
- 'id': video_id,
- })
-
- return info
diff --git a/youtube_dl/extractor/twitter.py b/youtube_dl/extractor/twitter.py
index 41d0b6be8..5f8d90fb4 100644
--- a/youtube_dl/extractor/twitter.py
+++ b/youtube_dl/extractor/twitter.py
@@ -4,32 +4,67 @@ from __future__ import unicode_literals
import re
from .common import InfoExtractor
-from ..compat import compat_urlparse
+from ..compat import (
+ compat_HTTPError,
+ compat_parse_qs,
+ compat_urllib_parse_unquote,
+ compat_urllib_parse_urlparse,
+)
from ..utils import (
- determine_ext,
dict_get,
ExtractorError,
float_or_none,
int_or_none,
- remove_end,
try_get,
+ strip_or_none,
+ unified_timestamp,
+ update_url_query,
xpath_text,
)
-from .periscope import PeriscopeIE
+from .periscope import (
+ PeriscopeBaseIE,
+ PeriscopeIE,
+)
class TwitterBaseIE(InfoExtractor):
+ _API_BASE = 'https://api.twitter.com/1.1/'
+ _BASE_REGEX = r'https?://(?:(?:www|m(?:obile)?)\.)?twitter\.com/'
+ _GUEST_TOKEN = None
+
+ def _extract_variant_formats(self, variant, video_id):
+ variant_url = variant.get('url')
+ if not variant_url:
+ return []
+ elif '.m3u8' in variant_url:
+ return self._extract_m3u8_formats(
+ variant_url, video_id, 'mp4', 'm3u8_native',
+ m3u8_id='hls', fatal=False)
+ else:
+ tbr = int_or_none(dict_get(variant, ('bitrate', 'bit_rate')), 1000) or None
+ f = {
+ 'url': variant_url,
+ 'format_id': 'http' + ('-%d' % tbr if tbr else ''),
+ 'tbr': tbr,
+ }
+ self._search_dimensions_in_video_url(f, variant_url)
+ return [f]
+
def _extract_formats_from_vmap_url(self, vmap_url, video_id):
vmap_data = self._download_xml(vmap_url, video_id)
- video_url = xpath_text(vmap_data, './/MediaFile').strip()
- if determine_ext(video_url) == 'm3u8':
- return self._extract_m3u8_formats(
- video_url, video_id, ext='mp4', m3u8_id='hls',
- entry_protocol='m3u8_native')
- return [{
- 'url': video_url,
- }]
+ formats = []
+ urls = []
+ for video_variant in vmap_data.findall('.//{http://twitter.com/schema/videoVMapV2.xsd}videoVariant'):
+ video_variant.attrib['url'] = compat_urllib_parse_unquote(
+ video_variant.attrib['url'])
+ urls.append(video_variant.attrib['url'])
+ formats.extend(self._extract_variant_formats(
+ video_variant.attrib, video_id))
+ video_url = strip_or_none(xpath_text(vmap_data, './/MediaFile'))
+ if video_url not in urls:
+ formats.extend(self._extract_variant_formats({'url': video_url}, video_id))
+ return formats
@staticmethod
def _search_dimensions_in_video_url(a_format, video_url):
@@ -40,10 +75,30 @@ class TwitterBaseIE(InfoExtractor):
'height': int(m.group('height')),
})
+ def _call_api(self, path, video_id, query={}):
+ headers = {
+ 'Authorization': 'Bearer AAAAAAAAAAAAAAAAAAAAAPYXBAAAAAAACLXUNDekMxqa8h%2F40K4moUkGsoc%3DTYfbDKbT3jJPCEVnMYqilB28NHfOPqkca3qaAxGfsyKCs0wRbw',
+ }
+ if not self._GUEST_TOKEN:
+ self._GUEST_TOKEN = self._download_json(
+ self._API_BASE + 'guest/activate.json', video_id,
+ 'Downloading guest token', data=b'',
+ headers=headers)['guest_token']
+ headers['x-guest-token'] = self._GUEST_TOKEN
+ try:
+ return self._download_json(
+ self._API_BASE + path, video_id, headers=headers, query=query)
