summaryrefslogtreecommitdiffstats
path: root/yt_dlp/extractor/tvnoe.py
diff options
context:
space:
mode:
authorDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-15 16:49:24 +0000
committerDaniel Baumann <daniel.baumann@progress-linux.org>2024-04-15 16:49:24 +0000
commit2415e66f889f38503b73e8ebc5f43ca342390e5c (patch)
treeac48ab69d1d96bae3d83756134921e0d90593aa5 /yt_dlp/extractor/tvnoe.py
parentInitial commit. (diff)
downloadyt-dlp-2415e66f889f38503b73e8ebc5f43ca342390e5c.tar.xz
yt-dlp-2415e66f889f38503b73e8ebc5f43ca342390e5c.zip
Adding upstream version 2024.03.10.upstream/2024.03.10
Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>
Diffstat (limited to 'yt_dlp/extractor/tvnoe.py')
-rw-r--r--yt_dlp/extractor/tvnoe.py46
1 files changed, 46 insertions, 0 deletions
diff --git a/yt_dlp/extractor/tvnoe.py b/yt_dlp/extractor/tvnoe.py
new file mode 100644
index 0000000..917c46b
--- /dev/null
+++ b/yt_dlp/extractor/tvnoe.py
@@ -0,0 +1,46 @@
+from .common import InfoExtractor
+from ..utils import (
+ clean_html,
+ get_element_by_class,
+ js_to_json,
+)
+
+
+class TVNoeIE(InfoExtractor):
+ _WORKING = False
+ _VALID_URL = r'https?://(?:www\.)?tvnoe\.cz/video/(?P<id>[0-9]+)'
+ _TEST = {
+ 'url': 'http://www.tvnoe.cz/video/10362',
+ 'md5': 'aee983f279aab96ec45ab6e2abb3c2ca',
+ 'info_dict': {
+ 'id': '10362',
+ 'ext': 'mp4',
+ 'series': 'Noční univerzita',
+ 'title': 'prof. Tomáš Halík, Th.D. - Návrat náboženství a střet civilizací',
+ 'description': 'md5:f337bae384e1a531a52c55ebc50fff41',
+ }
+ }
+
+ def _real_extract(self, url):
+ video_id = self._match_id(url)
+ webpage = self._download_webpage(url, video_id)
+
+ iframe_url = self._search_regex(
+ r'<iframe[^>]+src="([^"]+)"', webpage, 'iframe URL')
+
+ ifs_page = self._download_webpage(iframe_url, video_id)
+ jwplayer_data = self._find_jwplayer_data(
+ ifs_page, video_id, transform_source=js_to_json)
+ info_dict = self._parse_jwplayer_data(
+ jwplayer_data, video_id, require_title=False, base_url=iframe_url)
+
+ info_dict.update({
+ 'id': video_id,
+ 'title': clean_html(get_element_by_class(
+ 'field-name-field-podnazev', webpage)),
+ 'description': clean_html(get_element_by_class(
+ 'field-name-body', webpage)),
+ 'series': clean_html(get_element_by_class('title', webpage))
+ })
+
+ return info_dict