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

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