_ Git - youtube-dl/blob - youtube_dl/extractor/discovery.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4 import json
   5 from .common import InfoExtractor
   6
   7
   8 class DiscoveryIE(InfoExtractor):
   9     _VALID_URL = r'http://dsc\.discovery\.com\/[a-zA-Z0-9\-]*/[a-zA-Z0-9\-]*/videos/(?P<id>[a-zA-Z0-9\-]*)(.htm)?'
  10     _TEST = {
  11         'url': 'http://dsc.discovery.com/tv-shows/mythbusters/videos/mission-impossible-outtakes.htm',
  12         'file': 'mission-impossible-outtakes.mp4',
  13         'md5': 'e12614f9ee303a6ccef415cb0793eba2',
  14         'info_dict': {
  15             'title': 'MythBusters: Mission Impossible Outtakes'
  16         }
  17     }
  18
  19     def _real_extract(self, url):
  20         mobj = re.match(self._VALID_URL, url)
  21         video_id = mobj.group('id')
  22         webpage = self._download_webpage(url, video_id)
  23         title = self._search_regex(
  24             r'(?<=\"name\": ")(?P<title>.*?)(?=\"\,)', webpage, r'Filename')
  25         duration = int(self._search_regex(
  26             r'(?<=\"duration\"\: )(?P<duration>.*?)(?=,)', webpage, r'Duration'))
  27         formats_raw = self._search_regex(
  28             r'(?<=\"mp4\":)(.*?)(}])', webpage, r'formats') + '}]'
  29         formats_json = json.loads(formats_raw)
  30         formats = []
  31         for f in formats_json:
  32             formats.append(
  33                 {'url': f['src'], r'ext': r'mp4', 'tbr': int(f['bitrate'][:-1])})
  34
  35         return {
  36             'id': video_id,
  37             'duration': duration,
  38             'title': title,
  39             'formats': formats
  40         }