X-Git-Url: http://git.bitcoin.ninja/index.cgi?a=blobdiff_plain;f=youtube_dl%2Fextractor%2Fvporn.py;h=858ac9e71422548f688600450e3f7cc0a630c500;hb=2f483bc1c389709623117079439708783122b5ec;hp=426369c51bb524b41c63b8377b6ce3f489d0d4b7;hpb=04b4aa4a7b5f3257923640fbba4f90efb2a195fc;p=youtube-dl

diff --git a/youtube_dl/extractor/vporn.py b/youtube_dl/extractor/vporn.py
index 426369c51..858ac9e71 100644
--- a/youtube_dl/extractor/vporn.py
+++ b/youtube_dl/extractor/vporn.py
@@ -4,29 +4,52 @@ import re
 
 from .common import InfoExtractor
 from ..utils import (
+    ExtractorError,
     parse_duration,
     str_to_int,
+    urljoin,
 )
 
 
 class VpornIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?vporn\.com/[^/]+/(?P<display_id>[^/]+)/(?P<id>\d+)'
-    _TEST = {
-        'url': 'http://www.vporn.com/masturbation/violet-on-her-th-birthday/497944/',
-        'md5': 'facf37c1b86546fa0208058546842c55',
-        'info_dict': {
-            'id': '497944',
-            'display_id': 'violet-on-her-th-birthday',
-            '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$',
-            'uploader': 'kileyGrope',
-            'categories': ['Masturbation', 'Teen'],
-            'duration': 393,
-            'age_limit': 18,
-        }
-    }
+    _TESTS = [
+        {
+            'url': 'http://www.vporn.com/masturbation/violet-on-her-th-birthday/497944/',
+            'md5': 'facf37c1b86546fa0208058546842c55',
+            'info_dict': {
+                'id': '497944',
+                'display_id': 'violet-on-her-th-birthday',
+                'ext': 'mp4',
+                'title': 'Violet on her 19th birthday',
+                'description': 'Violet dances in front of the camera which is sure to get you horny.',
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'uploader': 'kileyGrope',
+                'categories': ['Masturbation', 'Teen'],
+                'duration': 393,
+                'age_limit': 18,
+                'view_count': int,
+            },
+            'skip': 'video removed',
+        },
+        {
+            'url': 'http://www.vporn.com/female/hana-shower/523564/',
+            'md5': 'ced35a4656198a1664cf2cda1575a25f',
+            'info_dict': {
+                'id': '523564',
+                'display_id': 'hana-shower',
+                'ext': 'mp4',
+                'title': 'Hana Shower',
+                'description': 'Hana showers at the bathroom.',
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'uploader': 'Hmmmmm',
+                'categories': ['Big Boobs', 'Erotic', 'Teen', 'Female', '720p'],
+                'duration': 588,
+                'age_limit': 18,
+                'view_count': int,
+            }
+        },
+    ]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
@@ -35,36 +58,39 @@ 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'<div class="description_txt">(.*?)</div>', 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
+            r'class="(?:descr|description_txt)">(.*?)</div>',
+            webpage, 'description', fatal=False)
+        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.*?<a href="/user/[^"]+">([^<]+)</a>',
+            r'(?s)Uploaded by:.*?<a href="/user/[^"]+"[^>]*>(.+?)</a>',
             webpage, 'uploader', fatal=False)
 
-        categories = re.findall(r'<a href="/cat/[^"]+">([^<]+)</a>', webpage)
+        categories = re.findall(r'<a href="/cat/[^"]+"[^>]*>([^<]+)</a>', 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'<span>([\d,\.]+) VIEWS</span>', webpage, 'view count', fatal=False))
-        like_count = str_to_int(self._html_search_regex(
-            r'<span id="like" class="n">([\d,\.]+)</span>', webpage, 'like count', fatal=False))
-        dislike_count = str_to_int(self._html_search_regex(
-            r'<span id="dislike" class="n">([\d,\.]+)</span>', webpage, 'dislike count', fatal=False))
+            r'Runtime:\s*</span>\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'<h4>Comments \(<b>([\d,\.]+)</b>\)</h4>', webpage, 'comment count', fatal=False))
+            r"'Comments \(([\d,\.]+)\)'",
+            webpage, 'comment count', default=None))
 
         formats = []
 
-        for video in re.findall(r'flashvars\.videoUrl([^=]+?)\s*=\s*"([^"]+)"', webpage):
+        for video in re.findall(r'flashvars\.videoUrl([^=]+?)\s*=\s*"(https?://[^"]+)"', webpage):
             video_url = video[1]
             fmt = {
                 'url': video_url,
@@ -91,8 +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,