瀏覽代碼

[rtvs] Add extractor (closes #9242, closes #15187)

Sergey M․ 7 年之前
父節點
當前提交
df58ecbeba
共有 2 個文件被更改,包括 48 次插入0 次删除
  1. 1 0
      youtube_dl/extractor/extractors.py
  2. 47 0
      youtube_dl/extractor/rtvs.py

+ 1 - 0
youtube_dl/extractor/extractors.py

@@ -900,6 +900,7 @@ from .rtp import RTPIE
 from .rts import RTSIE
 from .rts import RTSIE
 from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE
 from .rtve import RTVEALaCartaIE, RTVELiveIE, RTVEInfantilIE, RTVELiveIE, RTVETelevisionIE
 from .rtvnh import RTVNHIE
 from .rtvnh import RTVNHIE
+from .rtvs import RTVSIE
 from .rudo import RudoIE
 from .rudo import RudoIE
 from .ruhd import RUHDIE
 from .ruhd import RUHDIE
 from .ruleporn import RulePornIE
 from .ruleporn import RulePornIE

+ 47 - 0
youtube_dl/extractor/rtvs.py

@@ -0,0 +1,47 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+
+
+class RTVSIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?rtvs\.sk/(?:radio|televizia)/archiv/\d+/(?P<id>\d+)'
+    _TESTS = [{
+        # radio archive
+        'url': 'http://www.rtvs.sk/radio/archiv/11224/414872',
+        'md5': '134d5d6debdeddf8a5d761cbc9edacb8',
+        'info_dict': {
+            'id': '414872',
+            'ext': 'mp3',
+            'title': 'Ostrov pokladov 1 časť.mp3'
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }, {
+        # tv archive
+        'url': 'http://www.rtvs.sk/televizia/archiv/8249/63118',
+        'md5': '85e2c55cf988403b70cac24f5c086dc6',
+        'info_dict': {
+            'id': '63118',
+            'ext': 'mp4',
+            'title': 'Amaro Džives - Náš deň',
+            'description': 'Galavečer pri príležitosti Medzinárodného dňa Rómov.'
+        },
+        'params': {
+            'skip_download': True,
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        playlist_url = self._search_regex(
+            r'playlist["\']?\s*:\s*(["\'])(?P<url>(?:(?!\1).)+)\1', webpage,
+            'playlist url', group='url')
+
+        data = self._download_json(
+            playlist_url, video_id, 'Downloading playlist')[0]
+        return self._parse_jwplayer_data(data, video_id=video_id)