Released: ([^<]+)<', webpage, 'release date', fatal=False))
-
- data_json = self._search_regex(r'var\s+playlistItem\s*=\s*(\{.*?\});\n', webpage, 'JSON data block')
- data = json.loads(data_json)
-
- formats = [{
- 'url': data['media_url'],
- 'format_id': 'main',
- }, {
- 'url': data['media_url_libsyn'],
- 'format_id': 'libsyn',
- }]
- thumbnail = data.get('thumbnail_url')
- duration = parse_duration(data.get('duration'))
+ r'
Released: ([^<]+)<',
+ webpage, 'release date', default=None) or data.get('release_date'))
return {
'id': video_id,
'title': title,
'description': description,
- 'thumbnail': thumbnail,
+ 'thumbnail': data.get('thumbnail_url'),
'upload_date': release_date,
- 'duration': duration,
+ 'duration': parse_duration(data.get('duration')),
'formats': formats,
}
diff --git a/youtube_dl/extractor/linkedin.py b/youtube_dl/extractor/linkedin.py
index 259fc4c5e..5a86b0064 100644
--- a/youtube_dl/extractor/linkedin.py
+++ b/youtube_dl/extractor/linkedin.py
@@ -34,12 +34,15 @@ class LinkedInLearningBaseIE(InfoExtractor):
'Csrf-Token': self._get_cookies(api_url)['JSESSIONID'].value,
}, query=query)['elements'][0]
- def _get_video_id(self, urn, course_slug, video_slug):
+ def _get_urn_id(self, video_data):
+ urn = video_data.get('urn')
if urn:
mobj = re.search(r'urn:li:lyndaCourse:\d+,(\d+)', urn)
if mobj:
return mobj.group(1)
- return '%s/%s' % (course_slug, video_slug)
+
+ def _get_video_id(self, video_data, course_slug, video_slug):
+ return self._get_urn_id(video_data) or '%s/%s' % (course_slug, video_slug)
def _real_initialize(self):
email, password = self._get_login_info()
@@ -123,7 +126,7 @@ class LinkedInLearningIE(LinkedInLearningBaseIE):
self._sort_formats(formats, ('width', 'height', 'source_preference', 'tbr', 'abr'))
return {
- 'id': self._get_video_id(video_data.get('urn'), course_slug, video_slug),
+ 'id': self._get_video_id(video_data, course_slug, video_slug),
'title': title,
'formats': formats,
'thumbnail': video_data.get('defaultThumbnail'),
@@ -154,18 +157,21 @@ class LinkedInLearningCourseIE(LinkedInLearningBaseIE):
course_data = self._call_api(course_slug, 'chapters,description,title')
entries = []
- for chapter in course_data.get('chapters', []):
+ for chapter_number, chapter in enumerate(course_data.get('chapters', []), 1):
chapter_title = chapter.get('title')
+ chapter_id = self._get_urn_id(chapter)
for video in chapter.get('videos', []):
video_slug = video.get('slug')
if not video_slug:
continue
entries.append({
'_type': 'url_transparent',
- 'id': self._get_video_id(video.get('urn'), course_slug, video_slug),
+ 'id': self._get_video_id(video, course_slug, video_slug),
'title': video.get('title'),
'url': 'https://www.linkedin.com/learning/%s/%s' % (course_slug, video_slug),
'chapter': chapter_title,
+ 'chapter_number': chapter_number,
+ 'chapter_id': chapter_id,
'ie_key': LinkedInLearningIE.ie_key(),
})
diff --git a/youtube_dl/extractor/linuxacademy.py b/youtube_dl/extractor/linuxacademy.py
new file mode 100644
index 000000000..a78c6556e
--- /dev/null
+++ b/youtube_dl/extractor/linuxacademy.py
@@ -0,0 +1,174 @@
+from __future__ import unicode_literals
+
+import json
+import random
+import re
+
+from .common import InfoExtractor
+from ..compat import (
+ compat_b64decode,
+ compat_HTTPError,
+ compat_str,
+)
+from ..utils import (
+ ExtractorError,
+ orderedSet,
+ unescapeHTML,
+ urlencode_postdata,
+ urljoin,
+)
+
+
+class LinuxAcademyIE(InfoExtractor):
+ _VALID_URL = r'''(?x)
+ https?://
+ (?:www\.)?linuxacademy\.com/cp/
+ (?:
+ courses/lesson/course/(?P
\d+)/lesson/(?P\d+)|
+ modules/view/id/(?P\d+)
+ )
+ '''
+ _TESTS = [{
+ 'url': 'https://linuxacademy.com/cp/courses/lesson/course/1498/lesson/2/module/154',
