X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/15b1d10671b48df598afd70e17ba21e9e64ac766..47d80ec0b18245caeb97018d4c1af18d0b5b972b:/youtube_dl/extractor/thisav.py diff --git a/youtube_dl/extractor/thisav.py b/youtube_dl/extractor/thisav.py index 7f323c9..4473a3c 100644 --- a/youtube_dl/extractor/thisav.py +++ b/youtube_dl/extractor/thisav.py @@ -3,13 +3,13 @@ from __future__ import unicode_literals import re -from .common import InfoExtractor -from ..utils import determine_ext +from .jwplatform import JWPlatformBaseIE +from ..utils import remove_end -class ThisAVIE(InfoExtractor): +class ThisAVIE(JWPlatformBaseIE): _VALID_URL = r'https?://(?:www\.)?thisav\.com/video/(?P[0-9]+)/.*' - _TEST = { + _TESTS = [{ 'url': 'http://www.thisav.com/video/47734/%98%26sup1%3B%83%9E%83%82---just-fit.html', 'md5': '0480f1ef3932d901f0e0e719f188f19b', 'info_dict': { @@ -19,29 +19,49 @@ class ThisAVIE(InfoExtractor): 'uploader': 'dj7970', 'uploader_id': 'dj7970' } - } + }, { + '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, '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, 'video url') + r"addVariable\('file','([^']+)'\);", webpage, 'video url', default=None) + if video_url: + info_dict = { + 'formats': [{ + 'url': video_url, + }], + } + else: + info_dict = self._extract_jwplayer_data( + webpage, video_id, require_title=False) uploader = self._html_search_regex( r': ([^<]+)', webpage, 'uploader name', fatal=False) uploader_id = self._html_search_regex( r': (?:[^<]+)', webpage, 'uploader id', fatal=False) - ext = determine_ext(video_url) - return { + info_dict.update({ 'id': video_id, - 'url': video_url, 'uploader': uploader, 'uploader_id': uploader_id, 'title': title, - 'ext': ext, - } + }) + + return info_dict