diff options
Diffstat (limited to 'gallery_dl/extractor/sankakucomplex.py')
| -rw-r--r-- | gallery_dl/extractor/sankakucomplex.py | 24 |
1 files changed, 10 insertions, 14 deletions
diff --git a/gallery_dl/extractor/sankakucomplex.py b/gallery_dl/extractor/sankakucomplex.py index 50c21e3..405e07e 100644 --- a/gallery_dl/extractor/sankakucomplex.py +++ b/gallery_dl/extractor/sankakucomplex.py @@ -1,6 +1,6 @@ # -*- coding: utf-8 -*- -# Copyright 2019-2023 Mike Fährmann +# Copyright 2019-2025 Mike Fährmann # # This program is free software; you can redistribute it and/or modify # it under the terms of the GNU General Public License version 2 as @@ -10,7 +10,6 @@ from .common import Extractor, Message from .. import text, util -import re class SankakucomplexExtractor(Extractor): @@ -20,7 +19,7 @@ class SankakucomplexExtractor(Extractor): def __init__(self, match): Extractor.__init__(self, match) - self.path = match.group(1) + self.path = match[1] class SankakucomplexArticleExtractor(SankakucomplexExtractor): @@ -34,7 +33,7 @@ class SankakucomplexArticleExtractor(SankakucomplexExtractor): example = "https://news.sankakucomplex.com/1970/01/01/TITLE" def items(self): - url = "{}/{}/?pg=X".format(self.root, self.path) + url = f"{self.root}/{self.path}/?pg=X" extr = text.extract_from(self.request(url).text) data = { "title" : text.unescape( @@ -64,23 +63,20 @@ class SankakucomplexArticleExtractor(SankakucomplexExtractor): file.update(data) yield Message.Url, url, file - @staticmethod - def _extract_images(content): - orig_sub = re.compile(r"-\d+x\d+\.").sub + def _extract_images(self, content): + orig_sub = util.re(r"-\d+x\d+\.").sub return [ orig_sub(".", url) for url in util.unique(text.extract_iter(content, 'data-lazy-src="', '"')) ] - @staticmethod - def _extract_videos(content): - return re.findall(r"<source [^>]*src=[\"']([^\"']+)", content) + def _extract_videos(self, content): + return util.re(r"<source [^>]*src=[\"']([^\"']+)").findall(content) - @staticmethod - def _extract_embeds(content): + def _extract_embeds(self, content): return [ "ytdl:" + url for url in - re.findall(r"<iframe [^>]*src=[\"']([^\"']+)", content) + util.re(r"<iframe [^>]*src=[\"']([^\"']+)").findall(content) ] @@ -96,7 +92,7 @@ class SankakucomplexTagExtractor(SankakucomplexExtractor): data = {"_extractor": SankakucomplexArticleExtractor} while True: - url = "{}/{}/page/{}/".format(self.root, self.path, pnum) + url = f"{self.root}/{self.path}/page/{pnum}/" response = self.request(url, fatal=False) if response.status_code >= 400: return |