From 9ca6117c67a8305fd02c0960dc7bed9c26754d4e Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?Mike=20F=C3=A4hrmann?= <mike_faehrmann@web.de>
Date: Sat, 20 Jan 2024 02:53:44 +0100
Subject: [PATCH] [hbrowse] remove module

website gone
---
 docs/supportedsites.md          |  6 ---
 gallery_dl/extractor/hbrowse.py | 92 ---------------------------------
 test/results/hbrowse.py         | 28 ----------
 3 files changed, 126 deletions(-)
 delete mode 100644 gallery_dl/extractor/hbrowse.py
 delete mode 100644 test/results/hbrowse.py

diff --git a/docs/supportedsites.md b/docs/supportedsites.md
index 4da570e8..c6756c6a 100644
--- a/docs/supportedsites.md
+++ b/docs/supportedsites.md
@@ -271,12 +271,6 @@ Consider all listed sites to potentially be NSFW.
     <td>Archive, Individual Posts, Home Feed, Search Results</td>
     <td></td>
 </tr>
-<tr>
-    <td>HBrowse</td>
-    <td>https://www.hbrowse.com/</td>
-    <td>Chapters, Manga</td>
-    <td></td>
-</tr>
 <tr>
     <td>Hentai Cosplay</td>
     <td>https://hentai-cosplays.com/</td>
diff --git a/gallery_dl/extractor/hbrowse.py b/gallery_dl/extractor/hbrowse.py
deleted file mode 100644
index a5221409..00000000
--- a/gallery_dl/extractor/hbrowse.py
+++ /dev/null
@@ -1,92 +0,0 @@
-# -*- coding: utf-8 -*-
-
-# Copyright 2015-2023 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
-# published by the Free Software Foundation.
-
-"""Extractors for https://www.hbrowse.com/"""
-
-from .common import ChapterExtractor, MangaExtractor
-from .. import text, util, exception
-
-
-class HbrowseBase():
-    """Base class for hbrowse extractors"""
-    category = "hbrowse"
-    root = "https://www.hbrowse.com"
-
-    def parse_page(self, page, data):
-        """Parse metadata on 'page' and add it to 'data'"""
-        data, pos = text.extract_all(page, (
-            ('manga' , '<td class="listLong">', '</td>'),
-            ('artist', '<td class="listLong">', '</td>'),
-            ('total' , '<td class="listLong">', ' '),
-            ('origin', '<td class="listLong">', '</td>'),
-        ), values=data)
-
-        if not data["manga"] and "<b>Warning</b>" in page:
-            msg = page.rpartition(">")[2].strip()
-            raise exception.StopExtraction("Site is not accessible: '%s'", msg)
-
-        tags = text.extract(page, 'class="listTable"', '</table>', pos)[0]
-
-        data["manga"] = text.unescape(data["manga"])
-        data["total"] = text.parse_int(data["total"])
-        data["artist"] = text.remove_html(data["artist"])
-        data["origin"] = text.remove_html(data["origin"])
-        data["tags"] = list(text.extract_iter(tags, 'href="/browse/', '"'))
-        return data
-
-
-class HbrowseChapterExtractor(HbrowseBase, ChapterExtractor):
-    """Extractor for manga-chapters from hbrowse.com"""
-    directory_fmt = ("{category}", "{manga_id} {manga}", "c{chapter:>05}")
-    filename_fmt = ("{category}_{manga_id}_{chapter:>05}_"
-                    "{page:>03}.{extension}")
-    archive_fmt = "{manga_id}_{chapter}_{page}"
-    pattern = r"(?:https?://)?(?:www\.)?hbrowse\.com(/(\d+)/c(\d+))"
-    example = "https://www.hbrowse.com/12345/c00000"
-
-    def __init__(self, match):
-        self.path, self.gid, self.chapter = match.groups()
-        self.path += "/"
-        ChapterExtractor.__init__(self, match)
-
-    def metadata(self, page):
-        return self.parse_page(page, {
-            "manga_id": text.parse_int(self.gid),
-            "chapter": text.parse_int(self.chapter)
-        })
-
-    def images(self, page):
-        base = self.root + "/data" + self.path
-        json_data = text.extract(page, ';list = ', ',"zzz"')[0] + "]"
-        return [(base + name, None) for name in util.json_loads(json_data)]
-
-
-class HbrowseMangaExtractor(HbrowseBase, MangaExtractor):
-    """Extractor for manga from hbrowse.com"""
-    chapterclass = HbrowseChapterExtractor
-    reverse = False
-    pattern = r"(?:https?://)?(?:www\.)?hbrowse\.com(/\d+)/?$"
-    example = "https://www.hbrowse.com/12345"
-
-    def chapters(self, page):
-        results = []
-        data = self.parse_page(page, {
-            "manga_id": text.parse_int(
-                self.manga_url.rstrip("/").rpartition("/")[2])
-        })
-
-        pos = 0
-        needle = '<td class="listMiddle">\n<a class="listLink" href="'
-        while True:
-            url, pos = text.extract(page, needle, '"', pos)
-            if not url:
-                return results
-            title, pos = text.extract(page, '>View ', '<', pos)
-            data["chapter"] = text.parse_int(url.rpartition("/")[2][1:])
-            data["title"] = title
-            results.append((text.urljoin(self.root, url), data.copy()))
diff --git a/test/results/hbrowse.py b/test/results/hbrowse.py
deleted file mode 100644
index c4b3dcd6..00000000
--- a/test/results/hbrowse.py
+++ /dev/null
@@ -1,28 +0,0 @@
-# -*- coding: utf-8 -*-
-
-# 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
-# published by the Free Software Foundation.
-
-from gallery_dl.extractor import hbrowse
-
-
-__tests__ = (
-{
-    "#url"     : "https://www.hbrowse.com/10363/c00000",
-    "#category": ("", "hbrowse", "chapter"),
-    "#class"   : hbrowse.HbrowseChapterExtractor,
-    "#sha1_url"     : "6feefbc9f4b98e20d8425ddffa9dd111791dc3e6",
-    "#sha1_metadata": "274996f6c809e5250b6ff3abbc5147e29f89d9a5",
-    "#sha1_content" : "44578ebbe176c2c27434966aef22945787e2781e",
-},
-
-{
-    "#url"     : "https://www.hbrowse.com/10363",
-    "#category": ("", "hbrowse", "manga"),
-    "#class"   : hbrowse.HbrowseMangaExtractor,
-    "#sha1_url"     : "b89682bfb86c11d2af0dc47463804ec3ac4aadd6",
-    "#sha1_metadata": "4b15fda1858a69de1fbf5afddfe47dd893397312",
-},
-
-)