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 403:
+ raise ExtractorError(self._parse_json(
+ e.cause.read().decode(),
+ video_id)['errors'][0]['message'], expected=True)
+ raise
-class TwitterCardIE(TwitterBaseIE):
+
+class TwitterCardIE(InfoExtractor):
IE_NAME = 'twitter:card'
- _VALID_URL = r'https?://(?:www\.)?twitter\.com/i/(?P<path>cards/tfw/v1|videos(?:/tweet)?)/(?P<id>\d+)'
+ _VALID_URL = TwitterBaseIE._BASE_REGEX + r'i/(?:cards/tfw/v1|videos(?:/tweet)?)/(?P<id>\d+)'
_TESTS = [
{
'url': 'https://twitter.com/i/cards/tfw/v1/560070183650213889',
@@ -51,19 +106,28 @@ class TwitterCardIE(TwitterBaseIE):
'info_dict': {
'id': '560070183650213889',
'ext': 'mp4',
- 'title': 'Twitter web player',
- 'thumbnail': r're:^https?://.*\.jpg$',
+ 'title': "Twitter - You can now shoot, edit and share video on Twitter. Capture life's most moving moments from your perspective.",
+ 'description': 'md5:18d3e24bb4f6e5007487dd546e53bd96',
+ 'uploader': 'Twitter',
+ 'uploader_id': 'Twitter',
+ 'thumbnail': r're:^https?://.*\.jpg',
'duration': 30.033,
+ 'timestamp': 1422366112,
+ 'upload_date': '20150127',
},
},
{
'url': 'https://twitter.com/i/cards/tfw/v1/623160978427936768',
- 'md5': '7ee2a553b63d1bccba97fbed97d9e1c8',
+ 'md5': '7137eca597f72b9abbe61e5ae0161399',
'info_dict': {
'id': '623160978427936768',
'ext': 'mp4',
- 'title': 'Twitter web player',
- 'thumbnail': r're:^https?://.*$',
+ 'title': "NASA - Fly over Pluto's icy Norgay Mountains and Sputnik Plain in this @NASANewHorizons #PlutoFlyby video.",
+ 'description': "Fly over Pluto's icy Norgay Mountains and Sputnik Plain in this @NASANewHorizons #PlutoFlyby video. https://t.co/BJYgOjSeGA",
+ 'uploader': 'NASA',
+ 'uploader_id': 'NASA',
+ 'timestamp': 1437408129,
+ 'upload_date': '20150720',
},
},
{
@@ -75,7 +139,7 @@ class TwitterCardIE(TwitterBaseIE):
'title': 'Ubuntu 11.10 Overview',
'description': 'md5:a831e97fa384863d6e26ce48d1c43376',
'upload_date': '20111013',
- 'uploader': 'OMG! Ubuntu!',
+ 'uploader': 'OMG! UBUNTU!',
'uploader_id': 'omgubuntu',
},
'add_ie': ['Youtube'],
@@ -99,190 +163,30 @@ class TwitterCardIE(TwitterBaseIE):
'info_dict': {
'id': '705235433198714880',
'ext': 'mp4',
- 'title': 'Twitter web player',
- 'thumbnail': r're:^https?://.*',
+ 'title': "Brent Yarina - Khalil Iverson's missed highlight dunk. And made highlight dunk. In one highlight.",
+ 'description': "Khalil Iverson's missed highlight dunk. And made highlight dunk. In one highlight. https://t.co/OrxcJ28Bns",
+ 'uploader': 'Brent Yarina',
+ 'uploader_id': 'BTNBrentYarina',
+ 'timestamp': 1456976204,
+ 'upload_date': '20160303',
},
+ 'skip': 'This content is no longer available.',
}, {
'url': 'https://twitter.com/i/videos/752274308186120192',
'only_matching': True,
},
]
- _API_BASE = 'https://api.twitter.com/1.1'
-
- def _parse_media_info(self, media_info, video_id):
- formats = []
- for media_variant in media_info.get('variants', []):
- media_url = media_variant['url']
- if media_url.endswith('.m3u8'):
- formats.extend(self._extract_m3u8_formats(media_url, video_id, ext='mp4', m3u8_id='hls'))
- elif media_url.endswith('.mpd'):
- formats.extend(self._extract_mpd_formats(media_url, video_id, mpd_id='dash'))