+ 'info_dict': {
+ 'id': '1498-2',
+ 'ext': 'mp4',
+ 'title': "Introduction to the Practitioner's Brief",
+ },
+ 'params': {
+ 'skip_download': True,
+ },
+ 'skip': 'Requires Linux Academy account credentials',
+ }, {
+ 'url': 'https://linuxacademy.com/cp/courses/lesson/course/1498/lesson/2',
+ 'only_matching': True,
+ }, {
+ 'url': 'https://linuxacademy.com/cp/modules/view/id/154',
+ 'info_dict': {
+ 'id': '154',
+ 'title': 'AWS Certified Cloud Practitioner',
+ 'description': 'md5:039db7e60e4aac9cf43630e0a75fa834',
+ },
+ 'playlist_count': 41,
+ 'skip': 'Requires Linux Academy account credentials',
+ }]
+
+ _AUTHORIZE_URL = 'https://login.linuxacademy.com/authorize'
+ _ORIGIN_URL = 'https://linuxacademy.com'
+ _CLIENT_ID = 'KaWxNn1C2Gc7n83W9OFeXltd8Utb5vvx'
+ _NETRC_MACHINE = 'linuxacademy'
+
+ def _real_initialize(self):
+ self._login()
+
+ def _login(self):
+ username, password = self._get_login_info()
+ if username is None:
+ return
+
+ def random_string():
+ return ''.join([
+ random.choice('0123456789ABCDEFGHIJKLMNOPQRSTUVXYZabcdefghijklmnopqrstuvwxyz-._~')
+ for _ in range(32)])
+
+ webpage, urlh = self._download_webpage_handle(
+ self._AUTHORIZE_URL, None, 'Downloading authorize page', query={
+ 'client_id': self._CLIENT_ID,
+ 'response_type': 'token id_token',
+ 'redirect_uri': self._ORIGIN_URL,
+ 'scope': 'openid email user_impersonation profile',
+ 'audience': self._ORIGIN_URL,
+ 'state': random_string(),
+ 'nonce': random_string(),
+ })
+
+ login_data = self._parse_json(
+ self._search_regex(
+ r'atob\(\s*(["\'])(?P(?:(?!\1).)+)\1', webpage,
+ 'login info', group='value'), None,
+ transform_source=lambda x: compat_b64decode(x).decode('utf-8')
+ )['extraParams']
+
+ login_data.update({
+ 'client_id': self._CLIENT_ID,
+ 'redirect_uri': self._ORIGIN_URL,
+ 'tenant': 'lacausers',
+ 'connection': 'Username-Password-Authentication',
+ 'username': username,
+ 'password': password,
+ 'sso': 'true',
+ })
+
+ login_state_url = compat_str(urlh.geturl())
+
+ try:
+ login_page = self._download_webpage(
+ 'https://login.linuxacademy.com/usernamepassword/login', None,
+ 'Downloading login page', data=json.dumps(login_data).encode(),
+ headers={
+ 'Content-Type': 'application/json',
+ 'Origin': 'https://login.linuxacademy.com',
+ 'Referer': login_state_url,
+ })
+ except ExtractorError as e:
+ if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+ error = self._parse_json(e.cause.read(), None)
+ message = error.get('description') or error['code']
+ raise ExtractorError(
+ '%s said: %s' % (self.IE_NAME, message), expected=True)
+ raise
+
+ callback_page, urlh = self._download_webpage_handle(
+ 'https://login.linuxacademy.com/login/callback', None,
+ 'Downloading callback page',
+ data=urlencode_postdata(self._hidden_inputs(login_page)),
+ headers={
+ 'Content-Type': 'application/x-www-form-urlencoded',
+ 'Origin': 'https://login.linuxacademy.com',
+ 'Referer': login_state_url,
+ })
+
+ access_token = self._search_regex(
+ r'access_token=([^=&]+)', compat_str(urlh.geturl()),
+ 'access token')
+
+ self._download_webpage(
+ 'https://linuxacademy.com/cp/login/tokenValidateLogin/token/%s'
+ % access_token, None, 'Downloading token validation page')
+
+ def _real_extract(self, url):
+ mobj = re.match(self._VALID_URL, url)
+ chapter_id, lecture_id, course_id = mobj.group('chapter_id', 'lesson_id', 'course_id')
+ item_id = course_id if course_id else '%s-%s' % (chapter_id, lecture_id)
+
+ webpage = self._download_webpage(url, item_id)
+
+ # course path
+ if course_id:
+ entries = [
+ self.url_result(
+ urljoin(url, lesson_url), ie=LinuxAcademyIE.ie_key())
+ for lesson_url in orderedSet(re.findall(
