X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fbloomberg.py;h=0dca29b712c79a27fb621f094a6f64ab503ba3df;hb=ff2be6e180f1af471dd6d533719d9c595c756557;hp=3666a780b9209da0125d319e3851f40a05bc4e4f;hpb=4b6462fc1e4306e4a1a5b3613b2cef5b09cc9abe;p=youtube-dl diff --git a/youtube_dl/extractor/bloomberg.py b/youtube_dl/extractor/bloomberg.py index 3666a780b..0dca29b71 100644 --- a/youtube_dl/extractor/bloomberg.py +++ b/youtube_dl/extractor/bloomberg.py @@ -1,27 +1,44 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor class BloombergIE(InfoExtractor): - _VALID_URL = r'https?://www\.bloomberg\.com/video/(?P.+?).html' + _VALID_URL = r'https?://www\.bloomberg\.com/news/videos/[^/]+/(?P[^/?#]+)' _TEST = { - u'url': u'http://www.bloomberg.com/video/shah-s-presentation-on-foreign-exchange-strategies-qurhIVlJSB6hzkVi229d8g.html', - u'file': u'12bzhqZTqQHmmlA8I-i0NpzJgcG5NNYX.mp4', - u'info_dict': { - u'title': u'Shah\'s Presentation on Foreign-Exchange Strategies', - u'description': u'md5:abc86e5236f9f0e4866c59ad36736686', - }, - u'params': { - # Requires ffmpeg (m3u8 manifest) - u'skip_download': True, + 'url': 'http://www.bloomberg.com/news/videos/b/aaeae121-5949-481e-a1ce-4562db6f5df2', + # The md5 checksum changes + 'info_dict': { + 'id': 'qurhIVlJSB6hzkVi229d8g', + 'ext': 'flv', + 'title': 'Shah\'s Presentation on Foreign-Exchange Strategies', + 'description': 'md5:a8ba0302912d03d246979735c17d2761', }, } def _real_extract(self, url): - mobj = re.match(self._VALID_URL, url) - name = mobj.group('name') + name = self._match_id(url) webpage = self._download_webpage(url, name) - ooyala_url = self._og_search_video_url(webpage) - return self.url_result(ooyala_url, ie='Ooyala') + video_id = self._search_regex(r'"bmmrId":"(.+?)"', webpage, 'id') + title = re.sub(': Video$', '', self._og_search_title(webpage)) + + embed_info = self._download_json( + 'http://www.bloomberg.com/api/embed?id=%s' % video_id, video_id) + formats = [] + for stream in embed_info['streams']: + if stream["muxing_format"] == "TS": + formats.extend(self._extract_m3u8_formats(stream['url'], video_id)) + else: + formats.extend(self._extract_f4m_formats(stream['url'], video_id)) + self._sort_formats(formats) + + return { + 'id': video_id, + 'title': title, + 'formats': formats, + 'description': self._og_search_description(webpage), + 'thumbnail': self._og_search_thumbnail(webpage), + }