Plugin cleanup and tweaks

This commit is contained in:
2023-02-20 19:18:45 -06:00
parent 372e4ff3dc
commit 3ad9e1c7bb
1138 changed files with 48878 additions and 40445 deletions

View File

@@ -1,14 +1,8 @@
# coding: utf-8
from __future__ import unicode_literals
import re
from .common import InfoExtractor
from ..utils import (
determine_ext,
get_elements_text_and_html_by_attribute,
merge_dicts,
unescapeHTML,
scale_thumbnails_to_max_format_width,
)
@@ -75,24 +69,8 @@ class TVOpenGrWatchIE(TVOpenGrBaseIE):
continue
formats.extend(formats_)
self._merge_subtitles(subs_, target=subs)
self._sort_formats(formats)
return formats, subs
@staticmethod
def _scale_thumbnails_to_max_width(formats, thumbnails, url_width_re):
_keys = ('width', 'height')
max_dimensions = max(
[tuple(format.get(k) or 0 for k in _keys) for format in formats],
default=(0, 0))
if not max_dimensions[0]:
return thumbnails
return [
merge_dicts(
{'url': re.sub(url_width_re, str(max_dimensions[0]), thumbnail['url'])},
dict(zip(_keys, max_dimensions)), thumbnail)
for thumbnail in thumbnails
]
def _real_extract(self, url):
netloc, video_id, display_id = self._match_valid_url(url).group('netloc', 'id', 'slug')
if netloc.find('tvopen.gr') == -1:
@@ -102,7 +80,7 @@ class TVOpenGrWatchIE(TVOpenGrBaseIE):
info['formats'], info['subtitles'] = self._extract_formats_and_subs(
self._download_json(self._API_ENDPOINT, video_id, query={'cid': video_id}),
video_id)
info['thumbnails'] = self._scale_thumbnails_to_max_width(
info['thumbnails'] = scale_thumbnails_to_max_format_width(
info['formats'], info['thumbnails'], r'(?<=/imgHandler/)\d+')
description, _html = next(get_elements_text_and_html_by_attribute('class', 'description', webpage))
if description and _html.startswith('<span '):
@@ -116,7 +94,7 @@ class TVOpenGrEmbedIE(TVOpenGrBaseIE):
IE_NAME = 'tvopengr:embed'
IE_DESC = 'tvopen.gr embedded videos'
_VALID_URL = r'(?:https?:)?//(?:www\.|cdn\.|)(?:tvopen|ethnos).gr/embed/(?P<id>\d+)'
_EMBED_RE = re.compile(rf'''<iframe[^>]+?src=(?P<_q1>["'])(?P<url>{_VALID_URL})(?P=_q1)''')
_EMBED_REGEX = [rf'''<iframe[^>]+?src=(?P<_q1>["'])(?P<url>{_VALID_URL})(?P=_q1)''']
_TESTS = [{
'url': 'https://cdn.ethnos.gr/embed/100963',
@@ -133,11 +111,6 @@ class TVOpenGrEmbedIE(TVOpenGrBaseIE):
},
}]
@classmethod
def _extract_urls(cls, webpage):
for mobj in cls._EMBED_RE.finditer(webpage):
yield unescapeHTML(mobj.group('url'))
def _real_extract(self, url):
video_id = self._match_id(url)
return self._return_canonical_url(url, video_id)