X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/961c212c4f97846f00004b37e8dbd94b124a2f99..11021a3e7a38072a0072edc613930e0a1193196c:/youtube_dl/extractor/cspan.py diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index 2246515..d65046f 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -1,44 +1,60 @@ +from __future__ import unicode_literals + import re from .common import InfoExtractor from ..utils import ( - compat_urllib_parse, + unescapeHTML, + find_xpath_attr, ) + class CSpanIE(InfoExtractor): - _VALID_URL = r'http://www.c-spanvideo.org/program/(.*)' + _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P\d+)' + IE_DESC = 'C-SPAN' + _TEST = { + 'url': 'http://www.c-span.org/video/?313572-1/HolderonV', + 'md5': '8e44ce11f0f725527daccc453f553eb0', + '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.', + }, + 'skip': 'Regularly fails on travis, for unknown reasons', + } 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'(.*?)', - video_info, 'title') - description = self._html_search_regex(r'(.*?)', - video_info, 'video url') - url = url.replace('$(protocol)', 'rtmp').replace('$(port)', '443') - path = self._search_regex(r'(.*?)', - video_info, 'rtmp play path') - - return {'id': video_id, - 'title': title, - 'ext': 'flv', - 'url': url, - 'play_path': path, - 'description': description, - 'thumbnail': thumbnail, - } + page_id = mobj.group('id') + webpage = self._download_webpage(url, page_id) + video_id = self._search_regex(r'data-progid=\'(\d+)\'>', webpage, 'video id') + + description = self._html_search_regex( + [ + # The full description + r'
(.*?)(.*?)

' + ], + 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, + video_id) + + def find_string(s): + return find_xpath_attr(doc, './/string', 'name', s).text + + return { + 'id': video_id, + 'title': find_string('title'), + 'url': url, + 'description': description, + 'thumbnail': find_string('poster'), + }