Merge branch 'master' into KeezMovies-issue-16134

youtube_dl/extractor/cbc.py

@@ -5,7 +5,10 @@ import json
 import re
 
 from .common import InfoExtractor
-from ..compat import compat_str
+from ..compat import (
+    compat_str,
+    compat_HTTPError,
+)
 from ..utils import (
     js_to_json,
     smuggle_url,
@@ -206,30 +209,48 @@ class CBCWatchBaseIE(InfoExtractor):
 
     def _call_api(self, path, video_id):
         url = path if path.startswith('http') else self._API_BASE_URL + path
-        result = self._download_xml(url, video_id, headers={
+        for _ in range(2):
-            'X-Clearleap-DeviceId': self._device_id,
+            try:
-            'X-Clearleap-DeviceToken': self._device_token,
+                result = self._download_xml(url, video_id, headers={
-        })
+                    'X-Clearleap-DeviceId': self._device_id,
+                    'X-Clearleap-DeviceToken': self._device_token,
+                })
+            except ExtractorError as e:
+                if isinstance(e.cause, compat_HTTPError) and e.cause.code == 401:
+                    # Device token has expired, re-acquiring device token
+                    self._register_device()
+                    continue
+                raise
         error_message = xpath_text(result, 'userMessage') or xpath_text(result, 'systemMessage')
         if error_message:
             raise ExtractorError('%s said: %s' % (self.IE_NAME, error_message))
         return result
 
     def _real_initialize(self):
-        if not self._device_id or not self._device_token:
+        if self._valid_device_token():
-            device = self._downloader.cache.load('cbcwatch', 'device') or {}
+            return
-            self._device_id, self._device_token = device.get('id'), device.get('token')
+        device = self._downloader.cache.load('cbcwatch', 'device') or {}
-            if not self._device_id or not self._device_token:
+        self._device_id, self._device_token = device.get('id'), device.get('token')
-                result = self._download_xml(
+        if self._valid_device_token():
-                    self._API_BASE_URL + 'device/register',
+            return
-                    None, data=b'<device><type>web</type></device>')
+        self._register_device()
-                self._device_id = xpath_text(result, 'deviceId', fatal=True)
+
-                self._device_token = xpath_text(result, 'deviceToken', fatal=True)
+    def _valid_device_token(self):
-                self._downloader.cache.store(
+        return self._device_id and self._device_token
-                    'cbcwatch', 'device', {
+
-                        'id': self._device_id,
+    def _register_device(self):
-                        'token': self._device_token,
+        self._device_id = self._device_token = None
-                    })
+        result = self._download_xml(
+            self._API_BASE_URL + 'device/register',
+            None, 'Acquiring device token',
+            data=b'<device><type>web</type></device>')
+        self._device_id = xpath_text(result, 'deviceId', fatal=True)
+        self._device_token = xpath_text(result, 'deviceToken', fatal=True)
+        self._downloader.cache.store(
+            'cbcwatch', 'device', {
+                'id': self._device_id,
+                'token': self._device_token,
+            })
 
     def _parse_rss_feed(self, rss):
         channel = xpath_element(rss, 'channel', fatal=True)

youtube_dl/extractor/fxnetworks.py

@@ -41,7 +41,7 @@ class FXNetworksIE(AdobePassIE):
         if 'The content you are trying to access is not available in your region.' in webpage:
             self.raise_geo_restricted()
         video_data = extract_attributes(self._search_regex(
-            r'(<a.+?rel="http://link\.theplatform\.com/s/.+?</a>)', webpage, 'video data'))
+            r'(<a.+?rel="https?://link\.theplatform\.com/s/.+?</a>)', webpage, 'video data'))
         player_type = self._search_regex(r'playerType\s*=\s*[\'"]([^\'"]+)', webpage, 'player type', default=None)
         release_url = video_data['rel']
         title = video_data['data-title']

youtube_dl/extractor/pornhub.py

@@ -33,7 +33,7 @@ class PornHubIE(InfoExtractor):
     _VALID_URL = r'''(?x)
                     https?://
                         (?:
-                            (?:[a-z]+\.)?pornhub\.com/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
+                            (?:[^/]+\.)?pornhub\.com/(?:(?:view_video\.php|video/show)\?viewkey=|embed/)|
                             (?:www\.)?thumbzilla\.com/video/
                         )
                         (?P<id>[\da-z]+)
@@ -264,7 +264,7 @@ class PornHubPlaylistBaseIE(InfoExtractor):
 
 
 class PornHubPlaylistIE(PornHubPlaylistBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?pornhub\.com/playlist/(?P<id>\d+)'
+    _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/playlist/(?P<id>\d+)'
     _TESTS = [{
         'url': 'http://www.pornhub.com/playlist/4667351',
         'info_dict': {
@@ -272,11 +272,14 @@ class PornHubPlaylistIE(PornHubPlaylistBaseIE):
             'title': 'Nataly Hot',
         },
         'playlist_mincount': 2,
+    }, {
+        'url': 'https://de.pornhub.com/playlist/4667351',
+        'only_matching': True,
     }]
 
 
 class PornHubUserVideosIE(PornHubPlaylistBaseIE):
-    _VALID_URL = r'https?://(?:www\.)?pornhub\.com/(?:user|channel)s/(?P<id>[^/]+)/videos'
+    _VALID_URL = r'https?://(?:[^/]+\.)?pornhub\.com/(?:user|channel)s/(?P<id>[^/]+)/videos'
     _TESTS = [{
         'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
         'info_dict': {
@@ -305,6 +308,9 @@ class PornHubUserVideosIE(PornHubPlaylistBaseIE):
         # Most Viewed Videos
         'url': 'https://www.pornhub.com/channels/povd/videos?o=vi',
         'only_matching': True,
+    }, {
+        'url': 'http://www.pornhub.com/users/zoe_ph/videos/public',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):