[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

@@ -1,5 +1,3 @@
import re
from .common import InfoExtractor
from ..compat import (
compat_str,
@@ -10,8 +8,6 @@ from ..utils import (
parse_iso8601,
strip_or_none,
try_get,
unescapeHTML,
urljoin,
)
@@ -55,6 +51,7 @@ class KinjaEmbedIE(InfoExtractor):
vine|
youtube-(?:list|video)
)-(?P<id>[^&]+)''' % (_DOMAIN_REGEX, _COMMON_REGEX)
_EMBED_REGEX = [rf'(?x)<iframe[^>]+?src=(?P<q>["\'])(?P<url>(?:(?:https?:)?//{_DOMAIN_REGEX})?{_COMMON_REGEX}(?:(?!\1).)+)\1']
_TESTS = [{
'url': 'https://kinja.com/ajax/inset/iframe?id=fb-10103303356633621',
'only_matching': True,
@@ -119,12 +116,6 @@ class KinjaEmbedIE(InfoExtractor):
'youtube-video': ('youtube.com/embed/', 'Youtube'),
}
@staticmethod
def _extract_urls(webpage, url):
return [urljoin(url, unescapeHTML(mobj.group('url'))) for mobj in re.finditer(
r'(?x)<iframe[^>]+?src=(?P<q>["\'])(?P<url>(?:(?:https?:)?//%s)?%s(?:(?!\1).)+)\1' % (KinjaEmbedIE._DOMAIN_REGEX, KinjaEmbedIE._COMMON_REGEX),
webpage)]
def _real_extract(self, url):
video_type, video_id = self._match_valid_url(url).groups()