[wpmadara/toonily/webtoonxyz] Add WP-Manga/Madara base and extractors

docs/configuration.rst

@@ -6403,6 +6403,21 @@ Note
     It is possible to use ``"all"`` instead of listing all values separately.
 
 
+extractor.toonily.family-mode
+------------------------------
+Type
+    ``bool``
+Default
+    ``false``
+Description
+    Controls whether adult content is accessible.
+
+    ``true``
+        Enable family mode — adult content is hidden (``toonily-mature`` cookie is not set)
+    ``false``
+        Disable family mode — set ``toonily-mature=1`` to allow adult content
+
+
 extractor.tumblr.avatar
 -----------------------
 Type
@@ -7367,6 +7382,21 @@ Description
     Useful for creating CBZ archives with actual source thumbnails.
 
 
+extractor.webtoonxyz.family-mode
+---------------------------------
+Type
+    ``bool``
+Default
+    ``false``
+Description
+    Controls whether adult content is accessible.
+
+    ``true``
+        Enable family mode — adult content is hidden (``wpmanga-adault`` cookie is not set)
+    ``false``
+        Disable family mode — set ``wpmanga-adault=1`` to allow adult content
+
+
 extractor.weebdex.data-saver
 ----------------------------
 Type

docs/supportedsites.md

@@ -1159,6 +1159,12 @@ Consider all listed sites to potentially be NSFW.
     <td>Galleries</td>
     <td></td>
 </tr>
+<tr id="toonily" title="toonily">
+    <td>Toonily</td>
+    <td>https://toonily.com/</td>
+    <td>Chapters, Genres, Home Feed, Manga, Tag Searches</td>
+    <td><a href="https://github.com/mikf/gallery-dl#cookies">Cookies</a></td>
+</tr>
 <tr id="toyhouse" title="toyhouse">
     <td>Toyhouse</td>
     <td>https://toyhou.se/</td>
@@ -1273,6 +1279,12 @@ Consider all listed sites to potentially be NSFW.
     <td>Artists, Comics, Episodes</td>
     <td></td>
 </tr>
+<tr id="webtoonxyz" title="webtoonxyz">
+    <td>Webtoonxyz</td>
+    <td>https://www.webtoon.xyz/</td>
+    <td>Chapters, Home Feed, Manga</td>
+    <td><a href="https://github.com/mikf/gallery-dl#cookies">Cookies</a></td>
+</tr>
 <tr id="weebcentral" title="weebcentral">
     <td>Weeb Central</td>
     <td>https://weebcentral.com/</td>

gallery_dl/extractor/__init__.py

@@ -218,6 +218,7 @@
     "thehentaiworld",
     "tiktok",
     "tmohentai",
+    "toonily",
     "toyhouse",
     "tumblr",
     "tumblrgallery",
@@ -240,13 +241,15 @@
     "weasyl",
     "webmshare",
     "webtoons",
+    "webtoonxyz",
     "weebcentral",
     "weebdex",
     "weibo",
     "whyp",
     "wikiart",
     "wikifeet",
     "wikimedia",
+    "wpmadara",
     "xasiat",
     "xenforo",
     "xfolio",

