2
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2024-12-15 07:42:42 +00:00
yt-dlp/youtube_dl/extractor/breakcom.py

39 lines
1.4 KiB
Python
Raw Normal View History

2013-06-23 20:59:51 +00:00
import re
import json
2013-06-23 20:59:51 +00:00
from .common import InfoExtractor
from ..utils import determine_ext
2013-06-23 20:59:51 +00:00
class BreakIE(InfoExtractor):
_VALID_URL = r'(?:http://)?(?:www\.)?break\.com/video/([^/]+)'
2013-06-27 18:46:46 +00:00
_TEST = {
u'url': u'http://www.break.com/video/when-girls-act-like-guys-2468056',
u'file': u'2468056.mp4',
u'md5': u'a3513fb1547fba4fb6cfac1bffc6c46b',
u'info_dict': {
u"title": u"When Girls Act Like D-Bags"
}
}
2013-06-23 20:59:51 +00:00
def _real_extract(self, url):
mobj = re.match(self._VALID_URL, url)
video_id = mobj.group(1).split("-")[-1]
embed_url = 'http://www.break.com/embed/%s' % video_id
webpage = self._download_webpage(embed_url, video_id)
info_json = self._search_regex(r'var embedVars = ({.*?});', webpage,
u'info json', flags=re.DOTALL)
info = json.loads(info_json)
video_url = info['videoUri']
m_youtube = re.search(r'(https?://www\.youtube\.com/watch\?v=.*)', video_url)
if m_youtube is not None:
return self.url_result(m_youtube.group(1), 'Youtube')
final_url = video_url + '?' + info['AuthToken']
2013-06-23 20:59:51 +00:00
return [{
'id': video_id,
'url': final_url,
'ext': determine_ext(final_url),
'title': info['contentName'],
'thumbnail': info['thumbUri'],
2013-06-23 20:59:51 +00:00
}]