+ r']+\bhref=["\'](/cp/courses/lesson/course/\d+/lesson/\d+/module/\d+)',
+ webpage))]
+ title = unescapeHTML(self._html_search_regex(
+ (r'class=["\']course-title["\'][^>]*>(?P[^<]+)',
+ r'var\s+title\s*=\s*(["\'])(?P(?:(?!\1).)+)\1'),
+ webpage, 'title', default=None, group='value'))
+ description = unescapeHTML(self._html_search_regex(
+ r'var\s+description\s*=\s*(["\'])(?P(?:(?!\1).)+)\1',
+ webpage, 'description', default=None, group='value'))
+ return self.playlist_result(entries, course_id, title, description)
+
+ # single video path
+ info = self._extract_jwplayer_data(
+ webpage, item_id, require_title=False, m3u8_id='hls',)
+ title = self._search_regex(
+ (r'>Lecture\s*:\s*(?P[^<]+)',
+ r'lessonName\s*=\s*(["\'])(?P(?:(?!\1).)+)\1'), webpage,
+ 'title', group='value')
+ info.update({
+ 'id': item_id,
+ 'title': title,
+ })
+ return info
diff --git a/youtube_dl/extractor/malltv.py b/youtube_dl/extractor/malltv.py
new file mode 100644
index 000000000..e13c2e11a
--- /dev/null
+++ b/youtube_dl/extractor/malltv.py
@@ -0,0 +1,53 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import merge_dicts
+
+
+class MallTVIE(InfoExtractor):
+ _VALID_URL = r'https?://(?:www\.)?mall\.tv/(?:[^/]+/)*(?P[^/?#&]+)'
+ _TESTS = [{
+ 'url': 'https://www.mall.tv/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
+ 'md5': '1c4a37f080e1f3023103a7b43458e518',
+ 'info_dict': {
+ 'id': 't0zzt0',
+ 'display_id': '18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
+ 'ext': 'mp4',
+ 'title': '18 miliard pro neziskovky. Opravdu jsou sportovci nebo Člověk v tísni pijavice?',
+ 'description': 'md5:25fc0ec42a72ba602b602c683fa29deb',
+ 'duration': 216,
+ 'timestamp': 1538870400,
+ 'upload_date': '20181007',
+ 'view_count': int,
+ }
+ }, {
+ 'url': 'https://www.mall.tv/kdo-to-plati/18-miliard-pro-neziskovky-opravdu-jsou-sportovci-nebo-clovek-v-tisni-pijavice',
+ 'only_matching': True,
+ }]
+
+ def _real_extract(self, url):
+ display_id = self._match_id(url)
+
+ webpage = self._download_webpage(
+ url, display_id, headers=self.geo_verification_headers())
+
+ SOURCE_RE = r'(]+\bsrc=(?:(["\'])(?:(?!\2).)+|[^\s]+)/(?P[\da-z]+)/index)\b'
+ video_id = self._search_regex(
+ SOURCE_RE, webpage, 'video id', group='id')
+
+ media = self._parse_html5_media_entries(
+ url, re.sub(SOURCE_RE, r'\1.m3u8', webpage), video_id,
+ m3u8_id='hls', m3u8_entry_protocol='m3u8_native')[0]
+
+ info = self._search_json_ld(webpage, video_id, default={})
+
+ return merge_dicts(media, info, {
+ 'id': video_id,
+ 'display_id': display_id,
+ 'title': self._og_search_title(webpage, default=None) or display_id,
+ 'description': self._og_search_description(webpage, default=None),
+ 'thumbnail': self._og_search_thumbnail(webpage, default=None),
+ })
diff --git a/youtube_dl/extractor/metacafe.py b/youtube_dl/extractor/metacafe.py
index 28f59f63c..9e92416d1 100644
--- a/youtube_dl/extractor/metacafe.py
+++ b/youtube_dl/extractor/metacafe.py
@@ -1,12 +1,13 @@
from __future__ import unicode_literals
+import json
import re
from .common import InfoExtractor
from ..compat import (
compat_parse_qs,
+ compat_urllib_parse,
compat_urllib_parse_unquote,
- compat_urllib_parse_urlencode,
)
from ..utils import (
determine_ext,
@@ -144,7 +145,7 @@ class MetacafeIE(InfoExtractor):
headers = {
# Disable family filter
- 'Cookie': 'user=%s; ' % compat_urllib_parse_urlencode({'ffilter': False})
+ 'Cookie': 'user=%s; ' % compat_urllib_parse.quote(json.dumps({'ffilter': False}))
}
# AnyClip videos require the flashversion cookie so that we get the link
diff --git a/youtube_dl/extractor/noovo.py b/youtube_dl/extractor/noovo.py
index 974de3c3e..b40770d07 100644
