X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvporn.py;h=1557a0e0406ebfb75c2b5b4583c74f05c5dd2cc7;hb=25291b979a7ff8dc7ab57729a724e7e372c65c4b;hp=2d23effccdff0ba49ff628ded1f72d044fe609d6;hpb=fc96eb4e2180d9a2371d84daa4305a5f34f12321;p=youtube-dl diff --git a/youtube_dl/extractor/vporn.py b/youtube_dl/extractor/vporn.py index 2d23effcc..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, } }, ] @@ -61,32 +57,36 @@ 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'
(.*?)
', webpage, 'description', fatal=False) + 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 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'duration (\d+ min \d+ sec)', webpage, 'duration', fatal=False)) - - view_count = str_to_int(self._html_search_regex( - r'([\d,\.]+) VIEWS', webpage, 'view count', fatal=False)) - like_count = str_to_int(self._html_search_regex( - r'([\d,\.]+)', webpage, 'like count', fatal=False)) - dislike_count = str_to_int(self._html_search_regex( - r'([\d,\.]+)', webpage, 'dislike count', fatal=False)) + r'Runtime:\s*\s*(\d+ min \d+ sec)', + webpage, 'duration', fatal=False)) + + view_count = str_to_int(self._search_regex( + r'class="views">([\d,\.]+) [Vv]iews<', + webpage, 'view count', fatal=False)) comment_count = str_to_int(self._html_search_regex( - r'

Comments \(([\d,\.]+)\)

', webpage, 'comment count', fatal=False)) + r"'Comments \(([\d,\.]+)\)'", + webpage, 'comment count', default=None)) formats = [] @@ -117,8 +117,6 @@ class VpornIE(InfoExtractor): 'categories': categories, 'duration': duration, 'view_count': view_count, - 'like_count': like_count, - 'dislike_count': dislike_count, 'comment_count': comment_count, 'age_limit': 18, 'formats': formats,