]+\bclass=["\']bottom[^>]+>\s*[^<]*
\s*([^<]+)',
- webpage, 'description', fatal=False)
- thumbnail = self._og_search_thumbnail(webpage)
- uploader = self._search_regex(
- r'class="user"[^>]*>]+>([^<]+)',
+ webpage, 'description', default=None)
+ thumbnail = self._og_search_thumbnail(webpage, default=None)
+ uploader = self._html_search_regex(
+ (r'(?s)]+class=["\']profile[^>]+>(.+?)',
+ r'class="user"[^>]*>]+>([^<]+)'),
webpage, 'uploader', default=None)
duration = parse_duration(self._search_regex(
r']+\bclass=["\']right_side[^>]+>\s*([^<]+)',
- 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 +146,8 @@ 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/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']+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/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']+class=["\']magazineItemHeader[^>]+>(.+?)(?!\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(?!\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/twitter.py b/youtube_dl/extractor/twitter.py
index 41d0b6be8..cebb6238c 100644
--- a/youtube_dl/extractor/twitter.py
+++ b/youtube_dl/extractor/twitter.py
@@ -428,11 +428,22 @@ class TwitterIE(InfoExtractor):
'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': 'md5:66d493500c013e3e2d434195746a7f78',
+ 'uploader': 'Twitter',
+ 'uploader_id': 'Twitter',
+ 'duration': 61.567,
+ },
}]
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(
@@ -441,8 +452,13 @@ class TwitterIE(InfoExtractor):
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 = None
+
+ redirect_mobj = re.match(self._VALID_URL, urlh.geturl())
+ if redirect_mobj:
+ user_id = redirect_mobj.group('user_id')
+
+ if not user_id:
user_id = mobj.group('user_id')
username = remove_end(self._og_search_title(webpage), ' on Twitter')
diff --git a/youtube_dl/extractor/vimeo.py b/youtube_dl/extractor/vimeo.py
index b5b44a79a..ddf375c6c 100644
--- a/youtube_dl/extractor/vimeo.py
+++ b/youtube_dl/extractor/vimeo.py
@@ -2,12 +2,14 @@
from __future__ import unicode_literals
import base64
+import functools
import json
import re
import itertools
from .common import InfoExtractor
from ..compat import (
+ compat_kwargs,
compat_HTTPError,
compat_str,
compat_urlparse,
@@ -19,6 +21,7 @@ from ..utils import (
int_or_none,
merge_dicts,
NO_DEFAULT,
+ OnDemandPagedList,
parse_filesize,
qualities,
RegexNotFoundError,
@@ -98,6 +101,13 @@ class VimeoBaseInfoExtractor(InfoExtractor):
webpage, 'vuid', group='vuid')
return xsrft, vuid
+ def _extract_vimeo_config(self, webpage, video_id, *args, **kwargs):
+ vimeo_config = self._search_regex(
+ r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));',
+ webpage, 'vimeo config', *args, **compat_kwargs(kwargs))
+ if vimeo_config:
+ return self._parse_json(vimeo_config, video_id)
+
def _set_vimeo_cookie(self, name, value):
self._set_cookie('vimeo.com', name, value)
@@ -253,7 +263,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
\.
)?
vimeo(?Ppro)?\.com/
- (?!(?:channels|album)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
+ (?!(?:channels|album|showcase)/[^/?#]+/?(?:$|[?#])|[^/]+/review/|ondemand/)
(?:.*?/)?
(?:
(?:
@@ -580,11 +590,9 @@ class VimeoIE(VimeoBaseInfoExtractor):
# and latter we extract those that are Vimeo specific.
self.report_extraction(video_id)
- vimeo_config = self._search_regex(
- r'vimeo\.config\s*=\s*(?:({.+?})|_extend\([^,]+,\s+({.+?})\));', webpage,
- 'vimeo config', default=None)
+ vimeo_config = self._extract_vimeo_config(webpage, video_id, default=None)
if vimeo_config:
- seed_status = self._parse_json(vimeo_config, video_id).get('seed_status', {})
+ seed_status = vimeo_config.get('seed_status', {})
if seed_status.get('state') == 'failed':
raise ExtractorError(
'%s said: %s' % (self.IE_NAME, seed_status['title']),
@@ -905,7 +913,7 @@ class VimeoUserIE(VimeoChannelIE):
class VimeoAlbumIE(VimeoChannelIE):
IE_NAME = 'vimeo:album'
- _VALID_URL = r'https://vimeo\.com/album/(?P\d+)(?:$|[?#]|/(?!video))'
+ _VALID_URL = r'https://vimeo\.com/(?:album|showcase)/(?P\d+)(?:$|[?#]|/(?!video))'
_TITLE_RE = r'