support xeHentai

Author: URenko

comiclib/scanner/20-ccloli.py

@@ -28,14 +28,12 @@ def scan(self, path: Path, id: str, metadata: dict, prev_scanners: list[str]) ->
             else:
                 return False
             logger.info(f' <- {path}')
-            if "hentai.org" not in info[2]: return False
-            metadata["title"] = info[0]
-            metadata["subtitle"] = info[1]
             metadata["source"] = info[2]
             m = re.match(r"https?://e[x-]hentai\.org/g/(\d+)/(\w+)", metadata["source"])
             if m is None:
-                logger.error(metadata["source"])
-                raise NotImplementedError('Unknow source format.')
+                return False
+            metadata["title"] = info[0]
+            metadata["subtitle"] = info[1]
             metadata["id"] = f"EH{m[1]:>018}{m[2]}{id[-10:]}"
             line_tags = False
             for line in info:

comiclib/scanner/23-xeHentai.py

@@ -0,0 +1,29 @@
+from pathlib import Path
+from zipfile import ZipFile
+import re
+
+import logging
+logger = logging.getLogger(__name__)
+
+class Scanner:
+    '''For https://github.com/fffonion/xeHentai'''
+    
+    def scan(self, path: Path, id: str, metadata: dict, prev_scanners: list[str]) -> bool:
+        if not '10-zip' in prev_scanners or '20-ccloli' in prev_scanners:
+            return False
+        with ZipFile(path) as z:
+            try:
+                comment = z.comment.decode("utf-8")
+            except UnicodeDecodeError:
+                return False
+            if (m := re.fullmatch('xeHentai Archiver v\\S+\nTitle:(.+)\nOriginal URL:(\\S+)', comment)) is not None:
+                metadata["title"] = m[1]
+                metadata["source"] = m[2]
+                source = re.match(r"https?://e[x-]hentai\.org/g/(\d+)/(\w+)", metadata["source"])
+                if source is None:
+                    logger.error(metadata["source"])
+                    raise NotImplementedError('Unknow source format.')
+                metadata["id"] = f"EH{source[1]:>018}{source[2]}{id[-10:]}"
+                return True
+            else:
+                return False

docs/en/docs/scanner.md

@@ -36,6 +36,10 @@ Parse comic folders downloaded via [Hentai@Home](https://ehwiki.org/wiki/Hentai@
 
 Parse comic folders downloaded via [EhViewer](https://github.com/seven332/EhViewer).
 
+### 23-xeHentai.py
+
+Parse comic files downloaded via [xeHentai](https://github.com/fffonion/xeHentai).
+
 ### 30-importEHdb.py
 
 Import the corresponding metadata from [ehentai metadata database](https://sukebei.nyaa.si/user/gipaf23445).

docs/en/docs/supported-formats.md

@@ -5,6 +5,7 @@
 | zip | general | 10-zip.py |
 | rar, 7z [^1] | general | 11-archive.py |
 | zip | [ccloli/E-Hentai-Downloader](https://github.com/ccloli/E-Hentai-Downloader) | 20-ccloli.py |
+| zip | [xeHentai](https://github.com/fffonion/xeHentai) | 23-xeHentai.py |
 | folder | [Hentai@Home](https://ehwiki.org/wiki/Hentai@Home#H.40H_Downloader) | 21-hath.py |
 | folder | [EhViewer](https://github.com/seven332/EhViewer) | 22-ehviewer.py |
 

docs/zh/docs/scanner.md

@@ -35,6 +35,10 @@ ComicLib 的主体仅负责遍历漫画库，漫画文件的判断、解析等
 
 解析通过 [EhViewer](https://github.com/seven332/EhViewer) 下载的漫画文件夹。
 
+### 23-xeHentai.py
+
+解析通过 [xeHentai](https://github.com/fffonion/xeHentai) 下载的漫画文件。
+
 ### 30-importEHdb.py
 
 从 [ehentai 元数据库](https://sukebei.nyaa.si/user/gipaf23445)导入相应的元数据。

docs/zh/docs/supported-formats.md

@@ -5,6 +5,7 @@
 | zip | 一般 | 10-zip.py |
 | rar, 7z [^1] | 一般 | 11-archive.py |
 | zip | [ccloli/E-Hentai-Downloader](https://github.com/ccloli/E-Hentai-Downloader) | 20-ccloli.py |
+| zip | [xeHentai](https://github.com/fffonion/xeHentai) | 23-xeHentai.py |
 | 文件夹 | [Hentai@Home](https://ehwiki.org/wiki/Hentai@Home#H.40H_Downloader) | 21-hath.py |
 | 文件夹 | [EhViewer](https://github.com/seven332/EhViewer) | 22-ehviewer.py |