From 562de77f41d0c08df9dbb08cfa86ba6c7d239c5a Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Sergey=20M=E2=80=A4?= <dstftw@gmail.com>
Date: Sat, 6 Jun 2020 02:14:35 +0700
Subject: [PATCH] [kaltura] Add support for multiple embeds on a webpage
(closes #25523)
---
youtube_dl/extractor/generic.py | 18 +++++++++++++++---
youtube_dl/extractor/kaltura.py | 19 +++++++++++++------
2 files changed, 28 insertions(+), 9 deletions(-)
diff --git a/youtube_dl/extractor/generic.py b/youtube_dl/extractor/generic.py
index ce8252f6a..355067a50 100644
--- a/youtube_dl/extractor/generic.py
+++ b/youtube_dl/extractor/generic.py
@@ -1708,6 +1708,15 @@ class GenericIE(InfoExtractor):
},
'add_ie': ['Kaltura'],
},
+ {
+ # multiple kaltura embeds, nsfw
+ 'url': 'https://www.quartier-rouge.be/prive/femmes/kamila-avec-video-jaime-sadomie.html',
+ 'info_dict': {
+ 'id': 'kamila-avec-video-jaime-sadomie',
+ 'title': "Kamila avec vídeo “J'aime sadomie”",
+ },
+ 'playlist_count': 8,
+ },
{
# Non-standard Vimeo embed
'url': 'https://openclassrooms.com/courses/understanding-the-web',
@@ -2844,9 +2853,12 @@ def _real_extract(self, url):
return self.url_result(mobj.group('url'), 'Zapiks')
# Look for Kaltura embeds
- kaltura_url = KalturaIE._extract_url(webpage)
- if kaltura_url:
- return self.url_result(smuggle_url(kaltura_url, {'source_url': url}), KalturaIE.ie_key())
+ kaltura_urls = KalturaIE._extract_urls(webpage)
+ if kaltura_urls:
+ return self.playlist_from_matches(
+ kaltura_urls, video_id, video_title,
+ getter=lambda x: smuggle_url(x, {'source_url': url}),
+ ie=KalturaIE.ie_key())
# Look for EaglePlatform embeds
eagleplatform_url = EaglePlatformIE._extract_url(webpage)
diff --git a/youtube_dl/extractor/kaltura.py b/youtube_dl/extractor/kaltura.py
index 2d38b758b..49d13460d 100644
--- a/youtube_dl/extractor/kaltura.py
+++ b/youtube_dl/extractor/kaltura.py
@@ -113,9 +113,14 @@ class KalturaIE(InfoExtractor):
@staticmethod
def _extract_url(webpage):
+ urls = KalturaIE._extract_urls(webpage)
+ return urls[0] if urls else None
+
+ @staticmethod
+ def _extract_urls(webpage):
# Embed codes: https://knowledge.kaltura.com/embedding-kaltura-media-players-your-site
- mobj = (
- re.search(
+ finditer = (
+ re.finditer(
r"""(?xs)
kWidget\.(?:thumb)?[Ee]mbed\(
\{.*?
@@ -124,7 +129,7 @@ def _extract_url(webpage):
(?P<q3>['"])entry_?[Ii]d(?P=q3)\s*:\s*
(?P<q4>['"])(?P<id>(?:(?!(?P=q4)).)+)(?P=q4)(?:,|\s*\})
""", webpage)
- or re.search(
+ or re.finditer(
r'''(?xs)
(?P<q1>["'])
(?:https?:)?//cdnapi(?:sec)?\.kaltura\.com(?::\d+)?/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)(?:(?!(?P=q1)).)*
@@ -138,7 +143,7 @@ def _extract_url(webpage):
)
(?P<q3>["'])(?P<id>(?:(?!(?P=q3)).)+)(?P=q3)
''', webpage)
- or re.search(
+ or re.finditer(
r'''(?xs)
<(?:iframe[^>]+src|meta[^>]+\bcontent)=(?P<q1>["'])
(?:https?:)?//(?:(?:www|cdnapi(?:sec)?)\.)?kaltura\.com/(?:(?!(?P=q1)).)*\b(?:p|partner_id)/(?P<partner_id>\d+)
@@ -148,7 +153,8 @@ def _extract_url(webpage):
(?P=q1)
''', webpage)
)
- if mobj:
+ urls = []
+ for mobj in finditer:
embed_info = mobj.groupdict()
for k, v in embed_info.items():
if v:
@@ -160,7 +166,8 @@ def _extract_url(webpage):
webpage)
if service_mobj:
url = smuggle_url(url, {'service_url': service_mobj.group('id')})
- return url
+ urls.append(url)
+ return urls
def _kaltura_api_call(self, video_id, actions, service_url=None, *args, **kwargs):
params = actions[0]