Merge pull request #7045 from remitamine/ign

[youtube-dl] / youtube_dl / extractor / youporn.py

diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py
index d10ebb0bf93fda6f86c9ac3f272416e1ace1aef7..dd724085add2adbcacde458a23902cf07395382f 100644 (file)
--- a/youtube_dl/extractor/youporn.py
+++ b/youtube_dl/extractor/youporn.py
@@ -3,9 +3,9 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_urllib_request
 from ..utils import (
     int_or_none,
+    sanitized_Request,
     str_to_int,
     unescapeHTML,
     unified_strdate,
@@ -15,8 +15,9 @@ from ..aes import aes_decrypt_text
 
 class YouPornIE(InfoExtractor):
     _VALID_URL = r'https?://(?:www\.)?youporn\.com/watch/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
-    _TEST = {
+    _TESTS = [{
         'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
+        'md5': '71ec5fcfddacf80f495efa8b6a8d9a89',
         'info_dict': {
             'id': '505835',
             'display_id': 'sex-ed-is-it-safe-to-masturbate-daily',
@@ -28,18 +29,41 @@ class YouPornIE(InfoExtractor):
             'upload_date': '20101221',
             'average_rating': int,
             'view_count': int,
+            'comment_count': int,
             'categories': list,
             'tags': list,
             'age_limit': 18,
-        }
-    }
+        },
+    }, {
+        # Anonymous User uploader
+        'url': 'http://www.youporn.com/watch/561726/big-tits-awesome-brunette-on-amazing-webcam-show/?from=related3&al=2&from_id=561726&pos=4',
+        'info_dict': {
+            'id': '561726',
+            'display_id': 'big-tits-awesome-brunette-on-amazing-webcam-show',
+            'ext': 'mp4',
+            'title': 'Big Tits Awesome Brunette On amazing webcam show',
+            'description': 'http://sweetlivegirls.com Big Tits Awesome Brunette On amazing webcam show.mp4',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'uploader': 'Anonymous User',
+            'upload_date': '20111125',
+            'average_rating': int,
+            'view_count': int,
+            'comment_count': int,
+            'categories': list,
+            'tags': list,
+            'age_limit': 18,
+        },
+        'params': {
+            'skip_download': True,
+        },
+    }]
 
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
         display_id = mobj.group('display_id')
 
-        request = compat_urllib_request.Request(url)
+        request = sanitized_Request(url)
         request.add_header('Cookie', 'age_verified=1')
         webpage = self._download_webpage(request, display_id)
 
@@ -92,13 +116,13 @@ class YouPornIE(InfoExtractor):
 
         description = self._html_search_regex(
             r'(?s)<div[^>]+class=["\']video-description["\'][^>]*>(.+?)</div>',
-            webpage, 'description', fatal=False)
+            webpage, 'description', default=None)
         thumbnail = self._search_regex(
             r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
             webpage, 'thumbnail', fatal=False, group='thumbnail')
 
-        uploader = self._search_regex(
-            r'<div[^>]+class=["\']videoInfoBy["\'][^>]*>\s*By:\s*</div>\s*<a[^>]+href="[^"]*">([^<]+)</a>',
+        uploader = self._html_search_regex(
+            r'(?s)<div[^>]+class=["\']videoInfoBy["\'][^>]*>\s*By:\s*</div>(.+?)</(?:a|div)>',
             webpage, 'uploader', fatal=False)
         upload_date = unified_strdate(self._html_search_regex(
             r'(?s)<div[^>]+class=["\']videoInfoTime["\'][^>]*>(.+?)</div>',
@@ -113,6 +137,9 @@ class YouPornIE(InfoExtractor):
         view_count = str_to_int(self._search_regex(
             r'(?s)<div[^>]+class=["\']videoInfoViews["\'][^>]*>.*?([\d,.]+)\s*</div>',
             webpage, 'view count', fatal=False))
+        comment_count = str_to_int(self._search_regex(
+            r'>All [Cc]omments? \(([\d,.]+)\)',
+            webpage, 'comment count', fatal=False))
 
         def extract_tag_box(title):
             tag_box = self._search_regex(
@@ -136,6 +163,7 @@ class YouPornIE(InfoExtractor):
             'upload_date': upload_date,
             'average_rating': average_rating,
             'view_count': view_count,
+            'comment_count': comment_count,
             'categories': categories,
             'tags': tags,
             'age_limit': age_limit,