diff options
author | pukkandan <pukkandan.ytdlp@gmail.com> | 2022-08-01 06:53:25 +0530 |
---|---|---|
committer | pukkandan <pukkandan.ytdlp@gmail.com> | 2022-08-02 01:08:16 +0530 |
commit | bfd973ece3369c593b5e82a88cc16de80088a73e (patch) | |
tree | 6a61140e44f412d16ece6794b5b3e4ead4905b3c /yt_dlp/extractor/ant1newsgr.py | |
parent | 1e8fe57e5cd0f33f940df87430d75e1230ec5b7a (diff) | |
download | hypervideo-pre-bfd973ece3369c593b5e82a88cc16de80088a73e.tar.lz hypervideo-pre-bfd973ece3369c593b5e82a88cc16de80088a73e.tar.xz hypervideo-pre-bfd973ece3369c593b5e82a88cc16de80088a73e.zip |
[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
Diffstat (limited to 'yt_dlp/extractor/ant1newsgr.py')
-rw-r--r-- | yt_dlp/extractor/ant1newsgr.py | 15 |
1 files changed, 2 insertions, 13 deletions
diff --git a/yt_dlp/extractor/ant1newsgr.py b/yt_dlp/extractor/ant1newsgr.py index cd0f36856..fac476e21 100644 --- a/yt_dlp/extractor/ant1newsgr.py +++ b/yt_dlp/extractor/ant1newsgr.py @@ -1,4 +1,3 @@ -import re import urllib.parse from .common import InfoExtractor @@ -7,7 +6,6 @@ from ..utils import ( ExtractorError, determine_ext, scale_thumbnails_to_max_format_width, - unescapeHTML, ) @@ -91,7 +89,7 @@ class Ant1NewsGrArticleIE(Ant1NewsGrBaseIE): video_id = self._match_id(url) webpage = self._download_webpage(url, video_id) info = self._search_json_ld(webpage, video_id, expected_type='NewsArticle') - embed_urls = list(Ant1NewsGrEmbedIE._extract_urls(webpage)) + embed_urls = list(Ant1NewsGrEmbedIE._extract_embed_urls(url, webpage)) if not embed_urls: raise ExtractorError('no videos found for %s' % video_id, expected=True) return self.playlist_from_matches( @@ -104,6 +102,7 @@ class Ant1NewsGrEmbedIE(Ant1NewsGrBaseIE): IE_DESC = 'ant1news.gr embedded videos' _BASE_PLAYER_URL_RE = r'(?:https?:)?//(?:[a-zA-Z0-9\-]+\.)?(?:antenna|ant1news)\.gr/templates/pages/player' _VALID_URL = rf'{_BASE_PLAYER_URL_RE}\?([^#]+&)?cid=(?P<id>[^#&]+)' + _EMBED_REGEX = [rf'<iframe[^>]+?src=(?P<_q1>["\'])(?P<url>{_BASE_PLAYER_URL_RE}\?(?:(?!(?P=_q1)).)+)(?P=_q1)'] _API_PATH = '/news/templates/data/jsonPlayer' _TESTS = [{ @@ -117,16 +116,6 @@ class Ant1NewsGrEmbedIE(Ant1NewsGrBaseIE): }, }] - @classmethod - def _extract_urls(cls, webpage): - _EMBED_URL_RE = rf'{cls._BASE_PLAYER_URL_RE}\?(?:(?!(?P=_q1)).)+' - _EMBED_RE = rf'<iframe[^>]+?src=(?P<_q1>["\'])(?P<url>{_EMBED_URL_RE})(?P=_q1)' - for mobj in re.finditer(_EMBED_RE, webpage): - url = unescapeHTML(mobj.group('url')) - if not cls.suitable(url): - continue - yield url - def _real_extract(self, url): video_id = self._match_id(url) |