1 from __future__ import unicode_literals
5 from .common import InfoExtractor
14 from .senateisvp import SenateISVPIE
17 class CSpanIE(InfoExtractor):
18 _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)'
21 'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
22 'md5': '94b29a4f131ff03d23471dd6f60b6a1d',
26 'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
27 'description': 'Attorney General Eric Holder speaks 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.',
29 'skip': 'Regularly fails on travis, for unknown reasons',
31 'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
32 'md5': '8e5fbfabe6ad0f89f3012a7943c1287b',
36 'title': 'CSPAN - International Health Care Models',
37 'description': 'md5:7a985a2d595dba00af3d9c9f0783c967',
40 'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
41 'md5': '2ae5051559169baadba13fc35345ae74',
45 'title': 'General Motors Ignition Switch Recall',
47 'description': 'md5:118081aedd24bf1d3b68b3803344e7f3'
50 # Video from senate.gov
51 'url': 'http://www.c-span.org/video/?104517-1/immigration-reforms-needed-protect-skilled-american-workers',
53 'id': 'judiciary031715',
55 'title': 'Immigration Reforms Needed to Protect Skilled American Workers',
59 def _real_extract(self, url):
60 video_id = self._match_id(url)
62 webpage = self._download_webpage(url, video_id)
63 # We first look for clipid, because clipprog always appears before
64 patterns = [r'id=\'clip(%s)\'\s*value=\'([0-9]+)\'' % t for t in ('id', 'prog')]
65 results = list(filter(None, (re.search(p, webpage) for p in patterns)))
68 video_type, video_id = matches.groups()
69 video_type = 'clip' if video_type == 'id' else 'program'
71 senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
73 title = self._og_search_title(webpage)
74 surl = smuggle_url(senate_isvp_url, {'force_title': title})
75 return self.url_result(surl, 'SenateISVP', video_id, title)
76 if video_type is None or video_id is None:
77 raise ExtractorError('unable to find video id and type')
79 def get_text_attr(d, attr):
80 return d.get(attr, {}).get('#text')
82 data = self._download_json(
83 'http://www.c-span.org/assets/player/ajax-player.php?os=android&html5=%s&id=%s' % (video_type, video_id),
85 if data['@status'] != 'Success':
86 raise ExtractorError('%s said: %s' % (self.IE_NAME, get_text_attr(data, 'error')), expected=True)
88 doc = self._download_xml(
89 'http://www.c-span.org/common/services/flashXml.php?%sid=%s' % (video_type, video_id),
92 description = self._html_search_meta('description', webpage)
94 title = find_xpath_attr(doc, './/string', 'name', 'title').text
95 thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
98 capfile = get_text_attr(data, 'capfile')
101 for partnum, f in enumerate(files):
103 for quality in f['qualities']:
105 'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')),
106 'url': unescapeHTML(get_text_attr(quality, 'file')),
107 'height': int_or_none(get_text_attr(quality, 'height')),
108 'tbr': int_or_none(get_text_attr(quality, 'bitrate')),
110 self._sort_formats(formats)
112 'id': '%s_%d' % (video_id, partnum + 1),
114 title if len(files) == 1 else
115 '%s part %d' % (title, partnum + 1)),
117 'description': description,
118 'thumbnail': thumbnail,
119 'duration': int_or_none(get_text_attr(f, 'length')),
123 'ext': determine_ext(capfile, 'dfxp')
125 } if capfile else None,
128 if len(entries) == 1:
129 entry = dict(entries[0])
130 entry['id'] = 'c' + video_id if video_type == 'clip' else video_id
137 'id': 'c' + video_id if video_type == 'clip' else video_id,