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://www\.clipsyndicate\.com/video/play(list/\d+)?/(?P<id>\d+)'
  14
  15     _TEST = {
  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
  27     def _real_extract(self, url):
  28         mobj = re.match(self._VALID_URL, url)
  29         video_id = mobj.group('id')
  30         js_player = self._download_webpage(
  31             'http://eplayer.clipsyndicate.com/embed/player.js?va_id=%s' % video_id,
  32             video_id, 'Downlaoding player')
  33         # it includes a required token
  34         flvars = self._search_regex(r'flvars: "(.*?)"', js_player, 'flvars')
  35
  36         pdoc = self._download_xml(
  37             'http://eplayer.clipsyndicate.com/osmf/playlist?%s' % flvars,
  38             video_id, 'Downloading video info',
  39             transform_source=fix_xml_ampersands)
  40
  41         track_doc = pdoc.find('trackList/track')
  42         def find_param(name):
  43             node = find_xpath_attr(track_doc, './/param', 'name', name)
  44             if node is not None:
  45                 return node.attrib['value']
  46
  47         return {
  48             'id': video_id,
  49             'title': find_param('title'),
  50             'url': track_doc.find('location').text,
  51             'thumbnail': find_param('thumbnail'),
  52             'duration': int(find_param('duration')),
  53         }