[telegraaf] Add extractor (Closes #6492)
authorSergey M․ <dstftw@gmail.com>
Sun, 9 Aug 2015 13:11:23 +0000 (19:11 +0600)
committerSergey M․ <dstftw@gmail.com>
Sun, 9 Aug 2015 13:11:23 +0000 (19:11 +0600)
youtube_dl/extractor/__init__.py
youtube_dl/extractor/telegraaf.py [new file with mode: 0644]

index e38e77a278236a61654410837e2b64798f4b261d..dad3ec87f7621e17e1c8f7073be5f909fa8b54f1 100644 (file)
@@ -596,6 +596,7 @@ from .techtalks import TechTalksIE
 from .ted import TEDIE
 from .telebruxelles import TeleBruxellesIE
 from .telecinco import TelecincoIE
+from .telegraaf import TelegraafIE
 from .telemb import TeleMBIE
 from .teletask import TeleTaskIE
 from .tenplay import TenPlayIE
diff --git a/youtube_dl/extractor/telegraaf.py b/youtube_dl/extractor/telegraaf.py
new file mode 100644 (file)
index 0000000..6f8333c
--- /dev/null
@@ -0,0 +1,35 @@
+# coding: utf-8
+from __future__ import unicode_literals
+
+from .common import InfoExtractor
+from ..utils import remove_end
+
+
+class TelegraafIE(InfoExtractor):
+    _VALID_URL = r'https?://(?:www\.)?telegraaf\.nl/tv/(?:[^/]+/)+(?P<id>\d+)/[^/]+\.html'
+    _TEST = {
+        'url': 'http://www.telegraaf.nl/tv/nieuws/binnenland/24353229/__Tikibad_ontruimd_wegens_brand__.html',
+        'md5': '83245a9779bcc4a24454bfd53c65b6dc',
+        'info_dict': {
+            'id': '24353229',
+            'ext': 'mp4',
+            'title': 'Tikibad ontruimd wegens brand',
+            'description': 'md5:05ca046ff47b931f9b04855015e163a4',
+            'thumbnail': 're:^https?://.*\.jpg$',
+            'duration': 33,
+        },
+    }
+
+    def _real_extract(self, url):
+        playlist_id = self._match_id(url)
+
+        webpage = self._download_webpage(url, playlist_id)
+
+        playlist_url = self._search_regex(
+            r"iframe\.loadPlayer\('([^']+)'", webpage, 'player')
+
+        entries = self._extract_xspf_playlist(playlist_url, playlist_id)
+        title = remove_end(self._og_search_title(webpage), ' - VIDEO')
+        description = self._og_search_description(webpage)
+
+        return self.playlist_result(entries, playlist_id, title, description)