_ Git - youtube-dl/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     parse_iso8601,
  10 )
  11
  12
  13 class EllenTVIE(InfoExtractor):
  14     _VALID_URL = r'https?://(?:www\.)?(?:ellentv|ellentube)\.com/videos/(?P<id>[a-z0-9_-]+)'
  15     _TESTS = [{
  16         'url': 'http://www.ellentv.com/videos/0-7jqrsr18/',
  17         'md5': 'e4af06f3bf0d5f471921a18db5764642',
  18         'info_dict': {
  19             'id': '0-7jqrsr18',
  20             'ext': 'mp4',
  21             'title': 'What\'s Wrong with These Photos? A Whole Lot',
  22             'timestamp': 1406876400,
  23             'upload_date': '20140801',
  24         }
  25     }, {
  26         'url': 'http://ellentube.com/videos/0-dvzmabd5/',
  27         'md5': '98238118eaa2bbdf6ad7f708e3e4f4eb',
  28         'info_dict': {
  29             'id': '0-dvzmabd5',
  30             'ext': 'mp4',
  31             'title': '1 year old twin sister makes her brother laugh',
  32             'timestamp': 1419542075,
  33             'upload_date': '20141225',
  34         }
  35     }]
  36
  37     def _real_extract(self, url):
  38         video_id = self._match_id(url)
  39
  40         webpage = self._download_webpage(url, video_id)
  41         timestamp = parse_iso8601(self._search_regex(
  42             r'<span class="publish-date"><time datetime="([^"]+)">',
  43             webpage, 'timestamp'))
  44
  45         return {
  46             'id': video_id,
  47             'title': self._og_search_title(webpage),
  48             'url': self._html_search_meta('VideoURL', webpage, 'url'),
  49             'timestamp': timestamp,
  50         }
  51
  52
  53 class EllenTVClipsIE(InfoExtractor):
  54     IE_NAME = 'EllenTV:clips'
  55     _VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)'
  56     _TEST = {
  57         'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/',
  58         'info_dict': {
  59             'id': 'meryl-streep-vanessa-hudgens',
  60             'title': 'Meryl Streep, Vanessa Hudgens',
  61         },
  62         'playlist_mincount': 9,
  63     }
  64
  65     def _real_extract(self, url):
  66         playlist_id = self._match_id(url)
  67
  68         webpage = self._download_webpage(url, playlist_id)
  69         playlist = self._extract_playlist(webpage)
  70
  71         return {
  72             '_type': 'playlist',
  73             'id': playlist_id,
  74             'title': self._og_search_title(webpage),
  75             'entries': self._extract_entries(playlist)
  76         }
  77
  78     def _extract_playlist(self, webpage):
  79         json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json')
  80         try:
  81             return json.loads("[{" + json_string + "}]")
  82         except ValueError as ve:
  83             raise ExtractorError('Failed to download JSON', cause=ve)
  84
  85     def _extract_entries(self, playlist):
  86         return [self.url_result(item['url'], 'EllenTV') for item in playlist]