X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/af478477605bdf3f5d57562035885cfee905f379..099764c0c91f4ad7db03d9347798f8619383ea7e:/youtube_dl/extractor/cspan.py?ds=inline diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index d65046f..5411066 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -4,15 +4,16 @@ import re from .common import InfoExtractor from ..utils import ( + int_or_none, unescapeHTML, find_xpath_attr, ) class CSpanIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P\d+)' + _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P[0-9a-f]+)' IE_DESC = 'C-SPAN' - _TEST = { + _TESTS = [{ 'url': 'http://www.c-span.org/video/?313572-1/HolderonV', 'md5': '8e44ce11f0f725527daccc453f553eb0', 'info_dict': { @@ -22,13 +23,31 @@ class CSpanIE(InfoExtractor): '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.', }, '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', + 'info_dict': { + 'id': '340723', + 'ext': 'mp4', + 'title': 'International Health Care Models', + 'description': 'md5:7a985a2d595dba00af3d9c9f0783c967', + } + }, { + 'url': 'http://www.c-span.org/video/?318608-1/gm-ignition-switch-recall', + 'info_dict': { + 'id': '342759', + 'title': 'General Motors Ignition Switch Recall', + }, + 'playlist_duration_sum': 14855, + }] 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'data-progid=\'(\d+)\'>', webpage, 'video id') + video_id = self._search_regex(r'progid=\'?([0-9]+)\'?>', webpage, 'video id') description = self._html_search_regex( [ @@ -43,18 +62,29 @@ class CSpanIE(InfoExtractor): 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, + doc = self._download_xml( + 'http://www.c-span.org/common/services/flashXml.php?programid=' + video_id, video_id) - def find_string(s): - return find_xpath_attr(doc, './/string', 'name', s).text + title = find_xpath_attr(doc, './/string', 'name', 'title').text + thumbnail = find_xpath_attr(doc, './/string', 'name', 'poster').text + + files = data['video']['files'] + + 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')), + } for partnum, f in enumerate(files)] return { + '_type': 'playlist', + 'entries': entries, + 'title': title, 'id': video_id, - 'title': find_string('title'), - 'url': url, - 'description': description, - 'thumbnail': find_string('poster'), }