1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-09-03 08:35:32 +00:00

[extractors] Use new framework for existing embeds (#4307)

`Brightcove` is difficult to migrate because it's subclasses may depend
on the signature of the current functions. So it is left as-is for now

Note: Tests have not been migrated
This commit is contained in:
pukkandan
2022-08-01 06:53:25 +05:30
parent 1e8fe57e5c
commit bfd973ece3
138 changed files with 499 additions and 1909 deletions

View File

@ -13,7 +13,7 @@ from ..utils import (
str_or_none,
try_call,
try_get,
unescapeHTML,
smuggle_url,
unsmuggle_url,
url_or_none,
urljoin,
@ -25,6 +25,7 @@ _ID_RE = r'(?:[0-9a-f]{32,34}|[0-9a-f]{8}-[0-9a-f]{4}-[0-9a-f]{4}-[0-9a-f]{4}-[0
class MediasiteIE(InfoExtractor):
_VALID_URL = r'(?xi)https?://[^/]+/Mediasite/(?:Play|Showcase/[^/#?]+/Presentation)/(?P<id>%s)(?P<query>\?[^#]+|)' % _ID_RE
_EMBED_REGEX = [r'(?xi)<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:(?:https?:)?//[^/]+)?/Mediasite/Play/%s(?:\?.*?)?)\1' % _ID_RE]
_TESTS = [
{
'url': 'https://hitsmediaweb.h-its.org/mediasite/Play/2db6c271681e4f199af3c60d1f82869b1d',
@ -112,13 +113,10 @@ class MediasiteIE(InfoExtractor):
5: 'video3',
}
@staticmethod
def _extract_urls(webpage):
return [
unescapeHTML(mobj.group('url'))
for mobj in re.finditer(
r'(?xi)<iframe\b[^>]+\bsrc=(["\'])(?P<url>(?:(?:https?:)?//[^/]+)?/Mediasite/Play/%s(?:\?.*?)?)\1' % _ID_RE,
webpage)]
@classmethod
def _extract_embed_urls(cls, url, webpage):
for embed_url in super()._extract_embed_urls(url, webpage):
yield smuggle_url(embed_url, {'UrlReferrer': url})
def __extract_slides(self, *, stream_id, snum, Stream, duration, images):
slide_base_url = Stream['SlideBaseUrl']