From 273f603efb2028a54e04cca314b72bc2a9d767ef Mon Sep 17 00:00:00 2001 From: Philipp Hagemeister Date: Wed, 28 Aug 2013 00:14:19 +0200 Subject: [PATCH] [cnn] Allow more URLs --- youtube_dl/extractor/cnn.py | 22 +++++++++++++++++----- 1 file changed, 17 insertions(+), 5 deletions(-) diff --git a/youtube_dl/extractor/cnn.py b/youtube_dl/extractor/cnn.py index cee78765b..4338bd180 100644 --- a/youtube_dl/extractor/cnn.py +++ b/youtube_dl/extractor/cnn.py @@ -4,10 +4,12 @@ import xml.etree.ElementTree from .common import InfoExtractor from ..utils import determine_ext + class CNNIE(InfoExtractor): - _VALID_URL = r'https?://(edition\.)?cnn\.com/video/(data/.+?|\?)/(?P.+?/(?P[^/]+?)\.cnn)' + _VALID_URL = r'''(?x)https?://(edition\.)?cnn\.com/video/(data/.+?|\?)/ + (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn|(?=&)))''' - _TEST = { + _TESTS = [{ u'url': u'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn', u'file': u'sports_2013_06_09_nadal-1-on-1.cnn.mp4', u'md5': u'3e6121ea48df7e2259fe73a0628605c4', @@ -15,14 +17,24 @@ class CNNIE(InfoExtractor): u'title': u'Nadal wins 8th French Open title', u'description': u'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.', }, - } + }, + { + u"url": u"http://edition.cnn.com/video/?/video/us/2013/08/21/sot-student-gives-epic-speech.georgia-institute-of-technology&utm_source=feedburner&utm_medium=feed&utm_campaign=Feed%3A+rss%2Fcnn_topstories+%28RSS%3A+Top+Stories%29", + u"file": u"us_2013_08_21_sot-student-gives-epic-speech.georgia-institute-of-technology.mp4", + u"md5": u"b5cc60c60a3477d185af8f19a2a26f4e", + u"info_dict": { + u"title": "Student's epic speech stuns new freshmen", + u"description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\"" + } + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) path = mobj.group('path') page_title = mobj.group('title') - info_xml = self._download_webpage( - 'http://cnn.com/video/data/3.0/%s/index.xml' % path, page_title) + info_url = u'http://cnn.com/video/data/3.0/%s/index.xml' % path + print(info_url) + info_xml = self._download_webpage(info_url, page_title) info = xml.etree.ElementTree.fromstring(info_xml.encode('utf-8')) formats = []