From: Jaime Marquínez Ferrándiz Date: Sun, 2 Feb 2014 17:24:20 +0000 (+0100) Subject: [cspan] Fix extraction (fixes #2291) X-Git-Url: http://git.bitcoin.ninja/?a=commitdiff_plain;h=009a3408f5195442c4bd0471a91a0b38d283382d;p=youtube-dl [cspan] Fix extraction (fixes #2291) The webpage urls have changed. The title and thumbnail are now extracted from an xml. --- diff --git a/youtube_dl/extractor/cspan.py b/youtube_dl/extractor/cspan.py index e54009622..d65046f58 100644 --- a/youtube_dl/extractor/cspan.py +++ b/youtube_dl/extractor/cspan.py @@ -1,49 +1,60 @@ from __future__ import unicode_literals -import json import re from .common import InfoExtractor from ..utils import ( unescapeHTML, + find_xpath_attr, ) class CSpanIE(InfoExtractor): - _VALID_URL = r'http://(?:www\.)?c-spanvideo\.org/program/(?P.*)' + _VALID_URL = r'http://(?:www\.)?c-span\.org/video/\?(?P\d+)' IE_DESC = 'C-SPAN' _TEST = { - 'url': 'http://www.c-spanvideo.org/program/HolderonV', - 'file': '315139.mp4', + '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.', + '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('name') - webpage = self._download_webpage(url, prog_name) - video_id = self._search_regex(r'prog(?:ram)?id=(.*?)&', webpage, 'video id') - - title = self._html_search_regex( - r'\n\s*]*>(.*?)', webpage, 'title') - description = self._og_search_description(webpage) + 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'