- else:
- tbr = int_or_none(dict_get(media_variant, ('bitRate', 'bitrate')), scale=1000)
- a_format = {
- 'url': media_url,
- 'format_id': 'http-%d' % tbr if tbr else 'http',
- 'tbr': tbr,
- }
- # Reported bitRate may be zero
- if not a_format['tbr']:
- del a_format['tbr']
-
- self._search_dimensions_in_video_url(a_format, media_url)
-
- formats.append(a_format)
- return formats
-
- def _extract_mobile_formats(self, username, video_id):
- webpage = self._download_webpage(
- 'https://mobile.twitter.com/%s/status/%s' % (username, video_id),
- video_id, 'Downloading mobile webpage',
- headers={
- # A recent mobile UA is necessary for `gt` cookie
- 'User-Agent': 'Mozilla/5.0 (Android 6.0.1; Mobile; rv:54.0) Gecko/54.0 Firefox/54.0',
- })
- main_script_url = self._html_search_regex(
- r'<script[^>]+src="([^"]+main\.[^"]+)"', webpage, 'main script URL')
- main_script = self._download_webpage(
- main_script_url, video_id, 'Downloading main script')
- bearer_token = self._search_regex(
- r'BEARER_TOKEN\s*:\s*"([^"]+)"',
- main_script, 'bearer token')
- # https://developer.twitter.com/en/docs/tweets/post-and-engage/api-reference/get-statuses-show-id
- api_data = self._download_json(
- '%s/statuses/show/%s.json' % (self._API_BASE, video_id),
- video_id, 'Downloading API data',
- headers={
- 'Authorization': 'Bearer ' + bearer_token,
- })
- media_info = try_get(api_data, lambda o: o['extended_entities']['media'][0]['video_info']) or {}
- return self._parse_media_info(media_info, video_id)
-
def _real_extract(self, url):
- path, video_id = re.search(self._VALID_URL, url).groups()
-
- config = None
- formats = []
- duration = None
-
- urls = [url]
- if path.startswith('cards/'):
- urls.append('https://twitter.com/i/videos/' + video_id)
-
- for u in urls:
- webpage = self._download_webpage(
- u, video_id, headers={'Referer': 'https://twitter.com/'})
-
- iframe_url = self._html_search_regex(
- r'<iframe[^>]+src="((?:https?:)?//(?:www\.youtube\.com/embed/[^"]+|(?:www\.)?vine\.co/v/\w+/card))"',
- webpage, 'video iframe', default=None)
- if iframe_url:
- return self.url_result(iframe_url)
-
- config = self._parse_json(self._html_search_regex(
- r'data-(?:player-)?config="([^"]+)"', webpage,
- 'data player config', default='{}'),
- video_id)
-
- if config.get('source_type') == 'vine':
- return self.url_result(config['player_url'], 'Vine')
-
- periscope_url = PeriscopeIE._extract_url(webpage)
- if periscope_url:
- return self.url_result(periscope_url, PeriscopeIE.ie_key())
-
- video_url = config.get('video_url') or config.get('playlist', [{}])[0].get('source')
-
- if video_url:
- if determine_ext(video_url) == 'm3u8':
- formats.extend(self._extract_m3u8_formats(video_url, video_id, ext='mp4', m3u8_id='hls'))
- else:
- f = {
- 'url': video_url,
- }
-
- self._search_dimensions_in_video_url(f, video_url)
-
- formats.append(f)
-
- vmap_url = config.get('vmapUrl') or config.get('vmap_url')
- if vmap_url:
- formats.extend(
- self._extract_formats_from_vmap_url(vmap_url, video_id))
-
- media_info = None
-
- for entity in config.get('status', {}).get('entities', []):
