X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/03342304420e5daeb428ffdcc7bbd2bbfecfa61a..b74f612ed2a502bba6ac90db119bf0dea2b68629:/youtube_dl/extractor/jwplatform.py diff --git a/youtube_dl/extractor/jwplatform.py b/youtube_dl/extractor/jwplatform.py index 8e90d59..c34b5f5 100644 --- a/youtube_dl/extractor/jwplatform.py +++ b/youtube_dl/extractor/jwplatform.py @@ -4,12 +4,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import int_or_none +from ..utils import unsmuggle_url class JWPlatformIE(InfoExtractor): - _VALID_URL = r'(?:https?://content\.jwplatform\.com/(?:feeds|players|jw6)/|jwplatform:)(?P[a-zA-Z0-9]{8})' - _TEST = { + _VALID_URL = r'(?:https?://(?:content\.jwplatform|cdn\.jwplayer)\.com/(?:(?:feed|player|thumb|preview)s|jw6|v2/media)/|jwplatform:)(?P[a-zA-Z0-9]{8})' + _TESTS = [{ 'url': 'http://content.jwplatform.com/players/nPripu9l-ALJ3XQCI.js', 'md5': 'fa8899fa601eb7c83a64e9d568bdf325', 'info_dict': { @@ -20,51 +20,27 @@ class JWPlatformIE(InfoExtractor): 'upload_date': '20081127', 'timestamp': 1227796140, } - } + }, { + 'url': 'https://cdn.jwplayer.com/players/nPripu9l-ALJ3XQCI.js', + 'only_matching': True, + }] @staticmethod def _extract_url(webpage): - mobj = re.search( - r']+?src=["\'](?P(?:https?:)?//content.jwplatform.com/players/[a-zA-Z0-9]{8})', + urls = JWPlatformIE._extract_urls(webpage) + return urls[0] if urls else None + + @staticmethod + def _extract_urls(webpage): + return re.findall( + r'<(?:script|iframe)[^>]+?src=["\']((?:https?:)?//(?:content\.jwplatform|cdn\.jwplayer)\.com/players/[a-zA-Z0-9]{8})', webpage) - if mobj: - return mobj.group('url') def _real_extract(self, url): + url, smuggled_data = unsmuggle_url(url, {}) + self._initialize_geo_bypass({ + 'countries': smuggled_data.get('geo_countries'), + }) video_id = self._match_id(url) - json_data = self._download_json('http://content.jwplatform.com/feeds/%s.json' % video_id, video_id) - video_data = json_data['playlist'][0] - subtitles = {} - for track in video_data['tracks']: - if track['kind'] == 'captions': - subtitles[track['label']] = [{'url': self._proto_relative_url(track['file'])}] - - formats = [] - for source in video_data['sources']: - source_url = self._proto_relative_url(source['file']) - source_type = source.get('type') or '' - if source_type == 'application/vnd.apple.mpegurl': - formats.extend(self._extract_m3u8_formats( - source_url, video_id, 'mp4', 'm3u8_native', fatal=False)) - elif source_type.startswith('audio'): - formats.append({ - 'url': source_url, - 'vcodec': 'none', - }) - else: - formats.append({ - 'url': source_url, - 'width': int_or_none(source.get('width')), - 'height': int_or_none(source.get('height')), - }) - self._sort_formats(formats) - - return { - 'id': video_id, - 'title': video_data['title'], - 'description': video_data.get('description'), - 'thumbnail': self._proto_relative_url(video_data.get('image')), - 'timestamp': int_or_none(video_data.get('pubdate')), - 'subtitles': subtitles, - 'formats': formats, - } + json_data = self._download_json('https://cdn.jwplayer.com/v2/media/' + video_id, video_id) + return self._parse_jwplayer_data(json_data, video_id)