Merge branch 'lecture2go' of https://github.com/nichdu/youtube-dl into nichdu-lecture2go
[youtube-dl] / youtube_dl / extractor / played.py
index a396e62e50d64c977b96d796da6d22f006f0316f..8a1c296dda8b57611a0e464387be43ab0fc9a370 100644 (file)
@@ -2,19 +2,21 @@
 from __future__ import unicode_literals
 
 import re
-import time
 import os.path
 
 from .common import InfoExtractor
-from ..utils import (
+from ..compat import (
     compat_urllib_parse,
     compat_urllib_request,
 )
+from ..utils import (
+    ExtractorError,
+)
 
 
 class PlayedIE(InfoExtractor):
     IE_NAME = 'played.to'
-    _VALID_URL = r'https?://played\.to/(?P<id>[a-zA-Z0-9_-]+)'
+    _VALID_URL = r'https?://(?:www\.)?played\.to/(?P<id>[a-zA-Z0-9_-]+)'
 
     _TEST = {
         'url': 'http://played.to/j2f2sfiiukgt',
@@ -24,18 +26,21 @@ class PlayedIE(InfoExtractor):
             'ext': 'flv',
             'title': 'youtube-dl_test_video.mp4',
         },
+        'skip': 'Removed for copyright infringement.',  # oh wow
     }
 
     def _real_extract(self, url):
-        mobj = re.match(self._VALID_URL, url)
-        video_id = mobj.group('id')
-
+        video_id = self._match_id(url)
         orig_webpage = self._download_webpage(url, video_id)
-        fields = re.findall(r'type="hidden" name="(.+?)"\s* value="?(.+?)">', orig_webpage)
-        data = dict(fields)
 
-        self.to_screen('%s: Waiting for timeout' % video_id)
-        time.sleep(2)
+        m_error = re.search(
+            r'(?s)Reason for deletion:.*?<b class="err"[^>]*>(?P<msg>[^<]+)</b>', orig_webpage)
+        if m_error:
+            raise ExtractorError(m_error.group('msg'), expected=True)
+
+        data = self._hidden_inputs(orig_webpage)
+
+        self._sleep(2, video_id)
 
         post = compat_urllib_parse.urlencode(data)
         headers = {
@@ -54,4 +59,4 @@ class PlayedIE(InfoExtractor):
             'id': video_id,
             'title': title,
             'url': video_url,
-        }
\ No newline at end of file
+        }