0
0
Fork 0
youtube-dl/youtube_dl/extractor/breakcom.py

41 lines
1.3 KiB
Python
Raw Normal View History

2014-02-11 06:48:46 +11:00
from __future__ import unicode_literals
2013-06-24 06:59:51 +10:00
import re
import json
2013-06-24 06:59:51 +10:00
from .common import InfoExtractor
class BreakIE(InfoExtractor):
2014-02-11 06:48:46 +11:00
_VALID_URL = r'http://(?:www\.)?break\.com/video/([^/]+)'
2013-06-28 04:46:46 +10:00
_TEST = {
2014-02-11 06:48:46 +11:00
'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
'md5': 'a3513fb1547fba4fb6cfac1bffc6c46b',
'info_dict': {
'id': '2468056',
'ext': 'mp4',
'title': 'When Girls Act Like D-Bags',
2013-06-28 04:46:46 +10:00
}
}
2013-06-24 06:59:51 +10:00
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)
2014-02-23 22:20:58 +11:00
info_json = self._search_regex(r'var embedVars = ({.*})\s*?</script>',
webpage, 'info json', flags=re.DOTALL)
info = json.loads(info_json)
video_url = info['videoUri']
youtube_id = info.get('youtubeId')
if youtube_id:
return self.url_result(youtube_id, 'Youtube')
final_url = video_url + '?' + info['AuthToken']
2014-02-11 06:48:46 +11:00
return {
'id': video_id,
'url': final_url,
'title': info['contentName'],
'thumbnail': info['thumbUri'],
2014-02-11 06:48:46 +11:00
}