summaryrefslogtreecommitdiffstats
path: root/yt_dlp/extractor/gazeta.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/gazeta.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/gazeta.py')
-rw-r--r--yt_dlp/extractor/gazeta.py44
1 files changed, 44 insertions, 0 deletions
diff --git a/yt_dlp/extractor/gazeta.py b/yt_dlp/extractor/gazeta.py
new file mode 100644
index 0000000..8925b69
--- /dev/null
+++ b/yt_dlp/extractor/gazeta.py
@@ -0,0 +1,44 @@
+from .common import InfoExtractor
+
+
+class GazetaIE(InfoExtractor):
+ _WORKING = False
+ _VALID_URL = r'(?P<url>https?://(?:www\.)?gazeta\.ru/(?:[^/]+/)?video/(?:main/)*(?:\d{4}/\d{2}/\d{2}/)?(?P<id>[A-Za-z0-9-_.]+)\.s?html)'
+ _TESTS = [{
+ 'url': 'http://www.gazeta.ru/video/main/zadaite_vopros_vladislavu_yurevichu.shtml',
+ 'md5': 'd49c9bdc6e5a7888f27475dc215ee789',
+ 'info_dict': {
+ 'id': '205566',
+ 'ext': 'mp4',
+ 'title': '«70–80 процентов гражданских в Донецке на грани голода»',
+ 'description': 'md5:38617526050bd17b234728e7f9620a71',
+ 'thumbnail': r're:^https?://.*\.jpg',
+ },
+ 'skip': 'video not found',
+ }, {
+ 'url': 'http://www.gazeta.ru/lifestyle/video/2015/03/08/master-klass_krasivoi_byt._delaem_vesennii_makiyazh.shtml',
+ 'only_matching': True,
+ }, {
+ 'url': 'http://www.gazeta.ru/video/main/main/2015/06/22/platit_ili_ne_platit_po_isku_yukosa.shtml',
+ 'md5': '37f19f78355eb2f4256ee1688359f24c',
+ 'info_dict': {
+ 'id': '252048',
+ 'ext': 'mp4',
+ 'title': '"Если по иску ЮКОСа придется платить, это будет большой удар по бюджету"',
+ },
+ 'add_ie': ['EaglePlatform'],
+ }]
+
+ def _real_extract(self, url):
+ mobj = self._match_valid_url(url)
+
+ display_id = mobj.group('id')
+ embed_url = '%s?p=embed' % mobj.group('url')
+ embed_page = self._download_webpage(
+ embed_url, display_id, 'Downloading embed page')
+
+ video_id = self._search_regex(
+ r'<div[^>]*?class="eagleplayer"[^>]*?data-id="([^"]+)"', embed_page, 'video id')
+
+ return self.url_result(
+ 'eagleplatform:gazeta.media.eagleplatform.com:%s' % video_id, 'EaglePlatform')