Update upstream source from tag 'upstream/1.29.6'

Update to upstream version '1.29.6'
with Debian dir fb955c7c635591b07c8b52773c233ca312089e7a

1 files changed, 100 insertions, 79 deletions

diff --git a/gallery_dl/extractor/manganelo.py b/gallery_dl/extractor/manganelo.py
index 232b98d..5e92aee 100644
--- a/gallery_dl/extractor/manganelo.py
+++ b/gallery_dl/extractor/manganelo.py
@@ -1,107 +1,128 @@
 # -*- coding: utf-8 -*-
 
+# Copyright 2020 Jake Mannens
+# Copyright 2021-2025 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
 # published by the Free Software Foundation.
 
-"""Extractors for https://manganato.com/"""
+"""Extractors for https://www.mangakakalot.gg/ and mirror sites"""
 
-from .common import ChapterExtractor, MangaExtractor
-from .. import text
-import re
+from .common import BaseExtractor, ChapterExtractor, MangaExtractor
+from .. import text, util
 
-BASE_PATTERN = (
-    r"(?:https?://)?"
-    r"((?:chap|read|www\.|m\.)?mangan(?:at|el)o"
-    r"\.(?:to|com))"
-)
 
+class ManganeloExtractor(BaseExtractor):
+    basecategory = "manganelo"
 
-class ManganeloBase():
-    category = "manganelo"
-    root = "https://chapmanganato.com"
-    _match_chapter = None
 
-    def __init__(self, match):
-        domain, path = match.groups()
-        super().__init__(match, "https://" + domain + path)
-
-    def _init(self):
-        if self._match_chapter is None:
-            ManganeloBase._match_chapter = re.compile(
-                r"(?:[Vv]ol\.?\s*(\d+)\s?)?"
-                r"[Cc]hapter\s*(\d+)([^:]*)"
-                r"(?::\s*(.+))?").match
-
-    def _parse_chapter(self, info, manga, author, date=None):
-        match = self._match_chapter(info)
-        if match:
-            volume, chapter, minor, title = match.groups()
-        else:
-            volume = chapter = minor = ""
-            title = info
-
-        return {
-            "manga"        : manga,
-            "author"       : author,
-            "date"         : date,
-            "title"        : text.unescape(title) if title else "",
-            "volume"       : text.parse_int(volume),
-            "chapter"      : text.parse_int(chapter),
-            "chapter_minor": minor,
-            "lang"         : "en",
-            "language"     : "English",
-        }
+BASE_PATTERN = ManganeloExtractor.update({
+    "nelomanga": {
+        "root"   : "https://www.nelomanga.net",
+        "pattern": r"(?:www\.)?nelomanga\.net",
+    },
+    "natomanga": {
+        "root"   : "https://www.natomanga.com",
+        "pattern": r"(?:www\.)?natomanga\.com",
+    },
+    "manganato": {
+        "root"   : "https://www.manganato.gg",
+        "pattern": r"(?:www\.)?manganato\.gg",
+    },
+    "mangakakalot": {
+        "root"   : "https://www.mangakakalot.gg",
+        "pattern": r"(?:www\.)?mangakakalot\.gg",
+    },
+})
 
 
-class ManganeloChapterExtractor(ManganeloBase, ChapterExtractor):
-    """Extractor for manga chapters from manganelo.com"""
-    pattern = BASE_PATTERN + r"(/(?:manga-\w+|chapter/\w+)/chapter[-_][^/?#]+)"
-    example = "https://chapmanganato.com/manga-ID/chapter-01"
+class ManganeloChapterExtractor(ManganeloExtractor, ChapterExtractor):
+    """Extractor for manganelo manga chapters"""
+    pattern = BASE_PATTERN + r"(/manga/[^/?#]+/chapter-[^/?#]+)"
+    example = "https://www.mangakakalot.gg/manga/MANGA_NAME/chapter-123"
+
+    def __init__(self, match):
+        ManganeloExtractor.__init__(self, match)
+        self.gallery_url = self.root + self.groups[-1]
 
     def metadata(self, page):
         extr = text.extract_from(page)
-        extr('class="a-h"', ">")
-        manga = extr('title="', '"')
-        info = extr('title="', '"')
-        author = extr("- Author(s) : ", "</p>")
 
