parse_iso8601,
str_or_none,
try_get,
- unescapeHTML,
url_or_none,
variadic,
)
IE_DESC = 'ert.gr webtv embedded videos'
_BASE_PLAYER_URL_RE = re.escape('//www.ert.gr/webtv/live-uni/vod/dt-uni-vod.php')
_VALID_URL = rf'https?:{_BASE_PLAYER_URL_RE}\?([^#]+&)?f=(?P<id>[^#&]+)'
+ _EMBED_REGEX = [rf'<iframe[^>]+?src=(?P<_q1>["\'])(?P<url>(?:https?:)?{_BASE_PLAYER_URL_RE}\?(?:(?!(?P=_q1)).)+)(?P=_q1)']
_TESTS = [{
'url': 'https://www.ert.gr/webtv/live-uni/vod/dt-uni-vod.php?f=trailers/E2251_TO_DIKTYO_E09_16-01_1900.mp4&bgimg=/photos/2022/1/to_diktio_ep09_i_istoria_tou_diadiktiou_stin_Ellada_1021x576.jpg',
},
}]
- @classmethod
- def _extract_urls(cls, webpage):
- EMBED_URL_RE = rf'(?:https?:)?{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)
formats, subs = self._extract_m3u8_formats_and_subtitles(