1 from __future__ import unicode_literals
5 from .common import InfoExtractor
12 from .senateisvp import SenateISVPIE
15 class CSpanIE(InfoExtractor):
16 _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)'
19 'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
20 'md5': '8e44ce11f0f725527daccc453f553eb0',
24 'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
25 '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 'skip': 'Regularly fails on travis, for unknown reasons',
29 'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
30 # For whatever reason, the served video alternates between
35 'title': 'International Health Care Models',
36 'description': 'md5:7a985a2d595dba00af3d9c9f0783c967',
39 'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
40 'md5': '446562a736c6bf97118e389433ed88d4',
44 'title': 'General Motors Ignition Switch Recall',
46 'description': 'md5:70c7c3b8fa63fa60d42772440596034c'
49 # Video from senate.gov
50 'url': 'http://www.c-span.org/video/?104517-1/immigration-reforms-needed-protect-skilled-american-workers',
52 'id': 'judiciary031715',
54 'title': 'Immigration Reforms Needed to Protect Skilled American Workers',
58 def _real_extract(self, url):
59 mobj = re.match(self._VALID_URL, url)
60 page_id = mobj.group('id')
61 webpage = self._download_webpage(url, page_id)
62 video_id = self._search_regex(r'progid=\'?([0-9]+)\'?>', webpage, 'video id')
64 description = self._html_search_regex(
66 # The full description
67 r'<div class=\'expandable\'>(.*?)<a href=\'#\'',
68 # If the description is small enough the other div is not
69 # present, otherwise this is a stripped version
70 r'<p class=\'initial\'>(.*?)</p>'
72 webpage, 'description', flags=re.DOTALL, default=None)
74 info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
75 data = self._download_json(info_url, video_id)
77 doc = self._download_xml(
78 'http://www.c-span.org/common/services/flashXml.php?programid=' + video_id,
81 title = find_xpath_attr(doc, './/string', 'name', 'title').text
82 thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
84 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
86 surl = smuggle_url(senate_isvp_url, {'force_title': title})
87 return self.url_result(surl, 'SenateISVP', video_id, title)
89 files = data['video']['files']
92 'id': '%s_%d' % (video_id, partnum + 1),
94 title if len(files) == 1 else
95 '%s part %d' % (title, partnum + 1)),
96 'url': unescapeHTML(f['path']['#text']),
97 'description': description,
98 'thumbnail': thumbnail,
99 'duration': int_or_none(f.get('length', {}).get('#text')),
100 } for partnum, f in enumerate(files)]
102 if len(entries) == 1:
103 entry = dict(entries[0])
104 entry['id'] = video_id