Raphaël G. Git Repositories - youtubedl/blob - youtube_dl/extractor/collegehumor.py

   1 import re
   2 import xml.etree.ElementTree
   3
   4 from .common import InfoExtractor
   5 from ..utils import (
   6     compat_urllib_parse_urlparse,
   7     determine_ext,
   8
   9     ExtractorError,
  10 )
  11
  12
  13 class CollegeHumorIE(InfoExtractor):
  14     _VALID_URL = r'^(?:https?://)?(?:www\.)?collegehumor\.com/(video|embed|e)/(?P<videoid>[0-9]+)/?(?P<shorttitle>.*)$'
  15
  16     _TESTS = [{
  17         u'url': u'http://www.collegehumor.com/video/6902724/comic-con-cosplay-catastrophe',
  18         u'file': u'6902724.mp4',
  19         u'md5': u'1264c12ad95dca142a9f0bf7968105a0',
  20         u'info_dict': {
  21             u'title': u'Comic-Con Cosplay Catastrophe',
  22             u'description': u'Fans get creative this year at San Diego.  Too creative.  And yes, that\'s really Joss Whedon.',
  23         },
  24     },
  25     {
  26         u'url': u'http://www.collegehumor.com/video/3505939/font-conference',
  27         u'file': u'3505939.mp4',
  28         u'md5': u'c51ca16b82bb456a4397987791a835f5',
  29         u'info_dict': {
  30             u'title': u'Font Conference',
  31             u'description': u'This video wasn\'t long enough, so we made it double-spaced.',
  32         },
  33     }]
  34
  35     def _real_extract(self, url):
  36         mobj = re.match(self._VALID_URL, url)
  37         if mobj is None:
  38             raise ExtractorError(u'Invalid URL: %s' % url)
  39         video_id = mobj.group('videoid')
  40
  41         info = {
  42             'id': video_id,
  43             'uploader': None,
  44             'upload_date': None,
  45         }
  46
  47         self.report_extraction(video_id)
  48         xmlUrl = 'http://www.collegehumor.com/moogaloop/video/' + video_id
  49         metaXml = self._download_webpage(xmlUrl, video_id,
  50                                          u'Downloading info XML',
  51                                          u'Unable to download video info XML')
  52
  53         mdoc = xml.etree.ElementTree.fromstring(metaXml)
  54         try:
  55             videoNode = mdoc.findall('./video')[0]
  56             youtubeIdNode = videoNode.find('./youtubeID')
  57             if youtubeIdNode is not None:
  58                 return self.url_result(youtubeIdNode.text, 'Youtube')
  59             info['description'] = videoNode.findall('./description')[0].text
  60             info['title'] = videoNode.findall('./caption')[0].text
  61             info['thumbnail'] = videoNode.findall('./thumbnail')[0].text
  62             next_url = videoNode.findall('./file')[0].text
  63         except IndexError:
  64             raise ExtractorError(u'Invalid metadata XML file')
  65
  66         if next_url.endswith(u'manifest.f4m'):
  67             manifest_url = next_url + '?hdcore=2.10.3'
  68             manifestXml = self._download_webpage(manifest_url, video_id,
  69                                          u'Downloading XML manifest',
  70                                          u'Unable to download video info XML')
  71
  72             adoc = xml.etree.ElementTree.fromstring(manifestXml)
  73             try:
  74                 media_node = adoc.findall('./{http://ns.adobe.com/f4m/1.0}media')[0]
  75                 node_id = media_node.attrib['url']
  76                 video_id = adoc.findall('./{http://ns.adobe.com/f4m/1.0}id')[0].text
  77             except IndexError as err:
  78                 raise ExtractorError(u'Invalid manifest file')
  79             url_pr = compat_urllib_parse_urlparse(info['thumbnail'])
  80             info['url'] = url_pr.scheme + '://' + url_pr.netloc + video_id[:-2].replace('.csmil','').replace(',','')
  81             info['ext'] = 'mp4'
  82         else:
  83             # Old-style direct links
  84             info['url'] = next_url
  85             info['ext'] = determine_ext(info['url'])
  86
  87         return info