Add query to password-protected test URLs

youtube_dl/extractor/vimeo.py

@@ -42,6 +42,19 @@ class VimeoBaseInfoExtractor(InfoExtractor):
     _LOGIN_REQUIRED = False
     _LOGIN_URL = 'https://vimeo.com/log_in'
 
+    @staticmethod
+    # none of the standard library or utils.py routines does this
+    # join a path to a URL, removing query, fragment, with 1 / between
+    def _join_url(url, path):
+        url = compat_urlparse.urlunsplit(compat_urlparse.urlsplit(url)[:3] + (None, None))
+        if path:
+            if url.endswith('/') and path.startswith('/'):
+                url = url[:-1]
+            elif not url.endswith('/') and not path.startswith('/'):
+                url += '/'
+            return url + path
+        return url
+
     def _login(self):
         username, password = self._get_login_info()
         if username is None:
@@ -64,7 +77,7 @@ class VimeoBaseInfoExtractor(InfoExtractor):
                 self._LOGIN_URL, None, 'Logging in',
                 data=urlencode_postdata(data), headers={
                     'Content-Type': 'application/x-www-form-urlencoded',
-                    'Referer': self._LOGIN_URL,
+                    'Referer': compat_urlparse.urldefrag(self._LOGIN_URL),
                 })
         except ExtractorError as e:
             if isinstance(e.cause, compat_HTTPError) and e.cause.code == 418:
@@ -87,7 +100,7 @@ class VimeoBaseInfoExtractor(InfoExtractor):
             url = url.replace('http://', 'https://')
         self._set_vimeo_cookie('vuid', vuid)
         return self._download_webpage(
-            url + '/password', video_id, 'Verifying the password',
+            self._join_url(url, '/password'), video_id, 'Verifying the password',
             'Wrong password', data=urlencode_postdata({
                 'password': password,
                 'token': token,
@@ -345,7 +358,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
             'expected_warnings': ['Unable to download JSON metadata'],
         },
         {
-            'url': 'http://vimeo.com/68375962',
+            'url': 'http://vimeo.com/68375962?loop=0',
             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
             'note': 'Video protected with password',
             'info_dict': {
@@ -479,7 +492,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
             'skip': 'this page is no longer available.',
         },
         {
-            'url': 'http://player.vimeo.com/video/68375962',
+            'url': 'http://player.vimeo.com/video/68375962?loop=0',
             'md5': 'aaf896bdb7ddd6476df50007a0ac0ae7',
             'info_dict': {
                 'id': '68375962',
@@ -567,7 +580,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
             'Content-Type': 'application/x-www-form-urlencoded',
         })
         checked = self._download_json(
-            url + '/check-password', video_id,
+            self._join_url(url, '/check-password'), video_id,
             'Verifying the password', data=data, headers=headers)
         if checked is False:
             raise ExtractorError('Wrong video password', expected=True)
@@ -613,7 +626,7 @@ class VimeoIE(VimeoBaseInfoExtractor):
         if 'http_headers' in data:
             headers.update(data['http_headers'])
         if 'Referer' not in headers:
-            headers['Referer'] = url
+            headers['Referer'] = compat_urlparse.urldefrag(url)
 
         mobj = re.match(self._VALID_URL, url).groupdict()
         video_id, unlisted_hash = mobj['id'], mobj.get('unlisted_hash')