2013-08-27 11:56:48 +02:00
|
|
|
import re
|
|
|
|
|
|
|
|
|
|
from .common import InfoExtractor
|
|
|
|
|
from ..utils import determine_ext
|
|
|
|
|
|
2013-08-28 00:14:19 +02:00
|
|
|
|
2013-08-27 11:56:48 +02:00
|
|
|
class CNNIE(InfoExtractor):
|
2013-11-09 18:16:32 +01:00
|
|
|
_VALID_URL = r'''(?x)https?://((edition|www)\.)?cnn\.com/video/(data/.+?|\?)/
|
2013-08-28 00:14:19 +02:00
|
|
|
(?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn|(?=&)))'''
|
2013-08-27 11:56:48 +02:00
|
|
|
|
2013-08-28 00:14:19 +02:00
|
|
|
_TESTS = [{
|
2013-08-27 11:56:48 +02:00
|
|
|
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',
|
|
|
|
|
u'info_dict': {
|
|
|
|
|
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.',
|
|
|
|
|
},
|
2013-08-28 00:14:19 +02:00
|
|
|
},
|
|
|
|
|
{
|
|
|
|
|
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.\""
|
|
|
|
|
}
|
|
|
|
|
}]
|
2013-08-27 11:56:48 +02:00
|
|
|
|
|
|
|
|
def _real_extract(self, url):
|
|
|
|
|
mobj = re.match(self._VALID_URL, url)
|
|
|
|
|
path = mobj.group('path')
|
|
|
|
|
page_title = mobj.group('title')
|
2013-08-28 00:14:19 +02:00
|
|
|
info_url = u'http://cnn.com/video/data/3.0/%s/index.xml' % path
|
2013-11-26 18:48:52 +01:00
|
|
|
info = self._download_xml(info_url, page_title)
|
2013-08-27 11:56:48 +02:00
|
|
|
|
|
|
|
|
formats = []
|
|
|
|
|
for f in info.findall('files/file'):
|
|
|
|
|
mf = re.match(r'(\d+)x(\d+)(?:_(.*)k)?',f.attrib['bitrate'])
|
|
|
|
|
if mf is not None:
|
|
|
|
|
formats.append((int(mf.group(1)), int(mf.group(2)), int(mf.group(3) or 0), f.text))
|
|
|
|
|
formats = sorted(formats)
|
|
|
|
|
(_,_,_, video_path) = formats[-1]
|
|
|
|
|
video_url = 'http://ht.cdn.turner.com/cnn/big%s' % video_path
|
|
|
|
|
|
|
|
|
|
thumbnails = sorted([((int(t.attrib['height']),int(t.attrib['width'])), t.text) for t in info.findall('images/image')])
|
|
|
|
|
thumbs_dict = [{'resolution': res, 'url': t_url} for (res, t_url) in thumbnails]
|
|
|
|
|
|
|
|
|
|
return {'id': info.attrib['id'],
|
|
|
|
|
'title': info.find('headline').text,
|
|
|
|
|
'url': video_url,
|
|
|
|
|
'ext': determine_ext(video_url),
|
|
|
|
|
'thumbnail': thumbnails[-1][1],
|
|
|
|
|
'thumbnails': thumbs_dict,
|
|
|
|
|
'description': info.find('description').text,
|
|
|
|
|
}
|
