from .common import InfoExtractor
from ..utils import (
+ int_or_none,
unescapeHTML,
find_xpath_attr,
+ smuggle_url,
+ determine_ext,
+ ExtractorError,
)
+from .senateisvp import SenateISVPIE
class CSpanIE(InfoExtractor):
IE_DESC = 'C-SPAN'
_TESTS = [{
'url': 'http://www.c-span.org/video/?313572-1/HolderonV',
- 'md5': '8e44ce11f0f725527daccc453f553eb0',
+ 'md5': '94b29a4f131ff03d23471dd6f60b6a1d',
'info_dict': {
'id': '315139',
'ext': 'mp4',
'title': 'Attorney General Eric Holder on Voting Rights Act Decision',
- '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.',
+ '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.',
},
'skip': 'Regularly fails on travis, for unknown reasons',
}, {
'url': 'http://www.c-span.org/video/?c4486943/cspan-international-health-care-models',
- # For whatever reason, the served video alternates between
- # two different ones
- #'md5': 'dbb0f047376d457f2ab8b3929cbb2d0c',
+ 'md5': '8e5fbfabe6ad0f89f3012a7943c1287b',
'info_dict': {
- 'id': '340723',
+ 'id': 'c4486943',
'ext': 'mp4',
- 'title': 'International Health Care Models',
+ '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)
- page_id = mobj.group('id')
- webpage = self._download_webpage(url, page_id)
- video_id = self._search_regex(r'progid=\'?([0-9]+)\'?>', webpage, 'video id')
-
- description = self._html_search_regex(
- [
- # The full description
- r'<div class=\'expandable\'>(.*?)<a href=\'#\'',
- # If the description is small enough the other div is not
- # present, otherwise this is a stripped version
- r'<p class=\'initial\'>(.*?)</p>'
- ],
- webpage, 'description', flags=re.DOTALL)
-
- info_url = 'http://c-spanvideo.org/videoLibrary/assets/player/ajax-player.php?os=android&html5=program&id=' + video_id
- data = self._download_json(info_url, video_id)
-
- url = unescapeHTML(data['video']['files'][0]['path']['#text'])
-
- doc = self._download_xml('http://www.c-span.org/common/services/flashXml.php?programid=' + video_id + '&version=2014-01-23',
+ 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)
- formats = [
- {
- 'url': url,
- }
- ]
-
- def find_string(node, s):
- return find_xpath_attr(node, './/string', 'name', s).text
+ description = self._html_search_meta('description', webpage)
- def find_number(node, s):
- return int(find_xpath_attr(node, './/number', 'name', s).text)
+ title = find_xpath_attr(doc, './/string', 'name', 'title').text
+ thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text
- def find_array(node, s):
- return find_xpath_attr(node, './/array', 'name', s)
+ files = data['files']
+ capfile = get_text_attr(data, 'capfile')
- def process_files(files, url, formats):
- for file in files:
- path = find_string(file, 'path')
- #duration = find_number(file, './number', 'name', 'length')
- hd = find_number(file, 'hd')
+ entries = []
+ for partnum, f in enumerate(files):
+ formats = []
+ for quality in f['qualities']:
formats.append({
- 'url': url,
- 'play_path': path,
- 'ext': 'flv',
- 'quality': hd,
+ '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')),
})
-
- def process_node(node, formats):
- url = find_xpath_attr(node, './string', 'name', 'url')
- if url is None:
- url = find_xpath_attr(node, './string', 'name', 'URL')
- if url is None:
- return
- url = url.text.replace('$(protocol)', 'rtmp').replace('$(port)', '1935')
- files = find_array(node, 'files')
- if files is None:
- return
- process_files(files, url, formats)
-
- process_node(doc.find('./media-link'), formats)
-
- streams = find_array(doc, 'streams')
- if streams is not None:
- for stream in streams:
- if find_string(stream, 'name') != 'vod':
- continue
- process_node(stream, formats)
-
- return {
- 'id': video_id,
- 'title': find_string(doc, 'title'),
- 'description': description,
- 'thumbnail': find_string(doc, 'poster'),
- 'formats': formats,
- }
+ 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])
+ 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