youtube_dl/extractor/asiancrush.py

   1 # coding: utf-8
   2 from __future__ import unicode_literals
   3
   4 import re
   5
   6 from .common import InfoExtractor
   7 from .kaltura import KalturaIE
   8 from ..utils import (
   9     extract_attributes,
  10     remove_end,
  11     urlencode_postdata,
  12 )
  13
  14
  15 class AsianCrushIE(InfoExtractor):
  16     _VALID_URL = r'https?://(?:www\.)?asiancrush\.com/video/(?:[^/]+/)?0+(?P<id>\d+)v\b'
  17     _TESTS = [{
  18         'url': 'https://www.asiancrush.com/video/012869v/women-who-flirt/',
  19         'md5': 'c3b740e48d0ba002a42c0b72857beae6',
  20         'info_dict': {
  21             'id': '1_y4tmjm5r',
  22             'ext': 'mp4',
  23             'title': 'Women Who Flirt',
  24             'description': 'md5:3db14e9186197857e7063522cb89a805',
  25             'timestamp': 1496936429,
  26             'upload_date': '20170608',
  27             'uploader_id': 'craig@crifkin.com',
  28         },
  29     }, {
  30         'url': 'https://www.asiancrush.com/video/she-was-pretty/011886v-pretty-episode-3/',
  31         'only_matching': True,
  32     }]
  33
  34     def _real_extract(self, url):
  35         video_id = self._match_id(url)
  36
  37         data = self._download_json(
  38             'https://www.asiancrush.com/wp-admin/admin-ajax.php', video_id,
  39             data=urlencode_postdata({
  40                 'postid': video_id,
  41                 'action': 'get_channel_kaltura_vars',
  42             }))
  43
  44         entry_id = data['entry_id']
  45
  46         return self.url_result(
  47             'kaltura:%s:%s' % (data['partner_id'], entry_id),
  48             ie=KalturaIE.ie_key(), video_id=entry_id,
  49             video_title=data.get('vid_label'))
  50
  51
  52 class AsianCrushPlaylistIE(InfoExtractor):
  53     _VALID_URL = r'https?://(?:www\.)?asiancrush\.com/series/0+(?P<id>\d+)s\b'
  54     _TEST = {
  55         'url': 'https://www.asiancrush.com/series/012481s/scholar-walks-night/',
  56         'info_dict': {
  57             'id': '12481',
  58             'title': 'Scholar Who Walks the Night',
  59             'description': 'md5:7addd7c5132a09fd4741152d96cce886',
  60         },
  61         'playlist_count': 20,
  62     }
  63
  64     def _real_extract(self, url):
  65         playlist_id = self._match_id(url)
  66
  67         webpage = self._download_webpage(url, playlist_id)
  68
  69         entries = []
  70
  71         for mobj in re.finditer(
  72                 r'<a[^>]+href=(["\'])(?P<url>%s.*?)\1[^>]*>' % AsianCrushIE._VALID_URL,
  73                 webpage):
  74             attrs = extract_attributes(mobj.group(0))
  75             if attrs.get('class') == 'clearfix':
  76                 entries.append(self.url_result(
  77                     mobj.group('url'), ie=AsianCrushIE.ie_key()))
  78
  79         title = remove_end(
  80             self._html_search_regex(
  81                 r'(?s)<h1\b[^>]\bid=["\']movieTitle[^>]+>(.+?)</h1>', webpage,
  82                 'title', default=None) or self._og_search_title(
  83                 webpage, default=None) or self._html_search_meta(
  84                 'twitter:title', webpage, 'title',
  85                 default=None) or self._search_regex(
  86                 r'<title>([^<]+)</title>', webpage, 'title', fatal=False),
  87             ' | AsianCrush')
  88
  89         description = self._og_search_description(
  90             webpage, default=None) or self._html_search_meta(
  91             'twitter:description', webpage, 'description', fatal=False)
  92
  93         return self.playlist_result(entries, playlist_id, title, description)