[KommunetvIE] Add extractor for kommunetv.no (#31516)

* Add extractor for kommunetv.no
* Using utils.update_url instead of regex

---------

Co-authored-by: dirkf <fieldhouse@gmx.net>

diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py
index f63a2e030ccdcfb83ceb7260830292b2d76abf1e..d8428f46fb70bb49cfb049eb4b93f6b15a7c65ea 100644 (file)
--- a/youtube_dl/extractor/extractors.py
+++ b/youtube_dl/extractor/extractors.py
@@ -557,6 +557,7 @@ from .khanacademy import (
 from .kickstarter import KickStarterIE
 from .kinja import KinjaEmbedIE
 from .kinopoisk import KinoPoiskIE
+from .kommunetv import KommunetvIE
 from .konserthusetplay import KonserthusetPlayIE
 from .krasview import KrasViewIE
 from .kth import KTHIE

diff --git a/youtube_dl/extractor/kommunetv.py b/youtube_dl/extractor/kommunetv.py
new file mode 100644 (file)
index 0000000..91d06a7
--- /dev/null
+++ b/youtube_dl/extractor/kommunetv.py
@@ -0,0 +1,35 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import update_url
+
+
+class KommunetvIE(InfoExtractor):
+    _VALID_URL = r'https://(\w+).kommunetv.no/archive/(?P<id>\w+)'
+    _TEST = {
+        'url': 'https://oslo.kommunetv.no/archive/921',
+        'md5': '5f102be308ee759be1e12b63d5da4bbc',
+        'info_dict': {
+            'id': '921',
+            'title': 'Bystyremøte',
+            'ext': 'mp4'
+        }
+    }
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+        headers = {
+            'Accept': 'application/json'
+        }
+        data = self._download_json('https://oslo.kommunetv.no/api/streams?streamType=1&id=%s' % video_id, video_id, headers=headers)
+        title = data['stream']['title']
+        file = data['playlist'][0]['playlist'][0]['file']
+        url = update_url(file, query=None, fragment=None)
+        formats = self._extract_m3u8_formats(url, video_id, ext='mp4', entry_protocol='m3u8_native', m3u8_id='hls', fatal=False)
+        self._sort_formats(formats)
+        return {
+            'id': video_id,
+            'formats': formats,
+            'title': title
+        }