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

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import json
   5
   6 from .common import InfoExtractor
   7 from ..utils import (
   8     ExtractorError,
   9 )
  10
  11
  12 class EllenTVIE(InfoExtractor):
  13     _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
  14     _TEST = {
  15         'url': 'http://www.ellentv.com/videos/0-ipq1gsai/',
  16         'md5': '8e3c576bf2e9bfff4d76565f56f94c9c',
  17         'info_dict': {
  18             'id': '0_ipq1gsai',
  19             'ext': 'mp4',
  20             'title': 'Fast Fingers of Fate',
  21             'description': 'md5:587e79fbbd0d73b148bc596d99ce48e6',
  22             'timestamp': 1428035648,
  23             'upload_date': '20150403',
  24             'uploader_id': 'batchUser',
  25         }
  26     }
  27
  28     def _real_extract(self, url):
  29         video_id = self._match_id(url)
  30
  31         webpage = self._download_webpage(
  32             'http://widgets.ellentube.com/videos/%s' % video_id,
  33             video_id)
  34
  35         partner_id = self._search_regex(
  36             r"var\s+partnerId\s*=\s*'([^']+)", webpage, 'partner id')
  37
  38         kaltura_id = self._search_regex(
  39             [r'id="kaltura_player_([^"]+)"',
  40              r"_wb_entry_id\s*:\s*'([^']+)",
  41              r'data-kaltura-entry-id="([^"]+)'],
  42             webpage, 'kaltura id')
  43
  44         return self.url_result('kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura')
  45
  46
  47 class EllenTVClipsIE(InfoExtractor):
  48     IE_NAME = 'EllenTV:clips'
  49     _VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)'
  50     _TEST = {
  51         'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/',
  52         'info_dict': {
  53             'id': 'meryl-streep-vanessa-hudgens',
  54             'title': 'Meryl Streep, Vanessa Hudgens',
  55         },
  56         'playlist_mincount': 7,
  57     }
  58
  59     def _real_extract(self, url):
  60         playlist_id = self._match_id(url)
  61
  62         webpage = self._download_webpage(url, playlist_id)
  63         playlist = self._extract_playlist(webpage)
  64
  65         return {
  66             '_type': 'playlist',
  67             'id': playlist_id,
  68             'title': self._og_search_title(webpage),
  69             'entries': self._extract_entries(playlist)
  70         }
  71
  72     def _extract_playlist(self, webpage):
  73         json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json')
  74         try:
  75             return json.loads("[{" + json_string + "}]")
  76         except ValueError as ve:
  77             raise ExtractorError('Failed to download JSON', cause=ve)
  78
  79     def _extract_entries(self, playlist):
  80         return [
  81             self.url_result(
  82                 'kaltura:%s:%s' % (item['kaltura_partner_id'], item['kaltura_entry_id']),
  83                 'Kaltura')
  84             for item in playlist]