merge #8925: [mangatown] add support

docs/supportedsites.md

@@ -691,6 +691,12 @@ Consider all listed sites to potentially be NSFW.
     <td>Chapters, Manga</td>
     <td></td>
 </tr>
+<tr id="mangatown" title="mangatown">
+    <td>MangaTown</td>
+    <td>https://www.mangatown.com/</td>
+    <td>Chapters, Manga</td>
+    <td></td>
+</tr>
 <tr id="mangoxo" title="mangoxo">
     <td>Mangoxo</td>
     <td>https://www.mangoxo.com/</td>

gallery_dl/extractor/__init__.py

@@ -133,6 +133,7 @@ modules = [
     "mangaread",
     "mangareader",
     "mangataro",
+    "mangatown",
     "mangoxo",
     "misskey",
     "motherless",

gallery_dl/extractor/mangatown.py

@@ -0,0 +1,96 @@
+# -*- 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.mangatown.com/"""
+
+from .common import ChapterExtractor, MangaExtractor
+from .. import text
+
+BASE_PATTERN = r"(?:https?://)?(?:www\.)?mangatown\.com"
+
+
+class MangatownBase():
+    """Base class for mangatown extractors"""
+    category = "mangatown"
+    root = "https://www.mangatown.com"
+
+
+class MangatownChapterExtractor(MangatownBase, ChapterExtractor):
+    """Extractor for manga-chapters from mangatown.com"""
+    pattern = BASE_PATTERN + r"(/manga/[^/?#]+(?:/v0*(\d+))?/c(\d+[^/?#]*))"
+    example = "https://www.mangatown.com/manga/TITLE/c001/1.html"
+
+    def __init__(self, match):
+        self.part, self.volume, self.chapter = match.groups()
+        self.base = f"{self.root}{self.part}/"
+        ChapterExtractor.__init__(self, match, self.base + "1.html")
+
+    def metadata(self, page):
+        manga, pos = text.extract(
+            page, 'property="og:title" content="', '"')
+        count     , pos = text.extract(page, "total_pages = ", ";", pos)
+        manga_id  , pos = text.extract(page, "series_id=", ";", pos)
+        chapter_id, pos = text.extract(page, "chapter_id=", ";", pos)
+
+        chapter, dot, minor = self.chapter.partition(".")
+
+        return {
+            "manga"   : text.unescape(manga),
+            "manga_id": text.parse_int(manga_id),
+            "volume"  : text.parse_int(self.volume),
+            "chapter" : text.parse_int(chapter),
+            "chapter_minor": dot + minor,
+            "chapter_id": text.parse_int(chapter_id),
+            "count"   : text.parse_int(count),
+            "lang"    : "en",
+            "language": "English",
+        }
+
+    def images(self, page):
+        pnum = 1
+
+        while True:
+            url = (text.extr(page, 'id="image" src="', '"') or
+                   text.extr(page, '<img src="', '"'))
+            if not url:
+                return
+            yield text.ensure_http_scheme(url), None
+            pnum += 1
+            page = self.request(f"{self.base}{pnum}.html").text
+
+
+class MangatownMangaExtractor(MangatownBase, MangaExtractor):
+    """Extractor for manga from mangatown.com"""
+    chapterclass = MangatownChapterExtractor
+    pattern = BASE_PATTERN + r"(/manga/[^/?#]+)"
+    example = "https://www.mangatown.com/manga/TITLE"
+
+    def chapters(self, page):
+        results = []
+
+        manga, pos = text.extract(page, '<title>', '</title>')
+        manga = manga.partition(" Manga")[0].replace("Read ", "", 1)
+        manga = text.unescape(manga)
+
+        page = text.extract(page, 'class="chapter_list"', '</ul>', pos)[0]
+        for ch in text.extract_iter(page, "<li>", "</li>"):
+            path , pos = text.extract(ch, '<a href="', '"')
+            title, pos = text.extract(ch, "<span>", "<", pos)
+            date , pos = text.extract(ch, 'class="time">', "<", pos)
+
+            chapter = text.extr(path, "/c", "/")
+            chapter, sep, minor = chapter.partition(".")
+
+            results.append((self.root + path, {
+                "manga"   : manga,
+                "chapter" : text.parse_int(chapter),
+                "chapter_minor": sep + minor,
+                "title"   : "" if title is None else text.unescape(title),
+                "date"    : date,
+                "lang"    : "en",
+                "language": "English",
+            }))
+        return results

scripts/supportedsites.py

@@ -128,6 +128,7 @@ CATEGORY_MAP = {
     "mangafox"       : "Manga Fox",
     "mangahere"      : "Manga Here",
     "mangakakalot"   : "MangaKakalot",
+    "mangatown"      : "MangaTown",
     "manganato"      : "MangaNato",
     "mangapark"      : "MangaPark",
     "mangaread"      : "MangaRead",

test/results/mangatown.py

@@ -0,0 +1,64 @@
+# -*- 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 mangatown
+
+
+__tests__ = (
+{
+    "#url"     : "https://www.mangatown.com/manga/kimetsu_no_yaiba/c001/",
+    "#class"   : mangatown.MangatownChapterExtractor,
+    "#pattern" : r"https://zjcdn\.mangahere\.org/.*",
+    "#count"   : ">= 20",
+
+    "chapter"      : 1,
+    "chapter_id"   : 368511,
+    "chapter_minor": "",
+    "count"        : 55,
+    "page"         : range(1, 55),
+    "extension"    : "jpg",
+    "filename"     : str,
+    "lang"         : "en",
+    "language"     : "English",
+    "manga"        : "Kimetsu no Yaiba",
+    "manga_id"     : 21437,
+    "volume"       : 0,
+
+},
+
+{
+    "#url"     : "https://www.mangatown.com/manga/kimetsu_no_yaiba/c001/1.html",
+    "#class"   : mangatown.MangatownChapterExtractor,
+    "#pattern" : r"https://zjcdn\.mangahere\.org/.*",
+},
+
+{
+    "#url"     : "http://www.mangatown.com/manga/kimetsu_no_yaiba/c001/",
+    "#class"   : mangatown.MangatownChapterExtractor,
+},
+
+{
+    "#url"     : "https://www.mangatown.com/manga/kimetsu_no_yaiba/",
+    "#class"   : mangatown.MangatownMangaExtractor,
+    "#pattern" : mangatown.MangatownChapterExtractor.pattern,
+    "#count"   : ">= 100",
+
+    "chapter"  : int,
+    "chapter_minor": {"", ".5", ".6"},
+    "date"     : str,
+    "lang"     : "en",
+    "language" : "English",
+    "manga"    : "Kimetsu no Yaiba",
+    "title"    : str,
+
+},
+
+{
+    "#url"     : "http://www.mangatown.com/manga/kimetsu_no_yaiba/",
+    "#class"   : mangatown.MangatownMangaExtractor,
+},
+
+)