- if 'mediaInfo' in entity:
- media_info = entity['mediaInfo']
-
- if media_info:
- formats.extend(self._parse_media_info(media_info, video_id))
- duration = float_or_none(media_info.get('duration', {}).get('nanos'), scale=1e9)
-
- username = config.get('user', {}).get('screen_name')
- if username:
- formats.extend(self._extract_mobile_formats(username, video_id))
-
- if formats:
- title = self._search_regex(r'<title>([^<]+)', webpage, 'title')
- thumbnail = config.get('posterImageUrl') or config.get('image_src')
- duration = float_or_none(config.get('duration'), scale=1000) or duration
- break
-
- if not formats:
- headers = {
- 'Authorization': 'Bearer AAAAAAAAAAAAAAAAAAAAAPYXBAAAAAAACLXUNDekMxqa8h%2F40K4moUkGsoc%3DTYfbDKbT3jJPCEVnMYqilB28NHfOPqkca3qaAxGfsyKCs0wRbw',
- 'Referer': url,
- }
- ct0 = self._get_cookies(url).get('ct0')
- if ct0:
- headers['csrf_token'] = ct0.value
- guest_token = self._download_json(
- '%s/guest/activate.json' % self._API_BASE, video_id,
- 'Downloading guest token', data=b'',
- headers=headers)['guest_token']
- headers['x-guest-token'] = guest_token
- self._set_cookie('api.twitter.com', 'gt', guest_token)
- config = self._download_json(
- '%s/videos/tweet/config/%s.json' % (self._API_BASE, video_id),
- video_id, headers=headers)
- track = config['track']
- vmap_url = track.get('vmapUrl')
- if vmap_url:
- formats = self._extract_formats_from_vmap_url(vmap_url, video_id)
- else:
- playback_url = track['playbackUrl']
- if determine_ext(playback_url) == 'm3u8':
- formats = self._extract_m3u8_formats(
- playback_url, video_id, 'mp4',
- entry_protocol='m3u8_native', m3u8_id='hls')
- else:
- formats = [{
- 'url': playback_url,
- }]
- title = 'Twitter web player'
- thumbnail = config.get('posterImage')
- duration = float_or_none(track.get('durationMs'), scale=1000)
-
- self._remove_duplicate_formats(formats)
- self._sort_formats(formats)
-
- return {
- 'id': video_id,
- 'title': title,
- 'thumbnail': thumbnail,
- 'duration': duration,
- 'formats': formats,
- }
+ status_id = self._match_id(url)
+ return self.url_result(
+ 'https://twitter.com/statuses/' + status_id,
+ TwitterIE.ie_key(), status_id)
-class TwitterIE(InfoExtractor):
+class TwitterIE(TwitterBaseIE):
IE_NAME = 'twitter'
- _VALID_URL = r'https?://(?:www\.|m\.|mobile\.)?twitter\.com/(?:i/web|(?P[^/]+))/status/(?P\d+)'
- _TEMPLATE_URL = 'https://twitter.com/%s/status/%s'
- _TEMPLATE_STATUSES_URL = 'https://twitter.com/statuses/%s'
+ _VALID_URL = TwitterBaseIE._BASE_REGEX + r'(?:(?:i/web|[^/]+)/status|statuses)/(?P\d+)'
_TESTS = [{
'url': 'https://twitter.com/freethenipple/status/643211948184596480',
@@ -291,10 +195,13 @@ class TwitterIE(InfoExtractor):
'ext': 'mp4',
'title': 'FREE THE NIPPLE - FTN supporters on Hollywood Blvd today!',
'thumbnail': r're:^https?://.*\.jpg',
- 'description': 'FREE THE NIPPLE on Twitter: "FTN supporters on Hollywood Blvd today! http://t.co/c7jHH749xJ"',
+ 'description': 'FTN supporters on Hollywood Blvd today! http://t.co/c7jHH749xJ',
'uploader': 'FREE THE NIPPLE',
'uploader_id': 'freethenipple',
'duration': 12.922,
+ 'timestamp': 1442188653,
+ 'upload_date': '20150913',
