1
0
Fork 0
mirror of https://github.com/ytdl-org/youtube-dl.git synced 2024-11-05 09:01:21 +00:00
youtube-dl/youtube_dl/extractor/breakcom.py
2014-12-04 01:33:30 +01:00

63 lines
1.8 KiB
Python

from __future__ import unicode_literals
import re
import json
from .common import InfoExtractor
from ..utils import (
int_or_none,
parse_age_limit,
)
class BreakIE(InfoExtractor):
_VALID_URL = r'http://(?:www\.)?break\.com/video/(?:[^/]+/)*.+-(?P<id>\d+)'
_TESTS = [{
'url': 'http://www.break.com/video/when-girls-act-like-guys-2468056',
'info_dict': {
'id': '2468056',
'ext': 'mp4',
'title': 'When Girls Act Like D-Bags',
}
}, {
'url': 'http://www.break.com/video/ugc/baby-flex-2773063',
'only_matching': True,
}]
def _real_extract(self, url):
video_id = self._match_id(url)
webpage = self._download_webpage(
'http://www.break.com/embed/%s' % video_id, video_id)
info = json.loads(self._search_regex(
r'var embedVars = ({.*})\s*?</script>',
webpage, 'info json', flags=re.DOTALL))
youtube_id = info.get('youtubeId')
if youtube_id:
return self.url_result(youtube_id, 'Youtube')
formats = [{
'url': media['uri'] + '?' + info['AuthToken'],
'tbr': media['bitRate'],
'width': media['width'],
'height': media['height'],
} for media in info['media']]
if not formats:
formats.append({
'url': info['videoUri']
})
self._sort_formats(formats)
duration = int_or_none(info.get('videoLengthInSeconds'))
age_limit = parse_age_limit(info.get('audienceRating'))
return {
'id': video_id,
'title': info['contentName'],
'thumbnail': info['thumbUri'],
'duration': duration,
'age_limit': age_limit,
'formats': formats,
}