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

   1 from __future__ import unicode_literals
   2
   3 from .common import InfoExtractor
   4 from ..utils import (
   5     ExtractorError,
   6     int_or_none,
   7     js_to_json,
   8     determine_ext,
   9 )
  10
  11
  12 class ClipfishIE(InfoExtractor):
  13     IE_NAME = 'clipfish'
  14
  15     _VALID_URL = r'^https?://(?:www\.)?clipfish\.de/.*?/video/(?P<id>[0-9]+)/'
  16     _TEST = {
  17         'url': 'http://www.clipfish.de/special/game-trailer/video/3966754/fifa-14-e3-2013-trailer/',
  18         'md5': '79bc922f3e8a9097b3d68a93780fd475',
  19         'info_dict': {
  20             'id': '3966754',
  21             'ext': 'mp4',
  22             'title': 'FIFA 14 - E3 2013 Trailer',
  23             'duration': 82,
  24         }
  25     }
  26
  27     def _real_extract(self, url):
  28         video_id = self._match_id(url)
  29         webpage = self._download_webpage(url, video_id)
  30         video_info = self._parse_json(
  31             js_to_json(self._html_search_regex('var videoObject = ({[^}]+?})', webpage, 'videoObject')),
  32             video_id
  33         )
  34         info_url = self._parse_json(
  35             js_to_json(self._html_search_regex('var globalFlashvars = ({[^}]+?})', webpage, 'globalFlashvars')),
  36             video_id
  37         )['data']
  38
  39         doc = self._download_xml(
  40             info_url, video_id, note='Downloading info page')
  41         title = doc.find('title').text
  42         video_url = doc.find('filename').text
  43         thumbnail = doc.find('imageurl').text
  44         duration = int_or_none(video_info['length'])
  45         formats = [{'url': video_info['videourl']},{'url': video_url}]
  46         self._sort_formats(formats)
  47
  48         return {
  49             'id': video_id,
  50             'title': title,
  51             'formats': formats,
  52             'thumbnail': thumbnail,
  53             'duration': duration,
  54         }