+ 'age_limit': 18,
},
}, {
'url': 'https://twitter.com/giphz/status/657991469417025536/photo/1',
@@ -316,19 +223,23 @@ class TwitterIE(InfoExtractor):
'id': '665052190608723968',
'ext': 'mp4',
'title': 'Star Wars - A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens.',
- 'description': 'Star Wars on Twitter: "A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens."',
+ 'description': 'A new beginning is coming December 18. Watch the official 60 second #TV spot for #StarWars: #TheForceAwakens. https://t.co/OkSqT2fjWJ',
'uploader_id': 'starwars',
'uploader': 'Star Wars',
+ 'timestamp': 1447395772,
+ 'upload_date': '20151113',
},
}, {
'url': 'https://twitter.com/BTNBrentYarina/status/705235433198714880',
'info_dict': {
'id': '705235433198714880',
'ext': 'mp4',
- 'title': 'Brent Yarina - Khalil Iverson\'s missed highlight dunk. And made highlight dunk. In one highlight.',
- 'description': 'Brent Yarina on Twitter: "Khalil Iverson\'s missed highlight dunk. And made highlight dunk. In one highlight."',
+ 'title': "Brent Yarina - Khalil Iverson's missed highlight dunk. And made highlight dunk. In one highlight.",
+ 'description': "Khalil Iverson's missed highlight dunk. And made highlight dunk. In one highlight. https://t.co/OrxcJ28Bns",
'uploader_id': 'BTNBrentYarina',
'uploader': 'Brent Yarina',
+ 'timestamp': 1456976204,
+ 'upload_date': '20160303',
},
'params': {
# The same video as https://twitter.com/i/videos/tweet/705235433198714880
@@ -340,12 +251,14 @@ class TwitterIE(InfoExtractor):
'info_dict': {
'id': '700207533655363584',
'ext': 'mp4',
- 'title': 'JG - BEAT PROD: @suhmeduh #Damndaniel',
- 'description': 'JG on Twitter: "BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ"',
+ 'title': 'Simon Vertugo - BEAT PROD: @suhmeduh #Damndaniel',
+ 'description': 'BEAT PROD: @suhmeduh https://t.co/HBrQ4AfpvZ #Damndaniel https://t.co/byBooq2ejZ',
'thumbnail': r're:^https?://.*\.jpg',
- 'uploader': 'JG',
- 'uploader_id': 'jaydingeer',
+ 'uploader': 'Simon Vertugo',
+ 'uploader_id': 'simonvertugo',
'duration': 30.0,
+ 'timestamp': 1455777459,
+ 'upload_date': '20160218',
},
}, {
'url': 'https://twitter.com/Filmdrunk/status/713801302971588609',
@@ -353,10 +266,9 @@ class TwitterIE(InfoExtractor):
'info_dict': {
'id': 'MIOxnrUteUd',
'ext': 'mp4',
- 'title': 'Vince Mancini - Vine of the day',
- 'description': 'Vince Mancini on Twitter: "Vine of the day https://t.co/xmTvRdqxWf"',
- 'uploader': 'Vince Mancini',
- 'uploader_id': 'Filmdrunk',
+ 'title': 'Dr.Pepperの飲み方 #japanese #バカ #ドクペ #電動ガン',
+ 'uploader': 'TAKUMA',
+ 'uploader_id': '1004126642786242560',
'timestamp': 1402826626,
'upload_date': '20140615',
},
@@ -367,21 +279,22 @@ class TwitterIE(InfoExtractor):
'id': '719944021058060289',
'ext': 'mp4',
'title': 'Captain America - @King0fNerd Are you sure you made the right choice? Find out in theaters.',
- 'description': 'Captain America on Twitter: "@King0fNerd Are you sure you made the right choice? Find out in theaters. https://t.co/GpgYi9xMJI"',
- 'uploader_id': 'captainamerica',
+ 'description': '@King0fNerd Are you sure you made the right choice? Find out in theaters. https://t.co/GpgYi9xMJI',