-        return self._parse_chapter(
-            info, text.unescape(manga), text.unescape(author))
+        data = {
+            "date"        : text.parse_datetime(extr(
+                '"datePublished": "', '"')[:19], "%Y-%m-%dT%H:%M:%S"),
+            "date_updated": text.parse_datetime(extr(
+                '"dateModified": "', '"')[:19], "%Y-%m-%dT%H:%M:%S"),
+            "manga_id"    : text.parse_int(extr("comic_id =", ";")),
+            "chapter_id"  : text.parse_int(extr("chapter_id =", ";")),
+            "manga"       : extr("comic_name =", ";").strip('" '),
+            "lang"        : "en",
+            "language"    : "English",
+        }
+
+        chapter_name = extr("chapter_name =", ";").strip('" ')
+        chapter, sep, minor = chapter_name.rpartition(" ")[2].partition(".")
+        data["chapter"] = text.parse_int(chapter)
+        data["chapter_minor"] = sep + minor
+        data["author"] = extr(". Author:", " already has ").strip()
+
+        return data
 
     def images(self, page):
-        page = text.extr(
-            page, 'class="container-chapter-reader', 'class="container')
+        extr = text.extract_from(page)
+        cdns = util.json_loads(extr("var cdns =", ";"))[0]
+        imgs = util.json_loads(extr("var chapterImages =", ";"))
+
+        if cdns[-1] != "/":
+            cdns += "/"
+
         return [
-            (url, None)
-            for url in text.extract_iter(page, '<img src="', '"')
-            if not url.endswith("/gohome.png")
-        ] or [
-            (url, None)
-            for url in text.extract_iter(
-                page, '<img class="reader-content" src="', '"')
+            (cdns + path, None)
+            for path in imgs
         ]
 
 
-class ManganeloMangaExtractor(ManganeloBase, MangaExtractor):
-    """Extractor for manga from manganelo.com"""
+class ManganeloMangaExtractor(ManganeloExtractor, MangaExtractor):
+    """Extractor for manganelo manga"""
     chapterclass = ManganeloChapterExtractor
-    pattern = BASE_PATTERN + r"(/(?:manga[-/]|read_)\w+)/?$"
-    example = "https://manganato.com/manga-ID"
+    pattern = BASE_PATTERN + r"(/manga/[^/?#]+)$"
+    example = "https://www.mangakakalot.gg/manga/MANGA_NAME"
 
-    def chapters(self, page):
-        results = []
-        append = results.append
+    def __init__(self, match):
+        ManganeloExtractor.__init__(self, match)
+        self.manga_url = self.root + self.groups[-1]
 
+    def chapters(self, page):
         extr = text.extract_from(page)
+
         manga = text.unescape(extr("<h1>", "<"))
-        author = text.remove_html(extr("</i>Author(s) :</td>", "</tr>"))
-
-        extr('class="row-content-chapter', '')
-        while True:
-            url = extr('class="chapter-name text-nowrap" href="', '"')
-            if not url:
-                return results
-            info = extr(">", "<")
-            date = extr('class="chapter-time text-nowrap" title="', '"')
-            append((url, self._parse_chapter(info, manga, author, date)))
+        author = text.remove_html(extr("<li>Author(s) :", "</a>"))
+        status = extr("<li>Status :", "<").strip()
+        update = text.parse_datetime(extr(
+            "<li>Last updated :", "<").strip(), "%b-%d-%Y %I:%M:%S %p")
+        tags = text.split_html(extr(">Genres :", "</li>"))[::2]
+
+        results = []
+        for chapter in text.extract_iter(page, '<div class="row">', '</div>'):
+            url, pos = text.extract(chapter, '<a href="', '"')
+            title, pos = text.extract(chapter, '>', '</a>', pos)
+            date, pos = text.extract(chapter, '<span title="', '"', pos)
+            chapter, sep, minor = url.rpartition("/chapter-")[2].partition("-")
+
+            if url[0] == "/":
+                url = self.root + url
+            results.append((url, {
+                "manga"   : manga,
+                "author"  : author,
+                "status"  : status,
+                "tags"    : tags,
+                "date_updated": update,
+                "chapter" : text.parse_int(chapter),
+                "chapter_minor": (sep and ".") + minor,
+                "title"   : title.partition(": ")[2],
+                "date"    : text.parse_datetime(date, "%b-%d-%Y %H:%M"),
+                "lang"    : "en",
+                "language": "English",
+            }))
+        return results