X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvporn.py;h=858ac9e71422548f688600450e3f7cc0a630c500;hb=e6e68069f6fe25fe4a2b72487be840ba2ec3c5c6;hp=04ed0b38129feef337fb932934f0f3ada2b47501;hpb=cd298882cd6f8ed2571dd372f684ec17e992fd9d;p=youtube-dl diff --git a/youtube_dl/extractor/vporn.py b/youtube_dl/extractor/vporn.py index 04ed0b381..858ac9e71 100644 --- a/youtube_dl/extractor/vporn.py +++ b/youtube_dl/extractor/vporn.py @@ -4,8 +4,10 @@ import re from .common import InfoExtractor from ..utils import ( + ExtractorError, parse_duration, str_to_int, + urljoin, ) @@ -21,16 +23,14 @@ class VpornIE(InfoExtractor): 'ext': 'mp4', 'title': 'Violet on her 19th birthday', 'description': 'Violet dances in front of the camera which is sure to get you horny.', - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', 'uploader': 'kileyGrope', 'categories': ['Masturbation', 'Teen'], '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/', @@ -41,15 +41,12 @@ class VpornIE(InfoExtractor): 'ext': 'mp4', 'title': 'Hana Shower', 'description': 'Hana showers at the bathroom.', - 'thumbnail': 're:^https?://.*\.jpg$', + 'thumbnail': r're:^https?://.*\.jpg$', '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, } }, ] @@ -61,21 +58,24 @@ 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( r'class="(?:descr|description_txt)">(.*?)', webpage, 'description', fatal=False) - thumbnail = self._html_search_regex( - r'flashvars\.imageUrl\s*=\s*"([^"]+)"', webpage, 'description', fatal=False, default=None) - if thumbnail: - thumbnail = 'http://www.vporn.com' + thumbnail + thumbnail = urljoin('http://www.vporn.com', self._html_search_regex( + r'flashvars\.imageUrl\s*=\s*"([^"]+)"', webpage, 'description', + default=None)) 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)',