Update upstream source from tag 'upstream/2020.05.08'

[youtubedl] / youtube_dl / extractor / youporn.py

diff --git a/youtube_dl/extractor/youporn.py b/youtube_dl/extractor/youporn.py
index 547adefeba00ffb58a7e4dbd4205fc935c7ff2be..e7fca22dec9a17b10ef76efcd43c4b9e0e4da208 100644 (file)
--- a/youtube_dl/extractor/youporn.py
+++ b/youtube_dl/extractor/youporn.py
@@ -3,19 +3,18 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
 from ..utils import (
     int_or_none,
-    sanitized_Request,
     str_to_int,
     unescapeHTML,
     unified_strdate,
+    url_or_none,
 )
 from ..aes import aes_decrypt_text
 
 
 class YouPornIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?youporn\.com/watch/(?P<id>\d+)/(?P<display_id>[^/?#&]+)'
+    _VALID_URL = r'https?://(?:www\.)?youporn\.com/(?:watch|embed)/(?P<id>\d+)(?:/(?P<display_id>[^/?#&]+))?'
     _TESTS = [{
         'url': 'http://www.youporn.com/watch/505835/sex-ed-is-it-safe-to-masturbate-daily/',
         'md5': '3744d24c50438cf5b6f6d59feb5055c2',
@@ -57,22 +56,32 @@ class YouPornIE(InfoExtractor):
         'params': {
             'skip_download': True,
         },
+    }, {
+        'url': 'https://www.youporn.com/embed/505835/sex-ed-is-it-safe-to-masturbate-daily/',
+        'only_matching': True,
+    }, {
+        'url': 'http://www.youporn.com/watch/505835',
+        'only_matching': True,
     }]
 
+    @staticmethod
+    def _extract_urls(webpage):
+        return re.findall(
+            r'<iframe[^>]+\bsrc=["\']((?:https?:)?//(?:www\.)?youporn\.com/embed/\d+)',
+            webpage)
+
     def _real_extract(self, url):
         mobj = re.match(self._VALID_URL, url)
         video_id = mobj.group('id')
-        display_id = mobj.group('display_id')
+        display_id = mobj.group('display_id') or video_id
 
-        request = sanitized_Request(url)
-        request.add_header('Cookie', 'age_verified=1')
-        webpage = self._download_webpage(request, display_id)
+        webpage = self._download_webpage(
+            'http://www.youporn.com/watch/%s' % video_id, display_id,
+            headers={'Cookie': 'age_verified=1'})
 
-        title = self._search_regex(
-            [r'(?:video_titles|videoTitle)\s*[:=]\s*(["\'])(?P<title>(?:(?!\1).)+)\1',
-             r'<h1[^>]+class=["\']heading\d?["\'][^>]*>(?P<title>[^<]+)<'],
-            webpage, 'title', group='title',
-            default=None) or self._og_search_title(
+        title = self._html_search_regex(
+            r'(?s)<div[^>]+class=["\']watchVideoTitle[^>]+>(.+?)</div>',
+            webpage, 'title', default=None) or self._og_search_title(
             webpage, default=None) or self._html_search_meta(
             'title', webpage, fatal=True)
 
@@ -88,8 +97,8 @@ class YouPornIE(InfoExtractor):
             for definition in definitions:
                 if not isinstance(definition, dict):
                     continue
-                video_url = definition.get('videoUrl')
-                if isinstance(video_url, compat_str) and video_url:
+                video_url = url_or_none(definition.get('videoUrl'))
+                if video_url:
                     links.append(video_url)
 
         # Fallback #1, this also contains extra low quality 180p format
@@ -134,7 +143,11 @@ class YouPornIE(InfoExtractor):
             formats.append(f)
         self._sort_formats(formats)
 
-        description = self._og_search_description(webpage, default=None)
+        description = self._html_search_regex(
+            r'(?s)<div[^>]+\bid=["\']description["\'][^>]*>(.+?)</div>',
+            webpage, 'description',
+            default=None) or 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')