_ Git - youtube-dl/blob - youtube_dl/extractor/clipsyndicate.py

   1 from __future__ import unicode_literals
   2
   3 import re
   4
   5 from .common import InfoExtractor
   6 from ..utils import (
   7     find_xpath_attr,
   8     fix_xml_ampersands
   9 )
  10
  11
  12 class ClipsyndicateIE(InfoExtractor):
  13     _VALID_URL = r'http://(?:chic|www)\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
  14
  15     _TESTS = [{
  16         'url': 'http://www.clipsyndicate.com/video/play/4629301/brick_briscoe',
  17         'md5': '4d7d549451bad625e0ff3d7bd56d776c',
  18         'info_dict': {
  19             'id': '4629301',
  20             'ext': 'mp4',
  21             'title': 'Brick Briscoe',
  22             'duration': 612,
  23             'thumbnail': 're:^https?://.+\.jpg',
  24         },
  25     }, {
  26         'url': 'http://chic.clipsyndicate.com/video/play/5844117/shark_attack',
  27         'only_matching': True,
  28     }]
  29
  30     def _real_extract(self, url):
  31         mobj = re.match(self._VALID_URL, url)
  32         video_id = mobj.group('id')
  33         js_player = self._download_webpage(
  34             'http://eplayer.clipsyndicate.com/embed/player.js?va_id=%s' % video_id,
  35             video_id, 'Downlaoding player')
  36         # it includes a required token
  37         flvars = self._search_regex(r'flvars: "(.*?)"', js_player, 'flvars')
  38
  39         pdoc = self._download_xml(
  40             'http://eplayer.clipsyndicate.com/osmf/playlist?%s' % flvars,
  41             video_id, 'Downloading video info',
  42             transform_source=fix_xml_ampersands)
  43
  44         track_doc = pdoc.find('trackList/track')
  45
  46         def find_param(name):
  47             node = find_xpath_attr(track_doc, './/param', 'name', name)
  48             if node is not None:
  49                 return node.attrib['value']
  50
  51         return {
  52             'id': video_id,
  53             'title': find_param('title'),
  54             'url': track_doc.find('location').text,
  55             'thumbnail': find_param('thumbnail'),
  56             'duration': int(find_param('duration')),
  57         }