from .common import InfoExtractor
from ..utils import (
- int_or_none,
- unescapeHTML,
+ determine_ext,
+ ExtractorError,
+ extract_attributes,
find_xpath_attr,
+ get_element_by_class,
+ int_or_none,
smuggle_url,
- determine_ext,
+ unescapeHTML,
)
from .senateisvp import SenateISVPIE
+from .ustream import UstreamIE
class CSpanIE(InfoExtractor):
- _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)'
+ _VALID_URL = r'https?://(?:www\.)?c-span\.org/video/\?(?P<id>[0-9a-f]+)'
IE_DESC = 'C-SPAN'
_TESTS = [{
'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
- 'md5': '067803f994e049b455a58b16e5aab442',
+ 'md5': '94b29a4f131ff03d23471dd6f60b6a1d',
'info_dict': {
'id': '315139',
- 'ext': 'mp4',
'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
- '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.',
},
+ 'playlist_mincount': 2,
'skip': 'Regularly fails on travis, for unknown reasons',
}, {
'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
- 'md5': '4eafd1e91a75d2b1e6a3cbd0995816a2',
+ # md5 is unstable
'info_dict': {
'id': 'c4486943',
'ext': 'mp4',
}
}, {
'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
- 'md5': '446562a736c6bf97118e389433ed88d4',
'info_dict': {
'id': '342759',
- 'ext': 'mp4',
'title': 'General Motors Ignition Switch Recall',
- 'duration': 14848,
- 'description': 'md5:118081aedd24bf1d3b68b3803344e7f3'
},
+ 'playlist_mincount': 6,
}, {
# Video from senate.gov
'url': 'http://www.c-span.org/video/?104517-1/immigration-reforms-needed-protect-skilled-american-workers',
'info_dict': {
'id': 'judiciary031715',
- 'ext': 'flv',
+ 'ext': 'mp4',
'title': 'Immigration Reforms Needed to Protect Skilled American Workers',
+ },
+ 'params': {
+ 'skip_download': True, # m3u8 downloads
}
+ }, {
+ # Ustream embedded video
+ 'url': 'https://www.c-span.org/video/?114917-1/armed-services',
+ 'info_dict': {
+ 'id': '58428542',
+ 'ext': 'flv',
+ 'title': 'USHR07 Armed Services Committee',
+ 'description': 'hsas00-2118-20150204-1000et-07\n\n\nUSHR07 Armed Services Committee',
+ 'timestamp': 1423060374,
+ 'upload_date': '20150204',
+ 'uploader': 'HouseCommittee',
+ 'uploader_id': '12987475',
+ },
+ }, {
+ # Audio Only
+ 'url': 'https://www.c-span.org/video/?437336-1/judiciary-antitrust-competition-policy-consumer-rights',
+ 'only_matching': True,
}]
+ BRIGHTCOVE_URL_TEMPLATE = 'http://players.brightcove.net/%s/%s_%s/index.html?videoId=%s'
def _real_extract(self, url):
video_id = self._match_id(url)
+ video_type = None
webpage = self._download_webpage(url, video_id)
- matches = re.search(r'data-(prog|clip)id=\'([0-9]+)\'', webpage)
- if matches:
+
+ ustream_url = UstreamIE._extract_url(webpage)
+ if ustream_url:
+ return self.url_result(ustream_url, UstreamIE.ie_key())
+
+ if '&vod' not in url:
+ bc = self._search_regex(
+ r"(<[^>]+id='brightcove-player-embed'[^>]+>)",
+ webpage, 'brightcove embed', default=None)
+ if bc:
+ bc_attr = extract_attributes(bc)
+ bc_url = self.BRIGHTCOVE_URL_TEMPLATE % (
+ bc_attr.get('data-bcaccountid', '3162030207001'),
+ bc_attr.get('data-noprebcplayerid', 'SyGGpuJy3g'),
+ bc_attr.get('data-newbcplayerid', 'default'),
+ bc_attr['data-bcid'])
+ return self.url_result(smuggle_url(bc_url, {'source_url': url}))
+
+ # We first look for clipid, because clipprog always appears before
+ patterns = [r'id=\'clip(%s)\'\s*value=\'([0-9]+)\'' % t for t in ('id', 'prog')]
+ results = list(filter(None, (re.search(p, webpage) for p in patterns)))
+ if results:
+ matches = results[0]
video_type, video_id = matches.groups()
- if video_type == 'prog':
- video_type = 'program'
+ video_type = 'clip' if video_type == 'id' else 'program'
