mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-09-03 00:25:08 +00:00
Code Issues Projects Releases Wiki Activity

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

Browse Source 
`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
Download Patch File Download Diff File Expand all files Collapse all files

31
yt_dlp/extractor/wistia.py
View File

@ -5,8 +5,8 @@ from ..utils import (
ExtractorError,
float_or_none,
int_or_none,
try_call,
try_get,
unescapeHTML,
)
@ -117,7 +117,7 @@ class WistiaBaseIE(InfoExtractor):
class WistiaIE(WistiaBaseIE):
_VALID_URL = r'(?:wistia:|%s(?:iframe|medias)/)%s' % (WistiaBaseIE._VALID_URL_BASE, WistiaBaseIE._VALID_ID_REGEX)
_EMBED_REGEX = [r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})']
_TESTS = [{
# with hls video
'url': 'wistia:807fafadvk',
@ -146,17 +146,10 @@ class WistiaIE(WistiaBaseIE):
}]
# https://wistia.com/support/embed-and-share/video-on-your-website
@staticmethod
def _extract_url(webpage):
urls = WistiaIE._extract_urls(webpage)
return urls[0] if urls else None
@classmethod
def _extract_embed_urls(cls, url, webpage):
urls = list(super()._extract_embed_urls(url, webpage))
@staticmethod
def _extract_urls(webpage):
urls = []
for match in re.finditer(
r'<(?:meta[^>]+?content|(?:iframe|script)[^>]+?src)=["\'](?P<url>(?:https?:)?//(?:fast\.)?wistia\.(?:net|com)/embed/(?:iframe|medias)/[a-z0-9]{10})', webpage):
urls.append(unescapeHTML(match.group('url')))
for match in re.finditer(
r'''(?sx)
<div[^>]+class=(["'])(?:(?!\1).)*?\bwistia_async_(?P<id>[a-z0-9]{10})\b(?:(?!\1).)*?\1
@ -166,6 +159,20 @@ class WistiaIE(WistiaBaseIE):
urls.append('wistia:%s' % match.group('id'))
return urls
@classmethod
def _extract_from_webpage(cls, url, webpage):
from .teachable import TeachableIE
if list(TeachableIE._extract_embed_urls(url, webpage)):
return
for entry in super()._extract_from_webpage(url, webpage):
yield {
**entry,
'_type': 'url_transparent',
'uploader': try_call(lambda: re.match(r'(?:https?://)?([^/]+)/', url).group(1)),
}
def _real_extract(self, url):
video_id = self._match_id(url)
embed_config = self._download_embed_config('media', video_id, url)