[mangafreak] update & fix

- fix manga and title extraction
- fix 'chapter_minor'
- extend test results

gallery_dl/extractor/mangafreak.py

@@ -1,7 +1,5 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 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.
@@ -11,7 +9,7 @@
 from .common import ChapterExtractor, MangaExtractor
 from .. import text
 
-BASE_PATTERN = r"(?:https?://)?(?:ww\d\.)?mangafreak\.me"
+BASE_PATTERN = r"(?:https?://)?(?:ww[\dw]\.)?mangafreak\.me"
 
 
 class MangafreakBase():
@@ -22,33 +20,30 @@ class MangafreakBase():
 
 class MangafreakChapterExtractor(MangafreakBase, ChapterExtractor):
     """Extractor for mangafreak manga chapters"""
-    pattern = BASE_PATTERN + r"(/Read1_(.+)_(\d+[a-z]?))"
+    pattern = BASE_PATTERN + r"(/Read1_([^/?#]+)_((\d+)([a-z])?))"
     example = "https://ww2.mangafreak.me/Read1_Onepunch_Man_1"
 
     def metadata(self, page):
-        extr = text.extract_from(page)
+        manga = text.extr(page, "<title>Read ", " Chapter ")
-        manga = text.unescape(extr("<title>", " Chapter "))
+        title = text.extr(page, 'selected="selected">', "<").partition(": ")[2]
-        title = text.unescape(extr("", " - MangaFreak"))
+        _, manga_slug, chapter_string, chapter, minor = self.groups
-
-        chapter_str = self.groups[2]
-        chapter, sep, minor = chapter_str.partition("e")
 
         return {
-            "manga"        : manga,
+            "manga"        : text.unescape(manga),
-            "title"        : title,
+            "manga_slug"   : manga_slug,
+            "title"        : text.unescape(title) if title else "",
             "chapter"      : text.parse_int(chapter),
-            "chapter_minor": sep + minor,
+            "chapter_minor": "" if minor is None else minor,
-            "chapter_string": chapter_str,
+            "chapter_string": chapter_string,
-            "manga_slug"   : self.groups[1],
             "lang"         : "en",
             "language"     : "English",
         }
 
     def images(self, page):
+        base = "https://images.mangafreak.me/mangas/"
         return [
-            ("https://images.mangafreak.me/mangas/" + path, None)
+            (base + path, None)
-            for path in text.extract_iter(
+            for path in text.extract_iter(page, 'src="' + base, '"')
-                page, 'src="https://images.mangafreak.me/mangas/', '"')
         ]
 
 
@@ -59,34 +54,32 @@ class MangafreakMangaExtractor(MangafreakBase, MangaExtractor):
     example = "https://ww2.mangafreak.me/Manga/Onepunch_Man"
 
     def chapters(self, page):
-        extr = text.extract_from(page)
+        table = text.extr(page, "<table>", "</table>")
-        manga = text.unescape(extr("<title>", " Manga"))
+        if not table:
-
+            return ()
-        chapter_table = text.extr(page, "<table>", "</table>")
-        if not chapter_table:
-            return []
 
         data = {
-            "manga"     : manga,
+            "manga"     : text.unescape(text.extr(page, "<title>", " Manga")),
             "manga_slug": self.groups[1],
             "lang"      : "en",
             "language"  : "English",
         }
 
         results = []
-        for row in text.extract_iter(chapter_table, "<tr>", "</tr>"):
+        chapter_match = text.re(r"(\d+)(\w*)").match
+        for row in text.extract_iter(table, "<tr>", "</tr>"):
             href = text.extr(row, '<a href="', '"')
             if not href:
                 continue
             url = self.root + href
-            chapter_str = url.rpartition("_")[2]
+            chapter_string = href.rpartition("_")[2]
-            chapter, sep, minor = chapter_str.partition("e")
+            chapter, minor = chapter_match(chapter_string).groups()
-
+            title = text.extr(row, '">', '<').partition(" - ")[2]
             results.append((url, {
-                "chapter"      : text.parse_int(chapter),
+                "chapter"       : text.parse_int(chapter),
-                "chapter_minor": sep + minor,
+                "chapter_minor" : minor,
-                "chapter_string": chapter_str,
+                "chapter_string": chapter_string,
+                "title"         : text.unescape(title) if title else "",
                 **data,
             }))
-
         return results

