mirror of
https://github.com/l1ving/youtube-dl
synced 2024-12-24 10:22:52 +08:00
45 lines
1.5 KiB
Python
45 lines
1.5 KiB
Python
from __future__ import unicode_literals
|
|
|
|
import re
|
|
|
|
from .common import InfoExtractor
|
|
|
|
|
|
class BloombergIE(InfoExtractor):
|
|
_VALID_URL = r'https?://www\.bloomberg\.com/news/videos/[^/]+/(?P<id>[^/?#]+)'
|
|
|
|
_TEST = {
|
|
'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):
|
|
name = self._match_id(url)
|
|
webpage = self._download_webpage(url, name)
|
|
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),
|
|
}
|