X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fcspan.py;h=b6552c542411c2abf639e71c955c66c34db2b007;hb=8944ec0109b1e9c847f178755123d5453400dd50;hp=007d605299a8ae34698c56f3705a2deaec9117cd;hpb=11a15be4ce75105da98fad75dc5db44040f01b65;p=youtube-dl diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index 007d60529..b6552c542 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -4,6 +4,7 @@ import re from .common import InfoExtractor from ..utils import ( + int_or_none, unescapeHTML, find_xpath_attr, ) @@ -24,7 +25,7 @@ class CSpanIE(InfoExtractor): '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 vide oalternates between + # For whatever reason, the served video alternates between # two different ones #'md5': 'dbb0f047376d457f2ab8b3929cbb2d0c', 'info_dict': { @@ -54,18 +55,29 @@ 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'), }