--- a/youtube_dl/extractor/noovo.py
+++ b/youtube_dl/extractor/noovo.py
@@ -57,7 +57,8 @@ class NoovoIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
- bc_url = BrightcoveNewIE._extract_url(self, webpage)
+ brightcove_id = self._search_regex(
+ r'data-video-id=["\'](\d+)', webpage, 'brightcove id')
data = self._parse_json(
self._search_regex(
@@ -89,7 +90,10 @@ class NoovoIE(InfoExtractor):
return {
'_type': 'url_transparent',
'ie_key': BrightcoveNewIE.ie_key(),
- 'url': smuggle_url(bc_url, {'geo_countries': ['CA']}),
+ 'url': smuggle_url(
+ self.BRIGHTCOVE_URL_TEMPLATE % brightcove_id,
+ {'geo_countries': ['CA']}),
+ 'id': brightcove_id,
'title': title,
'description': description,
'series': series,
diff --git a/youtube_dl/extractor/npo.py b/youtube_dl/extractor/npo.py
index 5a427c396..857845d35 100644
--- a/youtube_dl/extractor/npo.py
+++ b/youtube_dl/extractor/npo.py
@@ -12,11 +12,16 @@ from ..utils import (
ExtractorError,
fix_xml_ampersands,
int_or_none,
+ merge_dicts,
orderedSet,
parse_duration,
qualities,
+ str_or_none,
strip_jsonp,
unified_strdate,
+ unified_timestamp,
+ url_or_none,
+ urlencode_postdata,
)
@@ -176,9 +181,118 @@ class NPOIE(NPOBaseIE):
def _real_extract(self, url):
video_id = self._match_id(url)
- return self._get_info(video_id)
+ try:
+ return self._get_info(url, video_id)
+ except ExtractorError:
+ return self._get_old_info(video_id)
- def _get_info(self, video_id):
+ def _get_info(self, url, video_id):
+ token = self._download_json(
+ 'https://www.npostart.nl/api/token', video_id,
+ 'Downloading token', headers={
+ 'Referer': url,
+ 'X-Requested-With': 'XMLHttpRequest',
+ })['token']
+
+ player = self._download_json(
+ 'https://www.npostart.nl/player/%s' % video_id, video_id,
+ 'Downloading player JSON', data=urlencode_postdata({
+ 'autoplay': 0,
+ 'share': 1,
+ 'pageUrl': url,
+ 'hasAdConsent': 0,
+ '_token': token,
+ }))
+
+ player_token = player['token']
+
+ format_urls = set()
+ formats = []
+ for profile in ('hls', 'dash-widevine', 'dash-playready', 'smooth'):
+ streams = self._download_json(
+ 'https://start-player.npo.nl/video/%s/streams' % video_id,
+ video_id, 'Downloading %s profile JSON' % profile, fatal=False,
+ query={
+ 'profile': profile,
+ 'quality': 'npo',
+ 'tokenId': player_token,
+ 'streamType': 'broadcast',
+ })
+ if not streams:
+ continue
+ stream = streams.get('stream')
+ if not isinstance(stream, dict):
+ continue
+ stream_url = url_or_none(stream.get('src'))
+ if not stream_url or stream_url in format_urls:
+ continue
+ format_urls.add(stream_url)
+ if stream.get('protection') is not None:
+ continue
+ stream_type = stream.get('type')
+ stream_ext = determine_ext(stream_url)
+ if stream_type == 'application/dash+xml' or stream_ext == 'mpd':
+ formats.extend(self._extract_mpd_formats(
+ stream_url, video_id, mpd_id='dash', fatal=False))
+ elif stream_type == 'application/vnd.apple.mpegurl' or stream_ext == 'm3u8':
+ formats.extend(self._extract_m3u8_formats(
+ stream_url, video_id, ext='mp4',
+ entry_protocol='m3u8_native', m3u8_id='hls', fatal=False))
+ elif '.ism/Manifest' in stream_url:
+ formats.extend(self._extract_ism_formats(
+ stream_url, video_id, ism_id='mss', fatal=False))
+ else:
+ formats.append({
+ 'url': stream_url,
+ })
+
+ self._sort_formats(formats)
+
+ info = {
+ 'id': video_id,
+ 'title': video_id,
+ 'formats': formats,
+ }
+
+ embed_url = url_or_none(player.get('embedUrl'))
+ if embed_url:
+ webpage = self._download_webpage(
+ embed_url, video_id, 'Downloading embed page', fatal=False)
+ if webpage:
+ video = self._parse_json(
+ self._search_regex(
+ r'\bvideo\s*=\s*({.+?})\s*;', webpage, 'video',
+ default='{}'), video_id)
+ if video:
