]> jfr.im git - yt-dlp.git/commitdiff
[extractor/volejtv] Add extractor (#5943)
authorHobbyistDev <redacted>
Wed, 4 Jan 2023 07:50:23 +0000 (16:50 +0900)
committerGitHub <redacted>
Wed, 4 Jan 2023 07:50:23 +0000 (13:20 +0530)
Authored by: HobbyistDev
Closes #5883

yt_dlp/extractor/_extractors.py
yt_dlp/extractor/volejtv.py [new file with mode: 0644]

index 83e732189c4b3510c95cb49f0da8d411d02cd828..f3707948f93ebb91a0897f21a2a8c10d051fd531 100644 (file)
     VoicyIE,
     VoicyChannelIE,
 )
+from .volejtv import VolejTVIE
 from .voot import (
     VootIE,
     VootSeriesIE,
diff --git a/yt_dlp/extractor/volejtv.py b/yt_dlp/extractor/volejtv.py
new file mode 100644 (file)
index 0000000..622d841
--- /dev/null
@@ -0,0 +1,40 @@
+from .common import InfoExtractor
+
+
+class VolejTVIE(InfoExtractor):
+    _VALID_URL = r'https?://volej\.tv/video/(?P<id>\d+)'
+    _TESTS = [{
+        'url': 'https://volej.tv/video/725742/',
+        'info_dict': {
+            'id': '725742',
+            'ext': 'mp4',
+            'description': 'Zápas VK Královo Pole vs VK Prostějov 10.12.2022 v 19:00 na Volej.TV',
+            'thumbnail': 'https://volej.tv/images/og/16/17186/og.png',
+            'title': 'VK Královo Pole vs VK Prostějov',
+        }
+    }, {
+        'url': 'https://volej.tv/video/725605/',
+        'info_dict': {
+            'id': '725605',
+            'ext': 'mp4',
+            'thumbnail': 'https://volej.tv/images/og/15/17185/og.png',
+            'title': 'VK Lvi Praha vs VK Euro Sitex Příbram',
+            'description': 'Zápas VK Lvi Praha vs VK Euro Sitex Příbram 11.12.2022 v 19:00 na Volej.TV',
+        }
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        webpage = self._download_webpage(url, video_id)
+        json_data = self._search_json(
+            r'<\s*!\[CDATA[^=]+=', webpage, 'CDATA', video_id)
+        formats, subtitle = self._extract_m3u8_formats_and_subtitles(
+            json_data['urls']['hls'], video_id)
+        return {
+            'id': video_id,
+            'title': self._html_search_meta(['og:title', 'twitter:title'], webpage),
+            'thumbnail': self._html_search_meta(['og:image', 'twitter:image'], webpage),
+            'description': self._html_search_meta(['description', 'og:description', 'twitter:description'], webpage),
+            'formats': formats,
+            'subtitles': subtitle,
+        }