Merge pull request #8092 from bpfoley/twitter-thumbnail

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

diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py
index b39fbb5fc7259b0b59a53c993ac174b8f238befb..1124fe6c280cb0e23bee3a41ea323165ec714dce 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,
@@ -29,6 +29,7 @@ class YouPornIE(InfoExtractor):
             'upload_date': '20101221',
             'average_rating': int,
             'view_count': int,
+            'comment_count': int,
             'categories': list,
             'tags': list,
             'age_limit': 18,
@@ -47,6 +48,7 @@ class YouPornIE(InfoExtractor):
             'upload_date': '20111125',
             'average_rating': int,
             'view_count': int,
+            'comment_count': int,
             'categories': list,
             'tags': list,
             'age_limit': 18,
@@ -61,7 +63,7 @@ class YouPornIE(InfoExtractor):
         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)
 
@@ -73,7 +75,7 @@ class YouPornIE(InfoExtractor):
         links = []
 
         sources = self._search_regex(
-            r'sources\s*:\s*({.+?})', webpage, 'sources', default=None)
+            r'(?s)sources\s*:\s*({.+?})', webpage, 'sources', default=None)
         if sources:
             for _, link in re.findall(r'[^:]+\s*:\s*(["\'])(http.+?)\1', sources):
                 links.append(link)
@@ -99,8 +101,9 @@ class YouPornIE(InfoExtractor):
             }
             # Video URL's path looks like this:
             #  /201012/17/505835/720p_1500k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
+            #  /201012/17/505835/vl_240p_240k_505835/YouPorn%20-%20Sex%20Ed%20Is%20It%20Safe%20To%20Masturbate%20Daily.mp4
             # We will benefit from it by extracting some metadata
-            mobj = re.search(r'/(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+/', video_url)
+            mobj = re.search(r'(?P<height>\d{3,4})[pP]_(?P<bitrate>\d+)[kK]_\d+/', video_url)
             if mobj:
                 height = int(mobj.group('height'))
                 bitrate = int(mobj.group('bitrate'))
@@ -112,15 +115,13 @@ class YouPornIE(InfoExtractor):
             formats.append(f)
         self._sort_formats(formats)
 
-        description = self._html_search_regex(
-            r'(?s)<div[^>]+class=["\']video-description["\'][^>]*>(.+?)</div>',
-            webpage, 'description', default=None)
+        description = self._og_search_description(webpage, default=None)
         thumbnail = self._search_regex(
             r'(?:imageurl\s*=|poster\s*:)\s*(["\'])(?P<thumbnail>.+?)\1',
             webpage, 'thumbnail', fatal=False, group='thumbnail')
 
         uploader = self._html_search_regex(
-            r'(?s)<div[^>]+class=["\']videoInfoBy["\'][^>]*>\s*By:\s*</div>(.+?)</(?:a|div)>',
+            r'(?s)<div[^>]+class=["\']videoInfoBy(?:\s+[^"\']+)?["\'][^>]*>\s*By:\s*</div>(.+?)</(?:a|div)>',
             webpage, 'uploader', fatal=False)
         upload_date = unified_strdate(self._html_search_regex(
             r'(?s)<div[^>]+class=["\']videoInfoTime["\'][^>]*>(.+?)</div>',
@@ -135,6 +136,9 @@ 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(
@@ -158,6 +162,7 @@ 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,