aboutsummaryrefslogtreecommitdiff
path: root/youtube_dl/extractor
diff options
context:
space:
mode:
Diffstat (limited to 'youtube_dl/extractor')
-rw-r--r--youtube_dl/extractor/generic.py7
-rw-r--r--youtube_dl/extractor/mediaset.py8
2 files changed, 15 insertions, 0 deletions
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index dde65fa96..32f38c401 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -89,6 +89,7 @@ from .limelight import LimelightBaseIE
from .anvato import AnvatoIE
from .washingtonpost import WashingtonPostIE
from .wistia import WistiaIE
+from .mediaset import MediasetIE
class GenericIE(InfoExtractor):
@@ -2648,6 +2649,12 @@ class GenericIE(InfoExtractor):
return self.playlist_from_matches(
wapo_urls, video_id, video_title, ie=WashingtonPostIE.ie_key())
+ # Look for Mediaset embeds
+ mediaset_urls = MediasetIE._extract_urls(webpage)
+ if mediaset_urls:
+ return self.playlist_from_matches(
+ mediaset_urls, video_id, video_title, ie=MediasetIE.ie_key())
+
# Looking for http://schema.org/VideoObject
json_ld = self._search_json_ld(
webpage, video_id, default={}, expected_type='VideoObject')
diff --git a/youtube_dl/extractor/mediaset.py b/youtube_dl/extractor/mediaset.py
index 3ebc7f2e1..9a0e41663 100644
--- a/youtube_dl/extractor/mediaset.py
+++ b/youtube_dl/extractor/mediaset.py
@@ -59,6 +59,14 @@ class MediasetIE(InfoExtractor):
'only_matching': True,
}]
+ @staticmethod
+ def _extract_urls(webpage):
+ return [
+ mobj.group('url')
+ for mobj in re.finditer(
+ r'<iframe\b[^>]+\bsrc=(["\'])(?P<url>https?://(?:www\.)?video\.mediaset\.it/player/playerIFrame(?:Twitter)?\.shtml\?.*?\bid=\d+.*?)\1',
+ webpage)]
+
def _real_extract(self, url):
video_id = self._match_id(url)