test/results/mangafreak.py

@@ -32,6 +32,37 @@ __tests__ = (
     "chapter_string": "167e",
 },
 
+{
+    "#url"     : "https://ww2.mangafreak.me/Read1_Sss_Rank_Dungeon_De_Knife_Ippon_Tewatasare_Tsuihou_Sareta_Shiro_Madoushi_Yggdrasil_No_Noroi_Ni_Yori_Jakuten_De_Aru_Maryoku_Fusoku_Wo_Kokufuku_Shi_Sekai_Saikyou_E_To_Itaru_23c",
+    "#class"   : mangafreak.MangafreakChapterExtractor,
+    "#pattern" : r"https://images\.mangafreak\.me/mangas/sss_rank_dungeon_de_knife_ippon_tewatasare_tsuihou_sareta_shiro_madoushi_yggdrasil_no_noroi_ni_yori_jakuten_de_aru_maryoku_fusoku_wo_kokufuku_shi_sekai_saikyou_e_to_itaru/sss_rank_dungeon_de_knife_ippon_tewatasare_tsuihou_sareta_shiro_madoushi_yggdrasil_no_noroi_ni_yori_jakuten_de_aru_maryoku_fusoku_wo_kokufuku_shi_sekai_saikyou_e_to_itaru_23c/sss_rank_dungeon_de_knife_ippon_tewatasare_tsuihou_sareta_shiro_madoushi_yggdrasil_no_noroi_ni_yori_jakuten_de_aru_maryoku_fusoku_wo_kokufuku_shi_sekai_saikyou_e_to_itaru_23c_\d+\.jpg",
+    "#count"   : 11,
+
+    "chapter"       : 23,
+    "chapter_minor" : "c",
+    "chapter_string": "23c",
+    "count"         : 11,
+    "page"          : range(1, 11),
+    "filename"      : str,
+    "extension"     : "jpg",
+    "lang"          : "en",
+    "language"      : "English",
+    "manga"         : "Sss Rank Dungeon De Knife Ippon Tewatasare Tsuihou Sareta Shiro Madoushi Yggdrasil No Noroi Ni Yori Jakuten De Aru Maryoku Fusoku Wo Kokufuku Shi Sekai Saikyou E To Itaru",
+    "manga_slug"    : "Sss_Rank_Dungeon_De_Knife_Ippon_Tewatasare_Tsuihou_Sareta_Shiro_Madoushi_Yggdrasil_No_Noroi_Ni_Yori_Jakuten_De_Aru_Maryoku_Fusoku_Wo_Kokufuku_Shi_Sekai_Saikyou_E_To_Itaru",
+    "title"         : "",
+},
+
+{
+    "#url"     : "https://ww2.mangafreak.me/Read1_Tensei_Shitara_Slime_Datta_Ken_62",
+    "#class"   : mangafreak.MangafreakChapterExtractor,
+    "#count"   : 19,
+
+    "chapter"  : 62,
+    "count"    : 19,
+    "manga"    : "Tensei Shitara Slime Datta Ken",
+    "title"    : "To be a Monster or Human",
+},
+
 {
     "#url"     : "https://ww2.mangafreak.me/Manga/Onepunch_Man",
     "#class"   : mangafreak.MangafreakMangaExtractor,
@@ -45,4 +76,20 @@ __tests__ = (
     "chapter"    : int,
 },
 
+{
+    "#url"     : "https://ww2.mangafreak.me/Manga/Sss_Rank_Dungeon_De_Knife_Ippon_Tewatasare_Tsuihou_Sareta_Shiro_Madoushi_Yggdrasil_No_Noroi_Ni_Yori_Jakuten_De_Aru_Maryoku_Fusoku_Wo_Kokufuku_Shi_Sekai_Saikyou_E_To_Itaru",
+    "#class"   : mangafreak.MangafreakMangaExtractor,
+    "#pattern" : mangafreak.MangafreakChapterExtractor.pattern,
+    "#count"   : range(40, 80),
+
+    "chapter"       : int,
+    "chapter_minor" : {"", "a", "b", "c"},
+    "chapter_string": str,
+    "lang"          : "en",
+    "language"      : "English",
+    "manga"         : "SSS Rank Dungeon de Knife Ippon Tewatasare Tsuihou Sareta Shiro Madoushi: Yggdrasil no Noroi ni yori Jakuten de aru Maryoku Fusoku wo Kokufuku-shi Sekai Saikyou e to Itaru",
+    "manga_slug"    : "Sss_Rank_Dungeon_De_Knife_Ippon_Tewatasare_Tsuihou_Sareta_Shiro_Madoushi_Yggdrasil_No_Noroi_Ni_Yori_Jakuten_De_Aru_Maryoku_Fusoku_Wo_Kokufuku_Shi_Sekai_Saikyou_E_To_Itaru",
+    "title"         : str,
+},
+
 )