w/youtube-dl
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

[cnn] Allow more URLs

Browse source
This commit is contained in:
Philipp Hagemeister 2013-08-28 00:14:19 +02:00
parent 1619e22f40
commit 273f603efb
1 changed files with 18 additions and 6 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

22
youtube_dl/extractor/cnn.py
View file

@ -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<path>.+?/(?P<title>[^/]+?)\.cnn)'
_TEST = {
class CNNIE(InfoExtractor):
_VALID_URL = r'''(?x)https?://(edition\.)?cnn\.com/video/(data/.+?|\?)/
(?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn|(?=&)))'''
_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 = []