]> Raphaƫl G. Git Repositories - youtubedl/blob - youtube_dl/extractor/cnn.py
Update changelog.
[youtubedl] / youtube_dl / extractor / cnn.py
1 import re
2
3 from .common import InfoExtractor
4 from ..utils import determine_ext
5
6
7 class CNNIE(InfoExtractor):
8 _VALID_URL = r'''(?x)https?://((edition|www)\.)?cnn\.com/video/(data/.+?|\?)/
9 (?P<path>.+?/(?P<title>[^/]+?)(?:\.cnn|(?=&)))'''
10
11 _TESTS = [{
12 u'url': u'http://edition.cnn.com/video/?/video/sports/2013/06/09/nadal-1-on-1.cnn',
13 u'file': u'sports_2013_06_09_nadal-1-on-1.cnn.mp4',
14 u'md5': u'3e6121ea48df7e2259fe73a0628605c4',
15 u'info_dict': {
16 u'title': u'Nadal wins 8th French Open title',
17 u'description': u'World Sport\'s Amanda Davies chats with 2013 French Open champion Rafael Nadal.',
18 },
19 },
20 {
21 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",
22 u"file": u"us_2013_08_21_sot-student-gives-epic-speech.georgia-institute-of-technology.mp4",
23 u"md5": u"b5cc60c60a3477d185af8f19a2a26f4e",
24 u"info_dict": {
25 u"title": "Student's epic speech stuns new freshmen",
26 u"description": "A Georgia Tech student welcomes the incoming freshmen with an epic speech backed by music from \"2001: A Space Odyssey.\""
27 }
28 }]
29
30 def _real_extract(self, url):
31 mobj = re.match(self._VALID_URL, url)
32 path = mobj.group('path')
33 page_title = mobj.group('title')
34 info_url = u'http://cnn.com/video/data/3.0/%s/index.xml' % path
35 info = self._download_xml(info_url, page_title)
36
37 formats = []
38 for f in info.findall('files/file'):
39 mf = re.match(r'(\d+)x(\d+)(?:_(.*)k)?',f.attrib['bitrate'])
40 if mf is not None:
41 formats.append((int(mf.group(1)), int(mf.group(2)), int(mf.group(3) or 0), f.text))
42 formats = sorted(formats)
43 (_,_,_, video_path) = formats[-1]
44 video_url = 'http://ht.cdn.turner.com/cnn/big%s' % video_path
45
46 thumbnails = sorted([((int(t.attrib['height']),int(t.attrib['width'])), t.text) for t in info.findall('images/image')])
47 thumbs_dict = [{'resolution': res, 'url': t_url} for (res, t_url) in thumbnails]
48
49 return {'id': info.attrib['id'],
50 'title': info.find('headline').text,
51 'url': video_url,
52 'ext': determine_ext(video_url),
53 'thumbnail': thumbnails[-1][1],
54 'thumbnails': thumbs_dict,
55 'description': info.find('description').text,
56 }