debian/copyright: use spaces rather than tabs to start continuation lines.

[youtubedl] / youtube_dl / extractor / radiojavan.py

diff --git a/youtube_dl/extractor/radiojavan.py b/youtube_dl/extractor/radiojavan.py
index 884c284206cb73303a6631695872ce79ecf7795e..3f74f0c01ffd570dcf996d9c004070d80d50731e 100644 (file)
--- a/youtube_dl/extractor/radiojavan.py
+++ b/youtube_dl/extractor/radiojavan.py
@@ -3,9 +3,12 @@ from __future__ import unicode_literals
 import re
 
 from .common import InfoExtractor
 import re
 
 from .common import InfoExtractor

-from ..utils import(
-    unified_strdate,
+from ..utils import (
+    parse_resolution,

     str_to_int,
     str_to_int,

+    unified_strdate,
+    urlencode_postdata,
+    urljoin,

 )
 
 
 )
 
 


@@ -18,7 +21,7 @@ class RadioJavanIE(InfoExtractor):
             'id': 'chaartaar-ashoobam',
             'ext': 'mp4',
             'title': 'Chaartaar - Ashoobam',
             'id': 'chaartaar-ashoobam',
             'ext': 'mp4',
             'title': 'Chaartaar - Ashoobam',

-            'thumbnail': 're:^https?://.*\.jpe?g$',
+            'thumbnail': r're:^https?://.*\.jpe?g$',

             'upload_date': '20150215',
             'view_count': int,
             'like_count': int,
             'upload_date': '20150215',
             'view_count': int,
             'like_count': int,


@@ -29,13 +32,26 @@ class RadioJavanIE(InfoExtractor):
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 

+        download_host = self._download_json(
+            'https://www.radiojavan.com/videos/video_host', video_id,
+            data=urlencode_postdata({'id': video_id}),
+            headers={
+                'Content-Type': 'application/x-www-form-urlencoded',
+                'Referer': url,
+            }).get('host', 'https://host1.rjmusicmedia.com')
+

         webpage = self._download_webpage(url, video_id)
 
         webpage = self._download_webpage(url, video_id)
 

-        formats = [{
-            'url': 'https://media.rdjavan.com/media/music_video/%s' % video_path,
-            'format_id': '%sp' % height,
-            'height': int(height),
-        } for height, video_path in re.findall(r"RJ\.video(\d+)p\s*=\s*'/?([^']+)'", webpage)]
+        formats = []
+        for format_id, _, video_path in re.findall(
+                r'RJ\.video(?P<format_id>\d+[pPkK])\s*=\s*(["\'])(?P<url>(?:(?!\2).)+)\2',
+                webpage):
+            f = parse_resolution(format_id)
+            f.update({
+                'url': urljoin(download_host, video_path),
+                'format_id': format_id,
+            })
+            formats.append(f)

         self._sort_formats(formats)
 
         title = self._og_search_title(webpage)
         self._sort_formats(formats)
 
         title = self._og_search_title(webpage)