+ title = video.get('episodeTitle')
+ subtitles = {}
+ subtitles_list = video.get('subtitles')
+ if isinstance(subtitles_list, list):
+ for cc in subtitles_list:
+ cc_url = url_or_none(cc.get('src'))
+ if not cc_url:
+ continue
+ lang = str_or_none(cc.get('language')) or 'nl'
+ subtitles.setdefault(lang, []).append({
+ 'url': cc_url,
+ })
+ return merge_dicts({
+ 'title': title,
+ 'description': video.get('description'),
+ 'thumbnail': url_or_none(
+ video.get('still_image_url') or video.get('orig_image_url')),
+ 'duration': int_or_none(video.get('duration')),
+ 'timestamp': unified_timestamp(video.get('broadcastDate')),
+ 'creator': video.get('channel'),
+ 'series': video.get('title'),
+ 'episode': title,
+ 'episode_number': int_or_none(video.get('episodeNumber')),
+ 'subtitles': subtitles,
+ }, info)
+
+ return info
+
+ def _get_old_info(self, video_id):
metadata = self._download_json(
'http://e.omroep.nl/metadata/%s' % video_id,
video_id,
@@ -280,7 +394,7 @@ class NPOIE(NPOBaseIE):
# JSON
else:
video_url = stream_info.get('url')
- if not video_url or video_url in urls:
+ if not video_url or 'vodnotavailable.' in video_url or video_url in urls:
continue
urls.add(video_url)
if determine_ext(video_url) == 'm3u8':
diff --git a/youtube_dl/extractor/openload.py b/youtube_dl/extractor/openload.py
index a2ae25272..c1dcbb7eb 100644
--- a/youtube_dl/extractor/openload.py
+++ b/youtube_dl/extractor/openload.py
@@ -249,7 +249,7 @@ class OpenloadIE(InfoExtractor):
(?:www\.)?
(?:
openload\.(?:co|io|link|pw)|
- oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw)
+ oload\.(?:tv|stream|site|xyz|win|download|cloud|cc|icu|fun|club|info|pw|live)
)
)/
(?:f|embed)/
@@ -346,6 +346,9 @@ class OpenloadIE(InfoExtractor):
}, {
'url': 'https://oload.pw/f/WyKgK8s94N0',
'only_matching': True,
+ }, {
+ 'url': 'https://oload.live/f/-Z58UZ-GR4M',
+ 'only_matching': True,
}]
_USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
diff --git a/youtube_dl/extractor/periscope.py b/youtube_dl/extractor/periscope.py
index 8afe541ec..b337a56c0 100644
--- a/youtube_dl/extractor/periscope.py
+++ b/youtube_dl/extractor/periscope.py
@@ -5,6 +5,7 @@ import re
from .common import InfoExtractor
from ..utils import (
+ int_or_none,
parse_iso8601,
unescapeHTML,
)
@@ -75,6 +76,14 @@ class PeriscopeIE(PeriscopeBaseIE):
'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'))
+
+ def add_width_and_height(f):
+ for key, val in (('width', width), ('height', height)):
+ if not f.get(key):
+ f[key] = val
+
video_urls = set()
formats = []
for format_id in ('replay', 'rtmp', 'hls', 'https_hls', 'lhls', 'lhlsweb'):
@@ -83,16 +92,21 @@ class PeriscopeIE(PeriscopeBaseIE):
continue
video_urls.add(video_url)
if format_id != 'rtmp':
- formats.extend(self._extract_m3u8_formats(
+ 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))
+ m3u8_id=format_id, fatal=False)
+ if len(m3u8_formats) == 1:
+ add_width_and_height(m3u8_formats[0])
+ formats.extend(m3u8_formats)
continue
- formats.append({
+ rtmp_format = {
'url': video_url,
'ext': 'flv' if format_id == 'rtmp' else 'mp4',
- })
+ }
+ add_width_and_height(rtmp_format)
+ formats.append(rtmp_format)
self._sort_formats(formats)
return {
diff --git a/youtube_dl/extractor/pornhd.py b/youtube_dl/extractor/pornhd.py
index b52879c7a..27d65d4b9 100644
--- a/youtube_dl/extractor/pornhd.py
+++ b/youtube_dl/extractor/pornhd.py
@@ -4,9 +4,11 @@ import re
from .common import InfoExtractor
from ..utils import (
+ determine_ext,
ExtractorError,
int_or_none,
js_to_json,
+ urljoin,
)
@@ -14,7 +16,7 @@ class PornHdIE(InfoExtractor):
_VALID_URL = r'https?://(?:www\.)?pornhd\.com/(?:[a-z]{2,4}/)?videos/(?P\d+)(?:/(?P.+))?'
