[ketnet] Add extractor (Closes #10343)

[youtube-dl] / youtube_dl / extractor / polskieradio.py

diff --git a/youtube_dl/extractor/polskieradio.py b/youtube_dl/extractor/polskieradio.py
index f5adff08ffd91bc01bffd57be3814e75415d553f..f559b899f44d216d0f59a5e282de0658cbf4af48 100644 (file)
--- a/youtube_dl/extractor/polskieradio.py
+++ b/youtube_dl/extractor/polskieradio.py
@@ -33,6 +33,7 @@ class PolskieRadioIE(InfoExtractor):
                 'timestamp': 1456594200,
                 'upload_date': '20160227',
                 'duration': 2364,
+                'thumbnail': 're:^https?://static\.prsa\.pl/images/.*\.jpg$'
             },
         }],
     }, {
@@ -49,6 +50,10 @@ class PolskieRadioIE(InfoExtractor):
     }, {
         'url': 'http://www.polskieradio.pl/7/5102/Artykul/1587943',
         'only_matching': True,
+    }, {
+        # with mp4 video
+        'url': 'http://www.polskieradio.pl/9/299/Artykul/1634903,Brexit-Leszek-Miller-swiat-sie-nie-zawali-Europa-bedzie-trwac-dalej',
+        'only_matching': True,
     }]
 
     def _real_extract(self, url):
@@ -64,6 +69,8 @@ class PolskieRadioIE(InfoExtractor):
             r'(?s)<span[^>]+id="datetime2"[^>]*>(.+?)</span>',
             webpage, 'timestamp', fatal=False))
 
+        thumbnail_url = self._og_search_thumbnail(webpage)
+
         entries = []
 
         media_urls = set()
@@ -83,6 +90,7 @@ class PolskieRadioIE(InfoExtractor):
                 'duration': int_or_none(media.get('length')),
                 'vcodec': 'none' if media.get('provider') == 'audio' else None,
                 'timestamp': timestamp,
+                'thumbnail': thumbnail_url
             })
 
         title = self._og_search_title(webpage).strip()