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     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             'description': 'md5:35f152dc66b587cf13e6d2cf4fa467f6',
  23             'timestamp': 1406876400,
  24             'upload_date': '20140801',
  25         }
  26     }, {
  27         'url': 'http://ellentube.com/videos/0-dvzmabd5/',
  28         'md5': '98238118eaa2bbdf6ad7f708e3e4f4eb',
  29         'info_dict': {
  30             'id': '0-dvzmabd5',
  31             'ext': 'mp4',
  32             'title': '1 year old twin sister makes her brother laugh',
  33             'description': '1 year old twin sister makes her brother laugh',
  34             'timestamp': 1419542075,
  35             'upload_date': '20141225',
  36         }
  37     }]
  38
  39     def _real_extract(self, url):
  40         video_id = self._match_id(url)
  41
  42         webpage = self._download_webpage(url, video_id)
  43         video_url = self._html_search_meta('VideoURL', webpage, 'url')
  44         title = self._og_search_title(webpage, default=None) or self._search_regex(
  45             r'pageName\s*=\s*"([^"]+)"', webpage, 'title')
  46         description = self._html_search_meta(
  47             'description', webpage, 'description') or self._og_search_description(webpage)
  48         timestamp = parse_iso8601(self._search_regex(
  49             r'<span class="publish-date"><time datetime="([^"]+)">',
  50             webpage, 'timestamp'))
  51
  52         return {
  53             'id': video_id,
  54             'url': video_url,
  55             'title': title,
  56             'description': description,
  57             'timestamp': timestamp,
  58         }
  59
  60
  61 class EllenTVClipsIE(InfoExtractor):
  62     IE_NAME = 'EllenTV:clips'
  63     _VALID_URL = r'https?://(?:www\.)?ellentv\.com/episodes/(?P<id>[a-z0-9_-]+)'
  64     _TEST = {
  65         'url': 'http://www.ellentv.com/episodes/meryl-streep-vanessa-hudgens/',
  66         'info_dict': {
  67             'id': 'meryl-streep-vanessa-hudgens',
  68             'title': 'Meryl Streep, Vanessa Hudgens',
  69         },
  70         'playlist_mincount': 9,
  71     }
  72
  73     def _real_extract(self, url):
  74         playlist_id = self._match_id(url)
  75
  76         webpage = self._download_webpage(url, playlist_id)
  77         playlist = self._extract_playlist(webpage)
  78
  79         return {
  80             '_type': 'playlist',
  81             'id': playlist_id,
  82             'title': self._og_search_title(webpage),
  83             'entries': self._extract_entries(playlist)
  84         }
  85
  86     def _extract_playlist(self, webpage):
  87         json_string = self._search_regex(r'playerView.addClips\(\[\{(.*?)\}\]\);', webpage, 'json')
  88         try:
  89             return json.loads("[{" + json_string + "}]")
  90         except ValueError as ve:
  91             raise ExtractorError('Failed to download JSON', cause=ve)
  92
  93     def _extract_entries(self, playlist):
  94         return [self.url_result(item['url'], 'EllenTV') for item in playlist]