_TESTS = [{
'url': 'http://www.pornhd.com/videos/9864/selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
- 'md5': 'c8b964b1f0a4b5f7f28ae3a5c9f86ad5',
+ 'md5': '87f1540746c1d32ec7a2305c12b96b25',
'info_dict': {
'id': '9864',
'display_id': 'selfie-restroom-masturbation-fun-with-chubby-cutie-hd-porn-video',
@@ -23,6 +25,7 @@ class PornHdIE(InfoExtractor):
'description': 'md5:3748420395e03e31ac96857a8f125b2b',
'thumbnail': r're:^https?://.*\.jpg',
'view_count': int,
+ 'like_count': int,
'age_limit': 18,
}
}, {
@@ -37,6 +40,7 @@ class PornHdIE(InfoExtractor):
'description': 'md5:8ff0523848ac2b8f9b065ba781ccf294',
'thumbnail': r're:^https?://.*\.jpg',
'view_count': int,
+ 'like_count': int,
'age_limit': 18,
},
'skip': 'Not available anymore',
@@ -65,12 +69,14 @@ class PornHdIE(InfoExtractor):
formats = []
for format_id, video_url in sources.items():
+ video_url = urljoin(url, video_url)
if not video_url:
continue
height = int_or_none(self._search_regex(
r'^(\d+)[pP]', format_id, 'height', default=None))
formats.append({
'url': video_url,
+ 'ext': determine_ext(video_url, 'mp4'),
'format_id': format_id,
'height': height,
})
@@ -85,6 +91,11 @@ class PornHdIE(InfoExtractor):
r"poster'?\s*:\s*([\"'])(?P(?:(?!\1).)+)\1", webpage,
'thumbnail', fatal=False, group='url')
+ like_count = int_or_none(self._search_regex(
+ (r'(\d+)\s*]+>(?: |\s)*\blikes',
+ r'class=["\']save-count["\'][^>]*>\s*(\d+)'),
+ webpage, 'like count', fatal=False))
+
return {
'id': video_id,
'display_id': display_id,
@@ -92,6 +103,7 @@ class PornHdIE(InfoExtractor):
'description': description,
'thumbnail': thumbnail,
'view_count': view_count,
+ 'like_count': like_count,
'formats': formats,
'age_limit': 18,
}
diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py
index be93d5d48..641083da7 100644
--- a/youtube_dl/extractor/pornhub.py
+++ b/youtube_dl/extractor/pornhub.py
@@ -16,7 +16,6 @@ from .openload import PhantomJSwrapper
from ..utils import (
ExtractorError,
int_or_none,
- js_to_json,
orderedSet,
remove_quotes,
str_to_int,
@@ -303,14 +302,12 @@ class PornHubIE(PornHubBaseIE):
comment_count = self._extract_count(
r'All Comments\s*\(([\d,.]+)\)', webpage, 'comment')
- page_params = self._parse_json(self._search_regex(
- r'page_params\.zoneDetails\[([\'"])[^\'"]+\1\]\s*=\s*(?P{[^}]+})',
- webpage, 'page parameters', group='data', default='{}'),
- video_id, transform_source=js_to_json, fatal=False)
- tags = categories = None
- if page_params:
- tags = page_params.get('tags', '').split(',')
- categories = page_params.get('categories', '').split(',')
+ def extract_list(meta_key):
+ div = self._search_regex(
+ r'(?s)]+\bclass=["\'].*?\b%sWrapper[^>]*>(.+?)'
+ % meta_key, webpage, meta_key, default=None)
+ if div:
+ return re.findall(r'