From: Sergey M․ Date: Sun, 18 Jun 2017 13:18:51 +0000 (+0700) Subject: [asiancrush] Add extractor (closes #13420) X-Git-Url: http://git.oshgnacknak.de/?a=commitdiff_plain;h=560050669b1e98bc76c797256c6e21719541b2ac;p=youtube-dl [asiancrush] Add extractor (closes #13420) --- diff --git a/youtube_dl/extractor/asiancrush.py b/youtube_dl/extractor/asiancrush.py new file mode 100644 index 000000000..594c88c9c --- /dev/null +++ b/youtube_dl/extractor/asiancrush.py @@ -0,0 +1,93 @@ +# coding: utf-8 +from __future__ import unicode_literals + +import re + +from .common import InfoExtractor +from .kaltura import KalturaIE +from ..utils import ( + extract_attributes, + remove_end, + urlencode_postdata, +) + + +class AsianCrushIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?asiancrush\.com/video/(?:[^/]+/)?0+(?P\d+)v\b' + _TESTS = [{ + 'url': 'https://www.asiancrush.com/video/012869v/women-who-flirt/', + 'md5': 'c3b740e48d0ba002a42c0b72857beae6', + 'info_dict': { + 'id': '1_y4tmjm5r', + 'ext': 'mp4', + 'title': 'Women Who Flirt', + 'description': 'md5:3db14e9186197857e7063522cb89a805', + 'timestamp': 1496936429, + 'upload_date': '20170608', + 'uploader_id': 'craig@crifkin.com', + }, + }, { + 'url': 'https://www.asiancrush.com/video/she-was-pretty/011886v-pretty-episode-3/', + 'only_matching': True, + }] + + def _real_extract(self, url): + video_id = self._match_id(url) + + data = self._download_json( + 'https://www.asiancrush.com/wp-admin/admin-ajax.php', video_id, + data=urlencode_postdata({ + 'postid': video_id, + 'action': 'get_channel_kaltura_vars', + })) + + entry_id = data['entry_id'] + + return self.url_result( + 'kaltura:%s:%s' % (data['partner_id'], entry_id), + ie=KalturaIE.ie_key(), video_id=entry_id, + video_title=data.get('vid_label')) + + +class AsianCrushPlaylistIE(InfoExtractor): + _VALID_URL = r'https?://(?:www\.)?asiancrush\.com/series/0+(?P\d+)s\b' + _TEST = { + 'url': 'https://www.asiancrush.com/series/012481s/scholar-walks-night/', + 'info_dict': { + 'id': '12481', + 'title': 'Scholar Who Walks the Night', + 'description': 'md5:7addd7c5132a09fd4741152d96cce886', + }, + 'playlist_count': 20, + } + + def _real_extract(self, url): + playlist_id = self._match_id(url) + + webpage = self._download_webpage(url, playlist_id) + + entries = [] + + for mobj in re.finditer( + r']+href=(["\'])(?P%s.*?)\1[^>]*>' % AsianCrushIE._VALID_URL, + webpage): + attrs = extract_attributes(mobj.group(0)) + if attrs.get('class') == 'clearfix': + entries.append(self.url_result( + mobj.group('url'), ie=AsianCrushIE.ie_key())) + + title = remove_end( + self._html_search_regex( + r'(?s)]\bid=["\']movieTitle[^>]+>(.+?)', webpage, + 'title', default=None) or self._og_search_title( + webpage, default=None) or self._html_search_meta( + 'twitter:title', webpage, 'title', + default=None) or self._search_regex( + r'([^<]+)', webpage, 'title', fatal=False), + ' | AsianCrush') + + description = self._og_search_description( + webpage, default=None) or self._html_search_meta( + 'twitter:description', webpage, 'description', fatal=False) + + return self.playlist_result(entries, playlist_id, title, description) diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 7e45232dd..edbb4bdde 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -71,6 +71,10 @@ from .arte import ( TheOperaPlatformIE, ArteTVPlaylistIE, ) +from .asiancrush import ( + AsianCrushIE, + AsianCrushPlaylistIE, +) from .atresplayer import AtresPlayerIE from .atttechchannel import ATTTechChannelIE from .atvat import ATVAtIE