X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/33cd347759d6d999325ebf3c69b7ed5692c343b2..HEAD:/youtube_dl/extractor/thisav.py diff --git a/youtube_dl/extractor/thisav.py b/youtube_dl/extractor/thisav.py index 9dcfc28..dc3dd03 100644 --- a/youtube_dl/extractor/thisav.py +++ b/youtube_dl/extractor/thisav.py @@ -1,47 +1,73 @@ -#coding: utf-8 +# coding: utf-8 +from __future__ import unicode_literals import re from .common import InfoExtractor -from ..utils import ( - determine_ext, -) +from ..utils import remove_end + class ThisAVIE(InfoExtractor): _VALID_URL = r'https?://(?:www\.)?thisav\.com/video/(?P[0-9]+)/.*' - _TEST = { - u"url": u"http://www.thisav.com/video/47734/%98%26sup1%3B%83%9E%83%82---just-fit.html", - u"file": u"47734.flv", - u"md5": u"0480f1ef3932d901f0e0e719f188f19b", - u"info_dict": { - u"title": u"高樹マリア - Just fit", - u"uploader": u"dj7970", - u"uploader_id": u"dj7970" + _TESTS = [{ + # jwplayer + 'url': 'http://www.thisav.com/video/47734/%98%26sup1%3B%83%9E%83%82---just-fit.html', + 'md5': '0480f1ef3932d901f0e0e719f188f19b', + 'info_dict': { + 'id': '47734', + 'ext': 'flv', + 'title': '高樹マリア - Just fit', + 'uploader': 'dj7970', + 'uploader_id': 'dj7970' } - } + }, { + # html5 media + 'url': 'http://www.thisav.com/video/242352/nerdy-18yo-big-ass-tattoos-and-glasses.html', + 'md5': 'ba90c076bd0f80203679e5b60bf523ee', + 'info_dict': { + 'id': '242352', + 'ext': 'mp4', + 'title': 'Nerdy 18yo Big Ass Tattoos and Glasses', + 'uploader': 'cybersluts', + 'uploader_id': 'cybersluts', + }, + }] def _real_extract(self, url): mobj = re.match(self._VALID_URL, url) video_id = mobj.group('id') webpage = self._download_webpage(url, video_id) - title = self._html_search_regex(r'

([^<]*)

', webpage, u'title') + title = remove_end(self._html_search_regex( + r'([^<]+)', webpage, 'title'), + ' - 視頻 - ThisAV.com-世界第一中文成人娛樂網站') video_url = self._html_search_regex( - r"addVariable\('file','([^']+)'\);", webpage, u'video url') + r"addVariable\('file','([^']+)'\);", webpage, 'video url', default=None) + if video_url: + info_dict = { + 'formats': [{ + 'url': video_url, + }], + } + else: + entries = self._parse_html5_media_entries(url, webpage, video_id) + if entries: + info_dict = entries[0] + else: + info_dict = self._extract_jwplayer_data( + webpage, video_id, require_title=False) uploader = self._html_search_regex( - r': ([^<]+)', - webpage, u'uploader name', fatal=False) + r': ([^<]+)', + webpage, 'uploader name', fatal=False) uploader_id = self._html_search_regex( - r': (?:[^<]+)', - webpage, u'uploader id', fatal=False) - ext = determine_ext(video_url) - - return { - '_type': 'video', - 'id': video_id, - 'url': video_url, - 'uploader': uploader, + r': (?:[^<]+)', + webpage, 'uploader id', fatal=False) + + info_dict.update({ + 'id': video_id, + 'uploader': uploader, 'uploader_id': uploader_id, - 'title': title, - 'ext': ext, - } + 'title': title, + }) + + return info_dict