New upstream version 1.23.5.upstream/1.23.5

1 files changed, 64 insertions, 18 deletions

diff --git a/gallery_dl/extractor/hentai2read.py b/gallery_dl/extractor/hentai2read.py
index 53be67b..dc4e31d 100644
--- a/gallery_dl/extractor/hentai2read.py
+++ b/gallery_dl/extractor/hentai2read.py
@@ -1,12 +1,12 @@
 # -*- coding: utf-8 -*-
 
-# Copyright 2016-2019 Mike Fährmann
+# Copyright 2016-2022 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.
 
-"""Extract hentai-manga from https://hentai2read.com/"""
+"""Extractors for https://hentai2read.com/"""
 
 from .common import ChapterExtractor, MangaExtractor
 from .. import text
@@ -23,11 +23,32 @@ class Hentai2readBase():
 class Hentai2readChapterExtractor(Hentai2readBase, ChapterExtractor):
     """Extractor for a single manga chapter from hentai2read.com"""
     archive_fmt = "{chapter_id}_{page}"
-    pattern = r"(?:https?://)?(?:www\.)?hentai2read\.com(/[^/?#]+/(\d+))"
-    test = ("https://hentai2read.com/amazon_elixir/1/", {
-        "url": "964b942cf492b3a129d2fe2608abfc475bc99e71",
-        "keyword": "ff84b8f751f0e4ee37717efc4332ff1db71951d9",
-    })
+    pattern = r"(?:https?://)?(?:www\.)?hentai2read\.com(/[^/?#]+/([^/?#]+))"
+    test = (
+        ("https://hentai2read.com/amazon_elixir/1/", {
+            "url": "964b942cf492b3a129d2fe2608abfc475bc99e71",
+            "keyword": "85645b02d34aa11b3deb6dadd7536863476e1bad",
+        }),
+        ("https://hentai2read.com/popuni_kei_joshi_panic/2.5/", {
+            "pattern": r"https://hentaicdn\.com/hentai"
+                       r"/13088/2\.5y/ccdn00\d+\.jpg",
+            "count": 36,
+            "keyword": {
+                "author": "Kurisu",
+                "chapter": 2,
+                "chapter_id": 75152,
+                "chapter_minor": ".5",
+                "count": 36,
+                "lang": "en",
+                "language": "English",
+                "manga": "Popuni Kei Joshi Panic!",
+                "manga_id": 13088,
+                "page": int,
+                "title": "Popuni Kei Joshi Panic! 2.5",
+                "type": "Original",
+            },
+        }),
+    )
 
     def __init__(self, match):
         self.chapter = match.group(2)
@@ -37,12 +58,14 @@ class Hentai2readChapterExtractor(Hentai2readBase, ChapterExtractor):
         title, pos = text.extract(page, "<title>", "</title>")
         manga_id, pos = text.extract(page, 'data-mid="', '"', pos)
         chapter_id, pos = text.extract(page, 'data-cid="', '"', pos)
+        chapter, sep, minor = self.chapter.partition(".")
         match = re.match(r"Reading (.+) \(([^)]+)\) Hentai(?: by (.+))? - "
-                         r"(\d+): (.+) . Page 1 ", title)
+                         r"([^:]+): (.+) . Page 1 ", title)
         return {
             "manga": match.group(1),
             "manga_id": text.parse_int(manga_id),
-            "chapter": text.parse_int(self.chapter),
+            "chapter": text.parse_int(chapter),
+            "chapter_minor": sep + minor,
             "chapter_id": text.parse_int(chapter_id),
             "type": match.group(2),
             "author": match.group(3),
@@ -51,8 +74,7 @@ class Hentai2readChapterExtractor(Hentai2readBase, ChapterExtractor):
             "language": "English",
         }
 
-    @staticmethod
-    def images(page):
+    def images(self, page):
         images = text.extract(page, "'images' : ", ",\n")[0]
         return [
             ("https://hentaicdn.com/hentai" + part, None)
@@ -67,18 +89,35 @@ class Hentai2readMangaExtractor(Hentai2readBase, MangaExtractor):
     test = (
         ("https://hentai2read.com/amazon_elixir/", {
             "url": "273073752d418ec887d7f7211e42b832e8c403ba",
-            "keyword": "13c1ce7e15cbb941f01c843b0e89adc993d939ac",
+            "keyword": "5c1b712258e78e120907121d3987c71f834d13e1",
         }),
         ("https://hentai2read.com/oshikage_riot/", {
             "url": "6595f920a3088a15c2819c502862d45f8eb6bea6",
-            "keyword": "675c7b7a4fa52cf569c283553bd16b4200a5cd36",
+            "keyword": "a2e9724acb221040d4b29bf9aa8cb75b2240d8af",
+        }),
+        ("https://hentai2read.com/popuni_kei_joshi_panic/", {
+            "pattern": Hentai2readChapterExtractor.pattern,
+            "range": "2-3",
+            "keyword": {
+                "chapter": int,
+                "chapter_id": int,
+                "chapter_minor": ".5",
+                "lang": "en",
+                "language": "English",
+                "manga": "Popuni Kei Joshi Panic!",
+                "manga_id": 13088,
+                "title": str,
+                "type": "Original",
+            },
         }),
     )
 
     def chapters(self, page):
         results = []
+
+        pos = page.find('itemscope itemtype="http://schema.org/Book') + 1
         manga, pos = text.extract(
-            page, '<span itemprop="name">', '</span>')
+            page, '<span itemprop="name">', '</span>', pos)
         mtype, pos = text.extract(
             page, '<small class="text-danger">[', ']</small>', pos)
         manga_id = text.parse_int(text.extract(
@@ -90,12 +129,19 @@ class Hentai2readMangaExtractor(Hentai2readBase, MangaExtractor):
                 return results
             _  , pos = text.extract(page, ' href="', '"', pos)
             url, pos = text.extract(page, ' href="', '"', pos)
-            chapter, pos = text.extract(page, '>', '<', pos)
 
+            chapter, pos = text.extract(page, '>', '<', pos)
             chapter, _, title = text.unescape(chapter).strip().partition(" - ")
+            chapter, sep, minor = chapter.partition(".")
+
             results.append((url, {
-                "manga_id": manga_id, "manga": manga, "type": mtype,
-                "chapter_id": text.parse_int(chapter_id),
+                "manga": manga,
+                "manga_id": manga_id,
                 "chapter": text.parse_int(chapter),
-                "title": title, "lang": "en", "language": "English",
+                "chapter_minor": sep + minor,
+                "chapter_id": text.parse_int(chapter_id),
+                "type": mtype,
+                "title": title,
+                "lang": "en",
+                "language": "English",
             }))