Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/cspan.py

   1 import re
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     compat_urllib_parse,
   6 )
   7
   8 class CSpanIE(InfoExtractor):
   9     _VALID_URL = r'http://www.c-spanvideo.org/program/(.*)'
  10     _TEST = {
  11         u'url': u'http://www.c-spanvideo.org/program/HolderonV',
  12         u'file': u'315139.flv',
  13         u'md5': u'74a623266956f69e4df0068ab6c80fe4',
  14         u'info_dict': {
  15             u"title": u"Attorney General Eric Holder on Voting Rights Act Decision"
  16         },
  17         u'skip': u'Requires rtmpdump'
  18     }
  19
  20     def _real_extract(self, url):
  21         mobj = re.match(self._VALID_URL, url)
  22         prog_name = mobj.group(1)
  23         webpage = self._download_webpage(url, prog_name)
  24         video_id = self._search_regex(r'programid=(.*?)&', webpage, 'video id')
  25         data = compat_urllib_parse.urlencode({'programid': video_id,
  26                                               'dynamic':'1'})
  27         info_url = 'http://www.c-spanvideo.org/common/services/flashXml.php?' + data
  28         video_info = self._download_webpage(info_url, video_id, u'Downloading video info')
  29
  30         self.report_extraction(video_id)
  31
  32         title = self._html_search_regex(r'<string name="title">(.*?)</string>',
  33                                         video_info, 'title')
  34         description = self._html_search_regex(r'<meta (?:property="og:|name=")description" content="(.*?)"',
  35                                               webpage, 'description',
  36                                               flags=re.MULTILINE|re.DOTALL)
  37         thumbnail = self._html_search_regex(r'<meta property="og:image" content="(.*?)"',
  38                                             webpage, 'thumbnail')
  39
  40         url = self._search_regex(r'<string name="URL">(.*?)</string>',
  41                                  video_info, 'video url')
  42         url = url.replace('$(protocol)', 'rtmp').replace('$(port)', '443')
  43         path = self._search_regex(r'<string name="path">(.*?)</string>',
  44                             video_info, 'rtmp play path')
  45
  46         return {'id': video_id,
  47                 'title': title,
  48                 'ext': 'flv',
  49                 'url': url,
  50                 'play_path': path,
  51                 'description': description,
  52                 'thumbnail': thumbnail,
  53                 }