+ 'uploader_id': 'CaptainAmerica',
'uploader': 'Captain America',
'duration': 3.17,
+ 'timestamp': 1460483005,
+ 'upload_date': '20160412',
},
}, {
'url': 'https://twitter.com/OPP_HSD/status/779210622571536384',
'info_dict': {
'id': '1zqKVVlkqLaKB',
'ext': 'mp4',
- 'title': 'Sgt Kerry Schmidt - LIVE on #Periscope: Road rage, mischief, assault, rollover and fire in one occurrence',
- 'description': 'Sgt Kerry Schmidt on Twitter: "LIVE on #Periscope: Road rage, mischief, assault, rollover and fire in one occurrence https://t.co/EKrVgIXF3s"',
+ 'title': 'Sgt Kerry Schmidt - Ontario Provincial Police - Road rage, mischief, assault, rollover and fire in one occurrence',
'upload_date': '20160923',
- 'uploader_id': 'OPP_HSD',
- 'uploader': 'Sgt Kerry Schmidt',
+ 'uploader_id': '1PmKqpJdOJQoY',
+ 'uploader': 'Sgt Kerry Schmidt - Ontario Provincial Police',
'timestamp': 1474613214,
},
'add_ie': ['Periscope'],
@@ -392,10 +305,12 @@ class TwitterIE(InfoExtractor):
'id': '852138619213144067',
'ext': 'mp4',
'title': 'عالم الأخبار - كلمة تاريخية بجلسة الجناسي التاريخية.. النائب خالد مؤنس العتيبي للمعارضين : اتقوا الله .. الظلم ظلمات يوم القيامة',
- 'description': 'عالم الأخبار on Twitter: "كلمة تاريخية بجلسة الجناسي التاريخية.. النائب خالد مؤنس العتيبي للمعارضين : اتقوا الله .. الظلم ظلمات يوم القيامة https://t.co/xg6OhpyKfN"',
+ 'description': 'كلمة تاريخية بجلسة الجناسي التاريخية.. النائب خالد مؤنس العتيبي للمعارضين : اتقوا الله .. الظلم ظلمات يوم القيامة https://t.co/xg6OhpyKfN',
'uploader': 'عالم الأخبار',
'uploader_id': 'news_al3alm',
'duration': 277.4,
+ 'timestamp': 1492000653,
+ 'upload_date': '20170412',
},
}, {
'url': 'https://twitter.com/i/web/status/910031516746514432',
@@ -404,10 +319,12 @@ class TwitterIE(InfoExtractor):
'ext': 'mp4',
'title': 'Préfet de Guadeloupe - [Direct] #Maria Le centre se trouve actuellement au sud de Basse-Terre. Restez confinés. Réfugiez-vous dans la pièce la + sûre.',
'thumbnail': r're:^https?://.*\.jpg',
- 'description': 'Préfet de Guadeloupe on Twitter: "[Direct] #Maria Le centre se trouve actuellement au sud de Basse-Terre. Restez confinés. Réfugiez-vous dans la pièce la + sûre. https://t.co/mwx01Rs4lo"',
+ 'description': '[Direct] #Maria Le centre se trouve actuellement au sud de Basse-Terre. Restez confinés. Réfugiez-vous dans la pièce la + sûre. https://t.co/mwx01Rs4lo',
'uploader': 'Préfet de Guadeloupe',
'uploader_id': 'Prefet971',
'duration': 47.48,
+ 'timestamp': 1505803395,
+ 'upload_date': '20170919',
},
'params': {
'skip_download': True, # requires ffmpeg
@@ -420,87 +337,180 @@ class TwitterIE(InfoExtractor):
'ext': 'mp4',
'title': 're:.*?Shep is on a roll today.*?',
'thumbnail': r're:^https?://.*\.jpg',
- 'description': 'md5:63b036c228772523ae1924d5f8e5ed6b',
+ 'description': 'md5:37b9f2ff31720cef23b2bd42ee8a0f09',
'uploader': 'Lis Power',
'uploader_id': 'LisPower1',
'duration': 111.278,
+ 'timestamp': 1527623489,
+ 'upload_date': '20180529',
},
'params': {
'skip_download': True, # requires ffmpeg
},
+ }, {
+ 'url': 'https://twitter.com/foobar/status/1087791357756956680',
+ 'info_dict': {
+ 'id': '1087791357756956680',