gallery_dl/extractor/toonily.py

@@ -0,0 +1,104 @@
+# -*- 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.
+
+"""Extractors for https://toonily.com/"""
+
+from .. import text
+from .wpmadara import (
+    WPMadaraChapterExtractor,
+    WPMadaraHomeExtractor,
+    WPMadaraMangaExtractor,
+)
+
+
+class ToonilyChapterExtractor(WPMadaraChapterExtractor):
+    """Extractor for manga chapters from toonily.com"""
+    category = "toonily"
+    root = "https://toonily.com"
+    cookies_domain = ".toonily.com"
+    pattern = r"(?:https?://)?(?:www\.)?toonily\.com(/serie/[^/?#]+/[^/?#]+)"
+    example = "https://toonily.com/serie/MANGA/chapter-1/"
+
+    def initialize(self):
+        WPMadaraChapterExtractor.initialize(self)
+        if not self.config("family-mode", False):
+            self.cookies.update({"toonily-mature": "1"})
+
+    def images(self, page):
+        return [
+            (url, data)
+            for url, data in WPMadaraChapterExtractor.images(self, page)
+            if "wp-content/assets" not in url
+        ]
+
+
+class ToonilyMangaExtractor(WPMadaraMangaExtractor):
+    """Extractor for manga from toonily.com"""
+    category = "toonily"
+    chapterclass = ToonilyChapterExtractor
+    root = "https://toonily.com"
+    cookies_domain = ".toonily.com"
+    pattern = r"(?:https?://)?(?:www\.)?toonily\.com(/serie/[^/?#]+)/?$"
+    example = "https://toonily.com/serie/MANGA/"
+
+    def initialize(self):
+        WPMadaraMangaExtractor.initialize(self)
+        if not self.config("family-mode", False):
+            self.cookies.update({"toonily-mature": "1"})
+
+
+class ToonilyListExtractor(WPMadaraHomeExtractor):
+    """Base class for manga listings from toonily.com"""
+    category = "toonily"
+    root = "https://toonily.com"
+    cookies_domain = ".toonily.com"
+    mangaextractor = ToonilyMangaExtractor
+
+    def initialize(self):
+        WPMadaraHomeExtractor.initialize(self)
+        if not self.config("family-mode", False):
+            self.cookies.update({"toonily-mature": "1"})
+
+
+class ToonilyHomeExtractor(ToonilyListExtractor):
+    """Extractor for manga listings from toonily.com"""
+    pattern = r"(?:https?://)?(?:www\.)?toonily\.com(?:/page/(\d+))?/?$"
+    example = "https://toonily.com/"
+
+
+class ToonilyTaxonomyExtractor(ToonilyListExtractor):
+    """Base class for taxonomy listings from toonily.com"""
+    taxonomy = ""
+
+    def __init__(self, match):
+        ToonilyListExtractor.__init__(self, match)
+        self.term = match[1]
+        self.page = text.parse_int(match[2], 1)
+
+    def page_url(self, page_num):
+        url = "{}/{}/{}/".format(
+            self.root.rstrip("/"), self.taxonomy, self.term)
+        if page_num == 1:
+            return url
+        return "{}page/{}/".format(url, page_num)
+
+
+class ToonilyTagExtractor(ToonilyTaxonomyExtractor):
+    """Extractor for tag listings from toonily.com"""
+    subcategory = "tag"
+    taxonomy = "tag"
+    pattern = (r"(?:https?://)?(?:www\.)?toonily\.com/tag/"
+               r"([^/?#]+)(?:/page/(\d+))?/?$")
+    example = "https://toonily.com/tag/TAG/"
+
+
+class ToonilyGenreExtractor(ToonilyTaxonomyExtractor):
+    """Extractor for genre listings from toonily.com"""
+    subcategory = "genre"
+    taxonomy = "genre"
+    pattern = (r"(?:https?://)?(?:www\.)?toonily\.com/genre/"
+               r"([^/?#]+)(?:/page/(\d+))?/?$")
+    example = "https://toonily.com/genre/GENRE/"

gallery_dl/extractor/webtoonxyz.py

@@ -0,0 +1,49 @@
+# -*- 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.
+
+"""Extractors for https://www.webtoon.xyz/"""
+
+from .wpmadara import (
+    WPMadaraChapterExtractor,
+    WPMadaraHomeExtractor,
+    WPMadaraMangaExtractor,
+)
+
+
+class WebtoonxyzBase():
+    """Base class for webtoon.xyz extractors"""
+    category = "webtoonxyz"
+    root = "https://www.webtoon.xyz"
+    cookies_domain = ".webtoon.xyz"
+    browser = "firefox"
+
+    def initialize(self):
+        super().initialize()
+        if not self.config("family-mode", False):
+            self.cookies.update({"wpmanga-adault": "1"})
+
+
+class WebtoonxyzChapterExtractor(WebtoonxyzBase, WPMadaraChapterExtractor):
+    """Extractor for webtoon.xyz chapter pages"""
+    pattern = (
+        r"(?:https?://)?(?:www\.)?webtoon\.xyz"
+        r"(/read/[^/?#]+/[^/?#]+)"
+    )
+    example = "https://www.webtoon.xyz/read/MANGA/chapter-1/"
+
+
+class WebtoonxyzMangaExtractor(WebtoonxyzBase, WPMadaraMangaExtractor):
+    """Extractor for webtoon.xyz manga pages"""
+    chapterclass = WebtoonxyzChapterExtractor
+    pattern = r"(?:https?://)?(?:www\.)?webtoon\.xyz(/read/[^/?#]+)/?$"
+    example = "https://www.webtoon.xyz/read/MANGA/"
+
+
+class WebtoonxyzHomeExtractor(WebtoonxyzBase, WPMadaraHomeExtractor):
+    """Extractor for the webtoon.xyz home feed"""
+    mangaextractor = WebtoonxyzMangaExtractor
+    pattern = r"(?:https?://)?(?:www\.)?webtoon\.xyz(?:/page/(\d+))?/?$"
+    example = "https://www.webtoon.xyz/"