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     smuggle_url,
  11     determine_ext,
  12 )
  13 from .senateisvp import SenateISVPIE
  14
  15
  16 class CSpanIE(InfoExtractor):
  17     _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)'
  18     IE_DESC = 'C-SPAN'
  19     _TESTS = [{
  20         'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
  21         'md5': '8e44ce11f0f725527daccc453f553eb0',
  22         'info_dict': {
  23             'id': '315139',
  24             'ext': 'mp4',
  25             'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
  26             '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.',
  27         },
  28         'skip': 'Regularly fails on travis, for unknown reasons',
  29     }, {
  30         'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
  31         # For whatever reason, the served video alternates between
  32         # two different ones
  33         'info_dict': {
  34             'id': '340723',
  35             'ext': 'mp4',
  36             'title': 'International Health Care Models',
  37             'description': 'md5:7a985a2d595dba00af3d9c9f0783c967',
  38         }
  39     }, {
  40         'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
  41         'md5': '446562a736c6bf97118e389433ed88d4',
  42         'info_dict': {
  43             'id': '342759',
  44             'ext': 'mp4',
  45             'title': 'General Motors Ignition Switch Recall',
  46             'duration': 14848,
  47             'description': 'md5:70c7c3b8fa63fa60d42772440596034c'
  48         },
  49     }, {
  50         # Video from senate.gov
  51         'url': 'http://www.c-span.org/video/?104517-1/immigration-reforms-needed-protect-skilled-american-workers',
  52         'info_dict': {
  53             'id': 'judiciary031715',
  54             'ext': 'flv',
  55             'title': 'Immigration Reforms Needed to Protect Skilled American Workers',
  56         }
  57     }]
  58
  59     def _real_extract(self, url):
  60         mobj = re.match(self._VALID_URL, url)
  61         page_id = mobj.group('id')
  62         webpage = self._download_webpage(url, page_id)
  63         video_id = self._search_regex(r'progid=\'?([0-9]+)\'?>', webpage, 'video id')
  64
  65         description = self._html_search_regex(
  66             [
  67                 # The full description
  68                 r'<div class=\'expandable\'>(.*?)<a href=\'#\'',
  69                 # If the description is small enough the other div is not
  70                 # present, otherwise this is a stripped version
  71                 r'<p class=\'initial\'>(.*?)</p>'
  72             ],
  73             webpage, 'description', flags=re.DOTALL, default=None)
  74
  75         info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
  76         data = self._download_json(info_url, video_id)
  77
  78         doc = self._download_xml(
  79             'http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
  80             video_id)
  81
  82         title = find_xpath_attr(doc, './/string', 'name', 'title').text
  83         thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
  84
  85         senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
  86         if senate_isvp_url:
  87             surl = smuggle_url(senate_isvp_url, {'force_title': title})
  88             return self.url_result(surl, 'SenateISVP', video_id, title)
  89
  90         files = data['video']['files']
  91         try:
  92             capfile = data['video']['capfile']['#text']
  93         except KeyError:
  94             capfile = None
  95
  96         entries = [{
  97             'id': '%s_%d' % (video_id, partnum + 1),
  98             'title': (
  99                 title if len(files) == 1 else
 100                 '%s part %d' % (title, partnum + 1)),
 101             'url': unescapeHTML(f['path']['#text']),
 102             'description': description,
 103             'thumbnail': thumbnail,
 104             'duration': int_or_none(f.get('length', {}).get('#text')),
 105             'subtitles': {
 106                 'en': [{
 107                     'url': capfile,
 108                     'ext': determine_ext(capfile, 'dfxp')
 109                 }],
 110             } if capfile else None,
 111         } for partnum, f in enumerate(files)]
 112
 113         if len(entries) == 1:
 114             entry = dict(entries[0])
 115             entry['id'] = video_id
 116             return entry
 117         else:
 118             return {
 119                 '_type': 'playlist',
 120                 'entries': entries,
 121                 'title': title,
 122                 'id': video_id,
 123             }