New upstream version 2019.09.01

[youtubedl] / youtube_dl / extractor / ruutu.py

diff --git a/youtube_dl/extractor/ruutu.py b/youtube_dl/extractor/ruutu.py
index 9fa8688f838c902de682ed69e1caedc93ed5f4bc..f984040aa07b08f56b1028d0dde1dc3fc78137cb 100644 (file)
--- a/youtube_dl/extractor/ruutu.py
+++ b/youtube_dl/extractor/ruutu.py
@@ -59,13 +59,28 @@ class RuutuIE(InfoExtractor):
             'url': 'http://www.ruutu.fi/video/3193728',
             'only_matching': True,
         },
             'url': 'http://www.ruutu.fi/video/3193728',
             'only_matching': True,
         },

+        {
+            # audio podcast
+            'url': 'https://www.supla.fi/supla/3382410',
+            'md5': 'b9d7155fed37b2ebf6021d74c4b8e908',
+            'info_dict': {
+                'id': '3382410',
+                'ext': 'mp3',
+                'title': 'Mikä ihmeen poltergeist?',
+                'description': 'md5:bbb6963df17dfd0ecd9eb9a61bf14b52',
+                'thumbnail': r're:^https?://.*\.jpg$',
+                'age_limit': 0,
+            },
+            'expected_warnings': ['HTTP Error 502: Bad Gateway'],
+        }

     ]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         video_xml = self._download_xml(
     ]
 
     def _real_extract(self, url):
         video_id = self._match_id(url)
 
         video_xml = self._download_xml(

-            'http://gatling.ruutu.fi/media-xml-cache?id=%s' % video_id, video_id)
+            'https://gatling.nelonenmedia.fi/media-xml-cache', video_id,
+            query={'id': video_id})

 
         formats = []
         processed_urls = []
 
         formats = []
         processed_urls = []


@@ -76,8 +91,8 @@ class RuutuIE(InfoExtractor):
                     extract_formats(child)
                 elif child.tag.endswith('File'):
                     video_url = child.text
                     extract_formats(child)
                 elif child.tag.endswith('File'):
                     video_url = child.text

-                    if (not video_url or video_url in processed_urls or
-                            any(p in video_url for p in ('NOT_USED', 'NOT-USED'))):
+                    if (not video_url or video_url in processed_urls
+                            or any(p in video_url for p in ('NOT_USED', 'NOT-USED'))):

                         continue
                     processed_urls.append(video_url)
                     ext = determine_ext(video_url)
                         continue
                     processed_urls.append(video_url)
                     ext = determine_ext(video_url)


@@ -93,6 +108,12 @@ class RuutuIE(InfoExtractor):
                         continue
                         formats.extend(self._extract_mpd_formats(
                             video_url, video_id, mpd_id='dash', fatal=False))
                         continue
                         formats.extend(self._extract_mpd_formats(
                             video_url, video_id, mpd_id='dash', fatal=False))

+                    elif ext == 'mp3' or child.tag == 'AudioMediaFile':
+                        formats.append({
+                            'format_id': 'audio',
+                            'url': video_url,
+                            'vcodec': 'none',
+                        })

                     else:
                         proto = compat_urllib_parse_urlparse(video_url).scheme
                         if not child.tag.startswith('HTTP') and proto != 'rtmp':
                     else:
                         proto = compat_urllib_parse_urlparse(video_url).scheme
                         if not child.tag.startswith('HTTP') and proto != 'rtmp':