debian/control: Mark compliancy with policy 4.1.3 (no changes needed).

[youtubedl] / youtube_dl / extractor / infoq.py

diff --git a/youtube_dl/extractor/infoq.py b/youtube_dl/extractor/infoq.py
index 9fb71e8effe107c6e182c3537cd634b7ac21e9bb..c3e892feb1fd905b98f99b5670ee7c120b0b208d 100644 (file)
--- a/youtube_dl/extractor/infoq.py
+++ b/youtube_dl/extractor/infoq.py
@@ -8,7 +8,10 @@ from ..compat import (
     compat_urllib_parse_unquote,
     compat_urlparse,
 )
     compat_urllib_parse_unquote,
     compat_urlparse,
 )

-from ..utils import determine_ext
+from ..utils import (
+    determine_ext,
+    update_url_query,
+)

 from .bokecc import BokeCCBaseIE
 
 
 from .bokecc import BokeCCBaseIE
 
 


@@ -68,45 +71,44 @@ class InfoQIE(BokeCCBaseIE):
             'play_path': playpath,
         }]
 
             'play_path': playpath,
         }]
 

-    def _extract_cookies(self, webpage):
-        policy = self._search_regex(r'InfoQConstants.scp\s*=\s*\'([^\']+)\'', webpage, 'policy')
-        signature = self._search_regex(r'InfoQConstants.scs\s*=\s*\'([^\']+)\'', webpage, 'signature')
-        key_pair_id = self._search_regex(r'InfoQConstants.sck\s*=\s*\'([^\']+)\'', webpage, 'key-pair-id')
-        return 'CloudFront-Policy=%s; CloudFront-Signature=%s; CloudFront-Key-Pair-Id=%s' % (
-            policy, signature, key_pair_id)
+    def _extract_cf_auth(self, webpage):
+        policy = self._search_regex(r'InfoQConstants\.scp\s*=\s*\'([^\']+)\'', webpage, 'policy')
+        signature = self._search_regex(r'InfoQConstants\.scs\s*=\s*\'([^\']+)\'', webpage, 'signature')
+        key_pair_id = self._search_regex(r'InfoQConstants\.sck\s*=\s*\'([^\']+)\'', webpage, 'key-pair-id')
+        return {
+            'Policy': policy,
+            'Signature': signature,
+            'Key-Pair-Id': key_pair_id,
+        }

 
     def _extract_http_video(self, webpage):
         http_video_url = self._search_regex(r'P\.s\s*=\s*\'([^\']+)\'', webpage, 'video URL')
 
     def _extract_http_video(self, webpage):
         http_video_url = self._search_regex(r'P\.s\s*=\s*\'([^\']+)\'', webpage, 'video URL')

+        http_video_url = update_url_query(http_video_url, self._extract_cf_auth(webpage))

         return [{
             'format_id': 'http_video',
             'url': http_video_url,
         return [{
             'format_id': 'http_video',
             'url': http_video_url,

-            'http_headers': {
-                'Cookie': self._extract_cookies(webpage)
-            },

         }]
 
     def _extract_http_audio(self, webpage, video_id):
         fields = self._hidden_inputs(webpage)
         }]
 
     def _extract_http_audio(self, webpage, video_id):
         fields = self._hidden_inputs(webpage)

-        http_audio_url = fields['filename']
-        if http_audio_url is None:
+        http_audio_url = fields.get('filename')
+        if not http_audio_url:

             return []
 
             return []
 

-        cookies_header = {'Cookie': self._extract_cookies(webpage)}
-

         # base URL is found in the Location header in the response returned by
         # GET https://www.infoq.com/mp3download.action?filename=... when logged in.
         http_audio_url = compat_urlparse.urljoin('http://res.infoq.com/downloads/mp3downloads/', http_audio_url)
         # base URL is found in the Location header in the response returned by
         # GET https://www.infoq.com/mp3download.action?filename=... when logged in.
         http_audio_url = compat_urlparse.urljoin('http://res.infoq.com/downloads/mp3downloads/', http_audio_url)

+        http_audio_url = update_url_query(http_audio_url, self._extract_cf_auth(webpage))

 
         # audio file seem to be missing some times even if there is a download link
         # so probe URL to make sure
 
         # audio file seem to be missing some times even if there is a download link
         # so probe URL to make sure

-        if not self._is_valid_url(http_audio_url, video_id, headers=cookies_header):
+        if not self._is_valid_url(http_audio_url, video_id):

             return []
 
         return [{
             'format_id': 'http_audio',
             'url': http_audio_url,
             'vcodec': 'none',
             return []
 
         return [{
             'format_id': 'http_audio',
             'url': http_audio_url,
             'vcodec': 'none',

-            'http_headers': cookies_header,

         }]
 
     def _real_extract(self, url):
         }]
 
     def _real_extract(self, url):