+from __future__ import unicode_literals
+
import re
from .common import InfoExtractor
from ..utils import (
- compat_urllib_parse,
+ int_or_none,
+ unescapeHTML,
+ find_xpath_attr,
+ smuggle_url,
+ determine_ext,
+ ExtractorError,
)
+from .senateisvp import SenateISVPIE
+
class CSpanIE(InfoExtractor):
- _VALID_URL = r'http://www.c-spanvideo.org/program/(.*)'
- _TEST = {
- u'url': u'http://www.c-spanvideo.org/program/HolderonV',
- u'file': u'315139.flv',
- u'md5': u'74a623266956f69e4df0068ab6c80fe4',
- u'info_dict': {
- u"title": u"Attorney General Eric Holder on Voting Rights Act Decision"
+ _VALID_URL = r'http://(?: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': '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.',
},
- u'skip': u'Requires rtmpdump'
- }
+ 'skip': 'Regularly fails on travis, for unknown reasons',
+ }, {
+ 'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
+ 'md5': '8e5fbfabe6ad0f89f3012a7943c1287b',
+ 'info_dict': {
+ 'id': 'c4486943',
+ 'ext': 'mp4',
+ 'title': 'CSPAN - International Health Care Models',
+ 'description': 'md5:7a985a2d595dba00af3d9c9f0783c967',
+ }
+ }, {
+ 'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall',
+ 'md5': '2ae5051559169baadba13fc35345ae74',
+ 'info_dict': {
+ 'id': '342759',
+ 'ext': 'mp4',
+ 'title': 'General Motors Ignition Switch Recall',
+ 'duration': 14848,
+ 'description': 'md5:118081aedd24bf1d3b68b3803344e7f3'
+ },
+ }, {
+ # 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',
+ 'title': 'Immigration Reforms Needed to Protect Skilled American Workers',
+ }
+ }]
def _real_extract(self, url):
- mobj = re.match(self._VALID_URL, url)
- prog_name = mobj.group(1)
- webpage = self._download_webpage(url, prog_name)
- video_id = self._search_regex(r'programid=(.*?)&', webpage, 'video id')
- data = compat_urllib_parse.urlencode({'programid': video_id,
- 'dynamic':'1'})
- info_url = 'http://www.c-spanvideo.org/common/services/flashXml.php?' + data
- video_info = self._download_webpage(info_url, video_id, u'Downloading video info')
-
- self.report_extraction(video_id)
-
- title = self._html_search_regex(r'<string name="title">(.*?)</string>',
- video_info, 'title')
- description = self._html_search_regex(r'<meta (?:property="og:|name=")description" content="(.*?)"',
- webpage, 'description',
- flags=re.MULTILINE|re.DOTALL)
-
- url = self._search_regex(r'<string name="URL">(.*?)</string>',
- video_info, 'video url')
- url = url.replace('$(protocol)', 'rtmp').replace('$(port)', '443')
- path = self._search_regex(r'<string name="path">(.*?)</string>',
- video_info, 'rtmp play path')
-
- return {'id': video_id,
- 'title': title,
- 'ext': 'flv',
- 'url': url,
- 'play_path': path,
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+ matches = re.search(r'data-(prog|clip)id=\'([0-9]+)\'', webpage)
+ if matches:
+ video_type, video_id = matches.groups()
+ if video_type == 'prog':
+ video_type = '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)
+
+ def get_text_attr(d, attr):
+ return d.get(attr, {}).get('#text')
+
+ data = self._download_json(
+ '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),
+ video_id)
+
+ description = self._html_search_meta('description', webpage)
+
+ title = find_xpath_attr(doc, './/string', 'name', 'title').text
+ thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
+
+ files = data['files']
+ capfile = get_text_attr(data, 'capfile')
+
+ entries = []
+ for partnum, f in enumerate(files):
+ formats = []
+ for quality in f['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')),
+ })
+ 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': self._og_search_thumbnail(webpage),
- }
+ '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])
+ entry['id'] = 'c' + video_id if video_type == 'clip' else video_id
+ return entry
+ else:
+ return {
+ '_type': 'playlist',
+ 'entries': entries,
+ 'title': title,
+ 'id': 'c' + video_id if video_type == 'clip' else video_id,
+ }
projects / youtube-dl / blobdiff