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

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     int_or_none,
   8     unescapeHTML,
   9     find_xpath_attr,
  10 )
  11
  12
  13 class CSpanIE(InfoExtractor):
  14     _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)'
  15     IE_DESC = 'C-SPAN'
  16     _TESTS = [{
  17         'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
  18         'md5': '8e44ce11f0f725527daccc453f553eb0',
  19         'info_dict': {
  20             'id': '315139',
  21             'ext': 'mp4',
  22             'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
  23             'description': 'Attorney General Eric Holder spoke to reporters following the Supreme Court decision in Shelby County v. Holder in which the court ruled that the preclearance provisions of the Voting Rights Act could not be enforced until Congress established new guidelines for review.',
  24         },
  25         'skip': 'Regularly fails on travis, for unknown reasons',
  26     }, {
  27         'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
  28         # For whatever reason, the served video alternates between
  29         # two different ones
  30         'info_dict': {
  31             'id': '340723',
  32             'ext': 'mp4',
  33             'title': 'International Health Care Models',
  34             'description': 'md5:7a985a2d595dba00af3d9c9f0783c967',
  35         }
  36     }, {
  37         'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
  38         'info_dict': {
  39             'id': '342759',
  40             'title': 'General Motors Ignition Switch Recall',
  41         },
  42         'playlist_duration_sum': 14855,
  43     }]
  44
  45     def _real_extract(self, url):
  46         mobj = re.match(self._VALID_URL, url)
  47         page_id = mobj.group('id')
  48         webpage = self._download_webpage(url, page_id)
  49         video_id = self._search_regex(r'progid=\'?([0-9]+)\'?>', webpage, 'video id')
  50
  51         description = self._html_search_regex(
  52             [
  53                 # The full description
  54                 r'<div class=\'expandable\'>(.*?)<a href=\'#\'',
  55                 # If the description is small enough the other div is not
  56                 # present, otherwise this is a stripped version
  57                 r'<p class=\'initial\'>(.*?)</p>'
  58             ],
  59             webpage, 'description', flags=re.DOTALL)
  60
  61         info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
  62         data = self._download_json(info_url, video_id)
  63
  64         doc = self._download_xml(
  65             'http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
  66             video_id)
  67
  68         title = find_xpath_attr(doc, './/string', 'name', 'title').text
  69         thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
  70
  71         files = data['video']['files']
  72
  73         entries = [{
  74             'id': '%s_%d' % (video_id, partnum + 1),
  75             'title': (
  76                 title if len(files) == 1 else
  77                 '%s part %d' % (title, partnum + 1)),
  78             'url': unescapeHTML(f['path']['#text']),
  79             'description': description,
  80             'thumbnail': thumbnail,
  81             'duration': int_or_none(f.get('length', {}).get('#text')),
  82         } for partnum, f in enumerate(files)]
  83
  84         return {
  85             '_type': 'playlist',
  86             'entries': entries,
  87             'title': title,
  88             'id': video_id,
  89         }