[tv2dk] Add extractor
authorSergey M․ <dstftw@gmail.com>
Tue, 29 Oct 2019 19:21:03 +0000 (02:21 +0700)
committerSergey M․ <dstftw@gmail.com>
Tue, 29 Oct 2019 19:21:03 +0000 (02:21 +0700)
youtube_dl/extractor/extractors.py
youtube_dl/extractor/tv2dk.py [new file with mode: 0644]

index 15f96fb8f06ad2f6cfeee8fb1f290325c442e688..5d20ba8638f6cf12a6b6281c264b9e9ad9ca7ae6 100644 (file)
@@ -1189,6 +1189,7 @@ from .tv2 import (
     TV2IE,
     TV2ArticleIE,
 )
+from .tv2dk import TV2DKIE
 from .tv2hu import TV2HuIE
 from .tv4 import TV4IE
 from .tv5mondeplus import TV5MondePlusIE
diff --git a/youtube_dl/extractor/tv2dk.py b/youtube_dl/extractor/tv2dk.py
new file mode 100644 (file)
index 0000000..eb39424
--- /dev/null
@@ -0,0 +1,82 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+import re
+
+from .common import InfoExtractor
+from ..utils import extract_attributes
+
+
+class TV2DKIE(InfoExtractor):
+    _VALID_URL = r'''(?x)
+                    https?://
+                        (?:www\.)?
+                        (?:
+                            tvsyd|
+                            tv2ostjylland|
+                            tvmidtvest|
+                            tv2fyn|
+                            tv2east|
+                            tv2lorry|
+                            tv2nord
+                        )\.dk/
+                        (:[^/]+/)*
+                        (?P<id>[^/?\#&]+)
+                    '''
+    _TESTS = [{
+        'url': 'https://www.tvsyd.dk/nyheder/28-10-2019/1930/1930-28-okt-2019?autoplay=1#player',
+        'info_dict': {
+            'id': '0_52jmwa0p',
+            'ext': 'mp4',
+            'title': '19:30 - 28. okt. 2019',
+            'timestamp': 1572290248,
+            'upload_date': '20191028',
+            'uploader_id': 'tvsyd',
+            'duration': 1347,
+            'view_count': int,
+        },
+        'params': {
+            'skip_download': True,
+        },
+        'add_ie': ['Kaltura'],
+    }, {
+        'url': 'https://www.tv2ostjylland.dk/artikel/minister-gaar-ind-i-sag-om-diabetes-teknologi',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tv2ostjylland.dk/nyheder/28-10-2019/22/2200-nyhederne-mandag-d-28-oktober-2019?autoplay=1#player',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tvmidtvest.dk/nyheder/27-10-2019/1930/1930-27-okt-2019',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tv2fyn.dk/artikel/fyn-kan-faa-landets-foerste-fabrik-til-groent-jetbraendstof',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tv2east.dk/artikel/gods-faar-indleveret-tonsvis-af-aebler-100-kilo-aebler-gaar-til-en-aeblebrandy',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tv2lorry.dk/koebenhavn/rasmus-paludan-evakueret-til-egen-demonstration#player',
+        'only_matching': True,
+    }, {
+        'url': 'https://www.tv2nord.dk/artikel/dybt-uacceptabelt',
+        'only_matching': True,
+    }]
+
+    def _real_extract(self, url):
+        video_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, video_id)
+
+        entries = []
+        for video_el in re.findall(r'(?s)<[^>]+\bdata-entryid\s*=[^>]*>', webpage):
+            video = extract_attributes(video_el)
+            kaltura_id = video.get('data-entryid')
+            if not kaltura_id:
+                continue
+            partner_id = video.get('data-partnerid')
+            if not partner_id:
+                continue
+            entries.append(self.url_result(
+                'kaltura:%s:%s' % (partner_id, kaltura_id), 'Kaltura',
+                video_id=kaltura_id))
+        return self.playlist_result(entries)