X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fjwplatform.py;h=63d0dc998cf1cf281dda3c27f3afaae84f4906c9;hb=70d35d166c1cfb14af20fb6d45ed820b6249f941;hp=a92adf2b348aa5aeb160f306139d6090e6623553;hpb=974c1b2d4292308a26a47136e7fcf9b61f8b285a;p=youtube-dl diff --git a/youtube_dl/extractor/jwplatform.py b/youtube_dl/extractor/jwplatform.py index a92adf2b3..63d0dc998 100644 --- a/youtube_dl/extractor/jwplatform.py +++ b/youtube_dl/extractor/jwplatform.py @@ -4,7 +4,6 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import int_or_none class JWPlatformIE(InfoExtractor): @@ -24,49 +23,16 @@ class JWPlatformIE(InfoExtractor): @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\.com/players/[a-zA-Z0-9]{8})', webpage) - if mobj: - return mobj.group('url') def _real_extract(self, url): 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': - m3u8_formats = self._extract_m3u8_formats( - source_url, video_id, 'mp4', 'm3u8_native', fatal=False) - if m3u8_formats: - formats.extend(m3u8_formats) - 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, - } + return self._parse_jwplayer_data(json_data, video_id)