1
0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-10-31 14:45:14 +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

@@ -1,5 +1,3 @@
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
@@ -12,6 +10,14 @@ from ..utils import (
class IndavideoEmbedIE(InfoExtractor):
_VALID_URL = r'https?://(?:(?:embed\.)?indavideo\.hu/player/video/|assets\.indavideo\.hu/swf/player\.swf\?.*\b(?:v(?:ID|id))=)(?P<id>[\da-f]+)'
# Some example URLs covered by generic extractor:
# http://indavideo.hu/video/Vicces_cica_1
# http://index.indavideo.hu/video/2015_0728_beregszasz
# http://auto.indavideo.hu/video/Sajat_utanfutoban_a_kis_tacsko
# http://erotika.indavideo.hu/video/Amator_tini_punci
# http://film.indavideo.hu/video/f_hrom_nagymamm_volt
# http://palyazat.indavideo.hu/video/Embertelen_dal_Dodgem_egyuttes
_EMBED_REGEX = [r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//embed\.indavideo\.hu/player/video/[\da-f]+)']
_TESTS = [{
'url': 'http://indavideo.hu/player/video/1bdc3c6d80/',
'md5': 'c8a507a1c7410685f83a06eaeeaafeab',
@@ -37,20 +43,6 @@ class IndavideoEmbedIE(InfoExtractor):
'only_matching': True,
}]
# Some example URLs covered by generic extractor:
# http://indavideo.hu/video/Vicces_cica_1
# http://index.indavideo.hu/video/2015_0728_beregszasz
# http://auto.indavideo.hu/video/Sajat_utanfutoban_a_kis_tacsko
# http://erotika.indavideo.hu/video/Amator_tini_punci
# http://film.indavideo.hu/video/f_hrom_nagymamm_volt
# http://palyazat.indavideo.hu/video/Embertelen_dal_Dodgem_egyuttes
@staticmethod
def _extract_urls(webpage):
return re.findall(
r'<iframe[^>]+\bsrc=["\'](?P<url>(?:https?:)?//embed\.indavideo\.hu/player/video/[\da-f]+)',
webpage)
def _real_extract(self, url):
video_id = self._match_id(url)