youtube-dl

commit 40e146aa1e1a8fd57d3f84b0a541174f56fa5dba
parent f3f9cd9234aada1d677517e3042bd9312610081d
Author: Sergey M․ <dstftw@gmail.com>
Date:   Thu, 18 Feb 2016 22:29:17 +0600

[pornhub:user:videos] Add extractor (Closes #8548)

Diffstat:
M
youtube_dl/extractor/__init__.py
 | 
1
+
M
youtube_dl/extractor/pornhub.py
 | 
53
++++++++++++++++++++++++++++++++++++++---------------

2 files changed, 39 insertions(+), 15 deletions(-)
diff --git a/youtube_dl/extractor/__init__.py b/youtube_dl/extractor/__init__.py
@@ -555,6 +555,7 @@ from .pornhd import PornHdIE
 from .pornhub import (
     PornHubIE,
     PornHubPlaylistIE,
+    PornHubUserVideosIE,
 )
 from .pornotube import PornotubeIE
 from .pornovoisines import PornoVoisinesIE
diff --git a/youtube_dl/extractor/pornhub.py b/youtube_dl/extractor/pornhub.py
@@ -129,27 +129,20 @@ class PornHubIE(InfoExtractor):
         }
 
 
-class PornHubPlaylistIE(InfoExtractor):
-    _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P<id>\d+)'
-    _TESTS = [{
-        'url': 'http://www.pornhub.com/playlist/6201671',
-        'info_dict': {
-            'id': '6201671',
-            'title': 'P0p4',
-        },
-        'playlist_mincount': 35,
-    }]
+class PornHubPlaylistBaseIE(InfoExtractor):
+    def _extract_entries(self, webpage):
+        return [
+            self.url_result('http://www.pornhub.com/%s' % video_url, 'PornHub')
+            for video_url in set(re.findall(
+                r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"', webpage))
+        ]
 
     def _real_extract(self, url):
         playlist_id = self._match_id(url)
 
         webpage = self._download_webpage(url, playlist_id)
 
-        entries = [
-            self.url_result('http://www.pornhub.com/%s' % video_url, 'PornHub')
-            for video_url in set(re.findall(
-                r'href="/?(view_video\.php\?.*\bviewkey=[\da-z]+[^"]*)"', webpage))
-        ]
+        entries = self._extract_entries(webpage)
 
         playlist = self._parse_json(
             self._search_regex(
@@ -158,3 +151,33 @@ class PornHubPlaylistIE(InfoExtractor):
 
         return self.playlist_result(
             entries, playlist_id, playlist.get('title'), playlist.get('description'))
+
+
+class PornHubPlaylistIE(PornHubPlaylistBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'http://www.pornhub.com/playlist/6201671',
+        'info_dict': {
+            'id': '6201671',
+            'title': 'P0p4',
+        },
+        'playlist_mincount': 35,
+    }]
+
+
+class PornHubUserVideosIE(PornHubPlaylistBaseIE):
+    _VALID_URL = r'https?://(?:www\.)?pornhub\.com/users/(?P<id>[^/]+)/videos'
+    _TESTS = [{
+        'url': 'http://www.pornhub.com/users/rushandlia/videos',
+        'info_dict': {
+            'id': 'rushandlia',
+        },
+        'playlist_mincount': 13,
+    }]
+
+    def _real_extract(self, url):
+        user_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, user_id)
+
+        return self.playlist_result(self._extract_entries(webpage), user_id)