From 2f3a021d7267f0ead5c73556575fae9b82bbfd4f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= Date: Tue, 5 Feb 2019 10:22:52 +0100 Subject: [PATCH] [hentaicafe] restore functionality --- gallery_dl/extractor/__init__.py | 2 +- gallery_dl/extractor/hentaicafe.py | 11 +++++++---- 2 files changed, 8 insertions(+), 5 deletions(-) diff --git a/gallery_dl/extractor/__init__.py b/gallery_dl/extractor/__init__.py index c9724f41..6b3561b5 100644 --- a/gallery_dl/extractor/__init__.py +++ b/gallery_dl/extractor/__init__.py @@ -28,7 +28,7 @@ modules = [ "gfycat", "hbrowse", "hentai2read", - # "hentaicafe", + "hentaicafe", "hentaifoundry", "hentaifox", "hentaihere", diff --git a/gallery_dl/extractor/hentaicafe.py b/gallery_dl/extractor/hentaicafe.py index 28f0a33c..e8b066cc 100644 --- a/gallery_dl/extractor/hentaicafe.py +++ b/gallery_dl/extractor/hentaicafe.py @@ -1,6 +1,6 @@ # -*- coding: utf-8 -*- -# Copyright 2018 Mike Fährmann +# Copyright 2018-2019 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 @@ -17,11 +17,13 @@ class HentaicafeChapterExtractor(foolslide.FoolslideChapterExtractor): """Extractor for manga-chapters from hentai.cafe""" category = "hentaicafe" directory_fmt = ["{category}", "{manga}"] - pattern = foolslide.chapter_pattern(r"(?:www\.)?hentai\.cafe/manga") + pattern = [r"(?:https?://)?(?:www\.)?hentai\.cafe" + r"(/manga/read/[^/?&#]+/[a-z-]+/\d+/\d+(?:/\d+)?)"] test = [("https://hentai.cafe/manga/read/saitom-box/en/0/1/", { "url": "8c6a8c56875ba3ed7ab0a74a64f9960077767fc2", "keyword": "1b24a3e8625b89d160d01ce3eb5e5eb12fbbf648", })] + root = "https://hentai.cafe" def get_metadata(self, page): info = text.unescape(text.extract(page, '', '')[0]) @@ -35,8 +37,8 @@ class HentaicafeChapterExtractor(foolslide.FoolslideChapterExtractor): class HentaicafeMangaExtractor(foolslide.FoolslideMangaExtractor): """Extractor for manga from hentai.cafe""" category = "hentaicafe" - pattern = [r"(?:https?://)?((?:www\.)?hentai\.cafe" - r"(?:/manga/series)?/[^/?&#]+/?$)"] + pattern = [r"(?:https?://)?" + r"(?:www\.)?hentai\.cafe" + r"((?:/manga/series)?/[^/?&#]+)/?$"] test = [ # single chapter ("https://hentai.cafe/hazuki-yuuto-summer-blues/", { @@ -52,6 +54,7 @@ class HentaicafeMangaExtractor(foolslide.FoolslideMangaExtractor): "keyword": "46012b857eb1a1394bc55c0efe7aa4e7f704d10d", }), ] + root = "https://hentai.cafe" reverse = False def chapters(self, page):