X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvporn.py;h=1557a0e0406ebfb75c2b5b4583c74f05c5dd2cc7;hb=340e31ca7449197450e0a50c925cf9ebd95a76d4;hp=04ed0b38129feef337fb932934f0f3ada2b47501;hpb=cd298882cd6f8ed2571dd372f684ec17e992fd9d;p=youtube-dl diff --git a/youtube_dl/extractor/vporn.py b/youtube_dl/extractor/vporn.py index 04ed0b381..1557a0e04 100644 --- a/youtube_dl/extractor/vporn.py +++ b/youtube_dl/extractor/vporn.py @@ -4,6 +4,7 @@ import re from .common import InfoExtractor from ..utils import ( + ExtractorError, parse_duration, str_to_int, ) @@ -27,10 +28,8 @@ class VpornIE(InfoExtractor): 'duration': 393, 'age_limit': 18, 'view_count': int, - 'like_count': int, - 'dislike_count': int, - 'comment_count': int, - } + }, + 'skip': 'video removed', }, { 'url': 'http://www.vporn.com/female/hana-shower/523564/', @@ -43,13 +42,10 @@ class VpornIE(InfoExtractor): 'description': 'Hana showers at the bathroom.', 'thumbnail': 're:^https?://.*\.jpg$', 'uploader': 'Hmmmmm', - 'categories': ['Big Boobs', 'Erotic', 'Teen', 'Female'], + 'categories': ['Big Boobs', 'Erotic', 'Teen', 'Female', '720p'], 'duration': 588, 'age_limit': 18, 'view_count': int, - 'like_count': int, - 'dislike_count': int, - 'comment_count': int, } }, ] @@ -61,6 +57,10 @@ class VpornIE(InfoExtractor): webpage = self._download_webpage(url, display_id) + errmsg = 'This video has been deleted due to Copyright Infringement or by the account owner!' + if errmsg in webpage: + raise ExtractorError('%s said: %s' % (self.IE_NAME, errmsg), expected=True) + title = self._html_search_regex( r'videoname\s*=\s*\'([^\']+)\'', webpage, 'title').strip() description = self._html_search_regex( @@ -72,10 +72,10 @@ class VpornIE(InfoExtractor): thumbnail = 'http://www.vporn.com' + thumbnail uploader = self._html_search_regex( - r'(?s)Uploaded by:.*?([^<]+)', + r'(?s)Uploaded by:.*?]*>(.+?)', webpage, 'uploader', fatal=False) - categories = re.findall(r'([^<]+)', webpage) + categories = re.findall(r']*>([^<]+)', webpage) duration = parse_duration(self._search_regex( r'Runtime:\s*\s*(\d+ min \d+ sec)',