else:
- senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
- if senate_isvp_url:
- title = self._og_search_title(webpage)
- surl = smuggle_url(senate_isvp_url, {'force_title': title})
- return self.url_result(surl, 'SenateISVP', video_id, title)
+ m = re.search(r'data-(?P<type>clip|prog)id=["\'](?P<id>\d+)', webpage)
+ if m:
+ video_id = m.group('id')
+ video_type = 'program' if m.group('type') == 'prog' else 'clip'
+ else:
+ senate_isvp_url = SenateISVPIE._search_iframe_url(webpage)
+ if senate_isvp_url:
+ title = self._og_search_title(webpage)
+ surl = smuggle_url(senate_isvp_url, {'force_title': title})
+ return self.url_result(surl, 'SenateISVP', video_id, title)
+ video_id = self._search_regex(
+ r'jwsetup\.clipprog\s*=\s*(\d+);',
+ webpage, 'jwsetup program id', default=None)
+ if video_id:
+ video_type = 'program'
+ if video_type is None or video_id is None:
+ error_message = get_element_by_class('VLplayer-error-message', webpage)
+ if error_message:
+ raise ExtractorError(error_message)
+ raise ExtractorError('unable to find video id and type')
+
+ def get_text_attr(d, attr):
+ return d.get(attr, {}).get('#text')
data = self._download_json(
- 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=%s&id=%s' % (video_type, video_id),
- video_id)
+ 'http://www.c-span.org/assets/player/ajax-player.php?os=android&html5=%s&id=%s' % (video_type, video_id),
+ video_id)['video']
+ if data['@status'] != 'Success':
+ raise ExtractorError('%s said: %s' % (self.IE_NAME, get_text_attr(data, 'error')), expected=True)
doc = self._download_xml(
'http://www.c-span.org/common/services/flashXml.php?%sid=%s' % (video_type, video_id),
title = find_xpath_attr(doc, './/string', 'name', 'title').text
thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
- files = data['video']['files']
- try:
- capfile = data['video']['capfile']['#text']
- except KeyError:
- capfile = None
-
- entries = [{
- 'id': '%s_%d' % (video_id, partnum + 1),
- 'title': (
- title if len(files) == 1 else
- '%s part %d' % (title, partnum + 1)),
- 'url': unescapeHTML(f['path']['#text']),
- 'description': description,
- 'thumbnail': thumbnail,
- 'duration': int_or_none(f.get('length', {}).get('#text')),
- 'subtitles': {
- 'en': [{
- 'url': capfile,
- 'ext': determine_ext(capfile, 'dfxp')
- }],
- } if capfile else None,
- } for partnum, f in enumerate(files)]
+ files = data['files']
+ capfile = get_text_attr(data, 'capfile')
+
+ entries = []
+ for partnum, f in enumerate(files):
+ formats = []
+ for quality in f.get('qualities', []):
+ formats.append({
+ 'format_id': '%s-%sp' % (get_text_attr(quality, 'bitrate'), get_text_attr(quality, 'height')),
+ 'url': unescapeHTML(get_text_attr(quality, 'file')),
+ 'height': int_or_none(get_text_attr(quality, 'height')),
+ 'tbr': int_or_none(get_text_attr(quality, 'bitrate')),
+ })
+ if not formats:
+ path = unescapeHTML(get_text_attr(f, 'path'))
+ if not path:
+ continue
+ formats = self._extract_m3u8_formats(
+ path, video_id, 'mp4', entry_protocol='m3u8_native',
+ m3u8_id='hls') if determine_ext(path) == 'm3u8' else [{'url': path, }]
+ self._sort_formats(formats)
+ entries.append({
+ 'id': '%s_%d' % (video_id, partnum + 1),
+ 'title': (
+ title if len(files) == 1 else
+ '%s part %d' % (title, partnum + 1)),
+ 'formats': formats,
+ 'description': description,
+ 'thumbnail': thumbnail,
+ 'duration': int_or_none(get_text_attr(f, 'length')),
+ 'subtitles': {
+ 'en': [{
+ 'url': capfile,
+ 'ext': determine_ext(capfile, 'dfxp')
+ }],
+ } if capfile else None,
+ })
if len(entries) == 1:
entry = dict(entries[0])