X-Git-Url: http://git.bitcoin.ninja/index.cgi?p=youtube-dl;a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fjwplatform.py;h=c34b5f5e6bd9e7d38e762f5d82f3669ac2c438a2;hp=8a5e562dbc24fac4d18498e631e8f5e10d8fe038;hb=b77888228d605a73f85d367845cf50609b855b62;hpb=b6c0d4f4315a282257adc6ab980b4cf4bfb3d418 diff --git a/youtube_dl/extractor/jwplatform.py b/youtube_dl/extractor/jwplatform.py index 8a5e562db..c34b5f5e6 100644 --- a/youtube_dl/extractor/jwplatform.py +++ b/youtube_dl/extractor/jwplatform.py @@ -4,60 +4,12 @@ from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - float_or_none, - int_or_none, -) +from ..utils import unsmuggle_url -class JWPlatformBaseIE(InfoExtractor): - def _parse_jwplayer_data(self, jwplayer_data, video_id, require_title=True): - video_data = jwplayer_data['playlist'][0] - - formats = [] - for source in video_data['sources']: - source_url = self._proto_relative_url(source['file']) - source_type = source.get('type') or '' - if source_type in ('application/vnd.apple.mpegurl', 'hls'): - 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) - - subtitles = {} - tracks = video_data.get('tracks') - if tracks and isinstance(tracks, list): - for track in tracks: - if track.get('file') and track.get('kind') == 'captions': - subtitles.setdefault(track.get('label') or 'en', []).append({ - 'url': self._proto_relative_url(track['file']) - }) - - return { - 'id': video_id, - 'title': video_data['title'] if require_title else video_data.get('title'), - 'description': video_data.get('description'), - 'thumbnail': self._proto_relative_url(video_data.get('image')), - 'timestamp': int_or_none(video_data.get('pubdate')), - 'duration': float_or_none(jwplayer_data.get('duration')), - 'subtitles': subtitles, - 'formats': formats, - } - - -class JWPlatformIE(JWPlatformBaseIE): - _VALID_URL = r'(?:https?://content\.jwplatform\.com/(?:feeds|players|jw6)/|jwplatform:)(?P[a-zA-Z0-9]{8})' - _TEST = { +class JWPlatformIE(InfoExtractor): + _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': { @@ -68,17 +20,27 @@ class JWPlatformIE(JWPlatformBaseIE): '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) + json_data = self._download_json('https://cdn.jwplayer.com/v2/media/' + video_id, video_id) return self._parse_jwplayer_data(json_data, video_id)