+ 'ext': 'mp4',
+ 'title': 'Twitter - A new is coming. Some of you got an opt-in to try it now. Check out the emoji button, quick keyboard shortcuts, upgraded trends, advanced search, and more. Let us know your thoughts!',
+ 'thumbnail': r're:^https?://.*\.jpg',
+ 'description': 'md5:6dfd341a3310fb97d80d2bf7145df976',
+ 'uploader': 'Twitter',
+ 'uploader_id': 'Twitter',
+ 'duration': 61.567,
+ 'timestamp': 1548184644,
+ 'upload_date': '20190122',
+ },
+ }, {
+ # not available in Periscope
+ 'url': 'https://twitter.com/ViviEducation/status/1136534865145286656',
+ 'info_dict': {
+ 'id': '1vOGwqejwoWxB',
+ 'ext': 'mp4',
+ 'title': 'Vivi - Vivi founder @lior_rauchy announcing our new student feedback tool live at @EduTECH_AU #EduTECH2019',
+ 'uploader': 'Vivi',
+ 'uploader_id': '1eVjYOLGkGrQL',
+ },
+ 'add_ie': ['TwitterBroadcast'],
+ }, {
+ # Twitch Clip Embed
+ 'url': 'https://twitter.com/GunB1g/status/1163218564784017422',
+ 'only_matching': True,
}]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- user_id = mobj.group('user_id')
- twid = mobj.group('id')
-
- webpage, urlh = self._download_webpage_handle(
- self._TEMPLATE_STATUSES_URL % twid, twid)
-
- if 'twitter.com/account/suspended' in urlh.geturl():
- raise ExtractorError('Account suspended by Twitter.', expected=True)
-
- if user_id is None:
- mobj = re.match(self._VALID_URL, urlh.geturl())
- user_id = mobj.group('user_id')
-
- username = remove_end(self._og_search_title(webpage), ' on Twitter')
-
- title = description = self._og_search_description(webpage).strip('').replace('\n', ' ').strip('“”')
+ twid = self._match_id(url)
+ status = self._call_api(
+ 'statuses/show/%s.json' % twid, twid, {
+ 'cards_platform': 'Web-12',
+ 'include_cards': 1,
+ 'include_reply_count': 1,
+ 'include_user_entities': 0,
+ 'tweet_mode': 'extended',
+ })
+ title = description = status['full_text'].replace('\n', ' ')
# strip 'https -_t.co_BJYgOjSeGA' junk from filenames
title = re.sub(r'\s+(https?://[^ ]+)', '', title)
+ user = status.get('user') or {}
+ uploader = user.get('name')
+ if uploader:
+ title = '%s - %s' % (uploader, title)
+ uploader_id = user.get('screen_name')
+
+ tags = []
+ for hashtag in (try_get(status, lambda x: x['entities']['hashtags'], list) or []):
+ hashtag_text = hashtag.get('text')
+ if not hashtag_text:
+ continue
+ tags.append(hashtag_text)
info = {
- 'uploader_id': user_id,
- 'uploader': username,
- 'webpage_url': url,
- 'description': '%s on Twitter: "%s"' % (username, description),
- 'title': username + ' - ' + title,
+ 'id': twid,
+ 'title': title,
+ 'description': description,
+ 'uploader': uploader,
+ 'timestamp': unified_timestamp(status.get('created_at')),
+ 'uploader_id': uploader_id,
+ 'uploader_url': 'https://twitter.com/' + uploader_id if uploader_id else None,
+ 'like_count': int_or_none(status.get('favorite_count')),
+ 'repost_count': int_or_none(status.get('retweet_count')),
+ 'comment_count': int_or_none(status.get('reply_count')),
+ 'age_limit': 18 if status.get('possibly_sensitive') else 0,
+ 'tags': tags,
}
- mobj = re.search(r'''(?x)
- ]+class="animated-gif"(?P[^>]+)>\s*
- ]+video-src="(?P