[heise] Add support for YouTube embeds
authorkayb94 <30302445+kayb94@users.noreply.github.com>
Sun, 17 Sep 2017 15:46:52 +0000 (15:46 +0000)
committerSergey M <dstftw@gmail.com>
Sun, 17 Sep 2017 15:46:52 +0000 (22:46 +0700)
youtube_dl/extractor/heise.py

index 382f32771db513fc1c41e81f14ce42308ad50276..495ffb7dcfa19fea73c6f213d5aa8f54969cc683 100644 (file)
@@ -2,6 +2,7 @@
 from __future__ import unicode_literals
 
 from .common import InfoExtractor
+from .youtube import YoutubeIE
 from ..utils import (
     determine_ext,
     int_or_none,
@@ -25,6 +26,22 @@ class HeiseIE(InfoExtractor):
             'description': 'md5:c934cbfb326c669c2bcabcbe3d3fcd20',
             'thumbnail': r're:^https?://.*/gallery/$',
         }
+    }, {
+        # YouTube embed
+        'url': 'http://www.heise.de/newsticker/meldung/Netflix-In-20-Jahren-vom-Videoverleih-zum-TV-Revolutionaer-3814130.html',
+        'md5': 'e403d2b43fea8e405e88e3f8623909f1',
+        'info_dict': {
+            'id': '6kmWbXleKW4',
+            'ext': 'mp4',
+            'title': 'NEU IM SEPTEMBER | Netflix',
+            'description': 'md5:2131f3c7525e540d5fd841de938bd452',
+            'upload_date': '20170830',
+            'uploader': 'Netflix Deutschland, Ã–sterreich und Schweiz',
+            'uploader_id': 'netflixdach',
+        },
+        'params': {
+            'skip_download': True,
+        },
     }, {
         'url': 'http://www.heise.de/ct/artikel/c-t-uplink-3-3-Owncloud-Tastaturen-Peilsender-Smartphone-2403911.html',
         'only_matching': True,
@@ -40,6 +57,16 @@ class HeiseIE(InfoExtractor):
         video_id = self._match_id(url)
         webpage = self._download_webpage(url, video_id)
 
+        title = self._html_search_meta('fulltitle', webpage, default=None)
+        if not title or title == "c't":
+            title = self._search_regex(
+                    r'<div[^>]+class="videoplayerjw"[^>]+data-title="([^"]+)"',
+                    webpage, 'title')
+
+        yt_urls = YoutubeIE._extract_urls(webpage)
+        if yt_urls:
+            return self.playlist_from_matches(yt_urls, video_id, title, ie=YoutubeIE.ie_key())
+
         container_id = self._search_regex(
             r'<div class="videoplayerjw"[^>]+data-container="([0-9]+)"',
             webpage, 'container ID')
@@ -47,12 +74,6 @@ class HeiseIE(InfoExtractor):
             r'<div class="videoplayerjw"[^>]+data-sequenz="([0-9]+)"',
             webpage, 'sequenz ID')
 
-        title = self._html_search_meta('fulltitle', webpage, default=None)
-        if not title or title == "c't":
-            title = self._search_regex(
-                r'<div[^>]+class="videoplayerjw"[^>]+data-title="([^"]+)"',
-                webpage, 'title')
-
         doc = self._download_xml(
             'http://www.heise.de/videout/feed', video_id, query={
                 'container': container_id,