mirrors/yt-dlp
1
0
Fork 0
mirror of https://github.com/yt-dlp/yt-dlp.git synced 2025-11-02 07:35:13 +00:00
Code Issues Projects Releases Wiki Activity

[cleanup] Add more ruff rules (#10149)

Browse Source 
Authored by: seproDev

Reviewed-by: bashonly <88596187+bashonly@users.noreply.github.com>
Reviewed-by: Simon Sawicki <contact@grub4k.xyz>
This commit is contained in:
sepro
2024-06-12 01:09:58 +02:00
committed by GitHub
parent db50f19d76
commit add96eb9f8
915 changed files with 7027 additions and 7246 deletions
Download Patch File Download Diff File Expand all files Collapse all files

27
yt_dlp/extractor/xhamster.py
View File

@@ -2,7 +2,6 @@ import itertools
import re
from .common import InfoExtractor
from ..compat import compat_str
from ..utils import (
ExtractorError,
clean_html,
@@ -22,14 +21,14 @@ from ..utils import (
class XHamsterIE(InfoExtractor):
_DOMAINS = r'(?:xhamster\.(?:com|one|desi)|xhms\.pro|xhamster\d+\.com|xhday\.com|xhvid\.com)'
_VALID_URL = r'''(?x)
_VALID_URL = rf'''(?x)
https?://
(?:[^/?#]+\.)?%s/
(?:[^/?#]+\.)?{_DOMAINS}/
(?:
movies/(?P<id>[\dA-Za-z]+)/(?P<display_id>[^/]*)\.html|
videos/(?P<display_id_2>[^/]*)-(?P<id_2>[\dA-Za-z]+)
)
''' % _DOMAINS
'''
_TESTS = [{
'url': 'https://xhamster.com/videos/femaleagent-shy-beauty-takes-the-bait-1509445',
'md5': '34e1ab926db5dc2750fed9e1f34304bb',
@@ -177,7 +176,7 @@ class XHamsterIE(InfoExtractor):
continue
format_urls.add(format_url)
formats.append({
'format_id': '%s-%s' % (format_id, quality),
'format_id': f'{format_id}-{quality}',
'url': format_url,
'ext': determine_ext(format_url, 'mp4'),
'height': get_height(quality),
@@ -228,7 +227,7 @@ class XHamsterIE(InfoExtractor):
or str_or_none(standard_format.get('label'))
or '')
formats.append({
'format_id': '%s-%s' % (format_id, quality),
'format_id': f'{format_id}-{quality}',
'url': standard_url,
'ext': ext,
'height': get_height(quality),
@@ -245,7 +244,7 @@ class XHamsterIE(InfoExtractor):
if not isinstance(c, dict):
continue
c_name = c.get('name')
if isinstance(c_name, compat_str):
if isinstance(c_name, str):
categories.append(c_name)
else:
categories = None
@@ -258,7 +257,7 @@ class XHamsterIE(InfoExtractor):
'description': video.get('description'),
'timestamp': int_or_none(video.get('created')),
'uploader': try_get(
video, lambda x: x['author']['name'], compat_str),
video, lambda x: x['author']['name'], str),
'uploader_url': uploader_url,
'uploader_id': uploader_url.split('/')[-1] if uploader_url else None,
'thumbnail': video.get('thumbURL'),
@@ -372,7 +371,7 @@ class XHamsterIE(InfoExtractor):
class XHamsterEmbedIE(InfoExtractor):
_VALID_URL = r'https?://(?:[^/?#]+\.)?%s/xembed\.php\?video=(?P<id>\d+)' % XHamsterIE._DOMAINS
_VALID_URL = rf'https?://(?:[^/?#]+\.)?{XHamsterIE._DOMAINS}/xembed\.php\?video=(?P<id>\d+)'
_EMBED_REGEX = [r'<iframe[^>]+?src=(["\'])(?P<url>(?:https?:)?//(?:www\.)?xhamster\.com/xembed\.php\?video=\d+)\1']
_TEST = {
'url': 'http://xhamster.com/xembed.php?video=3328539',
@@ -385,7 +384,7 @@ class XHamsterEmbedIE(InfoExtractor):
'uploader': 'ManyakisArt',
'duration': 5,
'age_limit': 18,
}
},
}
def _real_extract(self, url):
@@ -394,14 +393,14 @@ class XHamsterEmbedIE(InfoExtractor):
webpage = self._download_webpage(url, video_id)
video_url = self._search_regex(
r'href="(https?://xhamster\.com/(?:movies/{0}/[^"]*\.html|videos/[^/]*-{0})[^"]*)"'.format(video_id),
rf'href="(https?://xhamster\.com/(?:movies/{video_id}/[^"]*\.html|videos/[^/]*-{video_id})[^"]*)"',
webpage, 'xhamster url', default=None)
if not video_url:
vars = self._parse_json(
player_vars = self._parse_json(
self._search_regex(r'vars\s*:\s*({.+?})\s*,\s*\n', webpage, 'vars'),
video_id)
video_url = dict_get(vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
video_url = dict_get(player_vars, ('downloadLink', 'homepageLink', 'commentsLink', 'shareUrl'))
return self.url_result(video_url, 'XHamster')
@@ -441,7 +440,7 @@ class XHamsterUserIE(InfoExtractor):
next_page_url = f'https://xhamster.com/{prefix}/{user_id}/{suffix}/1'
for pagenum in itertools.count(1):
page = self._download_webpage(
next_page_url, user_id, 'Downloading page %s' % pagenum)
next_page_url, user_id, f'Downloading page {pagenum}')
for video_tag in re.findall(
r'(<a[^>]+class=["\'].*?\bvideo-thumb__image-container[^>]+>)',
page):