Use canonical URL in Vcs-Git.

[youtubedl] / youtube_dl / extractor / yourporn.py

diff --git a/youtube_dl/extractor/yourporn.py b/youtube_dl/extractor/yourporn.py
index c8dc29bd8a32cd7f50de601b94fe4ac77ff608bc..98347491ee00b66d2c2f8df69ddf663c1bffbd84 100644 (file)
--- a/youtube_dl/extractor/yourporn.py
+++ b/youtube_dl/extractor/yourporn.py
@@ -1,43 +1,67 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
 from __future__ import unicode_literals
 
 from .common import InfoExtractor

-from ..utils import urljoin
+from ..compat import compat_str
+from ..utils import (
+    parse_duration,
+    urljoin,
+)

 
 
 class YourPornIE(InfoExtractor):
 
 
 class YourPornIE(InfoExtractor):

-    _VALID_URL = r'https?://(?:www\.)?yourporn\.sexy/post/(?P<id>[^/?#&.]+)'
-    _TEST = {
-        'url': 'https://yourporn.sexy/post/57ffcb2e1179b.html',
+    _VALID_URL = r'https?://(?:www\.)?sxyprn\.com/post/(?P<id>[^/?#&.]+)'
+    _TESTS = [{
+        'url': 'https://sxyprn.com/post/57ffcb2e1179b.html',

         'md5': '6f8682b6464033d87acaa7a8ff0c092e',
         'info_dict': {
             'id': '57ffcb2e1179b',
             'ext': 'mp4',
             'title': 'md5:c9f43630bd968267672651ba905a7d35',
             'thumbnail': r're:^https?://.*\.jpg$',
         'md5': '6f8682b6464033d87acaa7a8ff0c092e',
         'info_dict': {
             'id': '57ffcb2e1179b',
             'ext': 'mp4',
             'title': 'md5:c9f43630bd968267672651ba905a7d35',
             'thumbnail': r're:^https?://.*\.jpg$',

-            'age_limit': 18
+            'duration': 165,
+            'age_limit': 18,

         },
         },

-    }
+        'params': {
+            'skip_download': True,
+        },
+    }, {
+        'url': 'https://sxyprn.com/post/57ffcb2e1179b.html',
+        'only_matching': True,
+    }]

 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
 
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         webpage = self._download_webpage(url, video_id)
 

-        video_url = urljoin(url, self._parse_json(
+        parts = self._parse_json(

             self._search_regex(
                 r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info',
                 group='data'),
             self._search_regex(
                 r'data-vnfo=(["\'])(?P<data>{.+?})\1', webpage, 'data info',
                 group='data'),

-            video_id)[video_id]).replace('/cdn/', '/cdn3/')
+            video_id)[video_id].split('/')
+
+        num = 0
+        for c in parts[6] + parts[7]:
+            if c.isnumeric():
+                num += int(c)
+        parts[5] = compat_str(int(parts[5]) - num)
+        parts[1] += '8'
+        video_url = urljoin(url, '/'.join(parts))

 
         title = (self._search_regex(
             r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title',
             default=None) or self._og_search_description(webpage)).strip()
         thumbnail = self._og_search_thumbnail(webpage)
 
         title = (self._search_regex(
             r'<[^>]+\bclass=["\']PostEditTA[^>]+>([^<]+)', webpage, 'title',
             default=None) or self._og_search_description(webpage)).strip()
         thumbnail = self._og_search_thumbnail(webpage)

+        duration = parse_duration(self._search_regex(
+            r'duration\s*:\s*<[^>]+>([\d:]+)', webpage, 'duration',
+            default=None))

 
         return {
             'id': video_id,
             'url': video_url,
             'title': title,
             'thumbnail': thumbnail,
 
         return {
             'id': video_id,
             'url': video_url,
             'title': title,
             'thumbnail': thumbnail,

-            'age_limit': 18
+            'duration': duration,
+            'age_limit': 18,
+            'ext': 'mp4',

         }
         }