画像の重複を排除, デフォルトの epub ファイル名を novel_id にする

README.md

@@ -25,21 +25,21 @@ options:
   -h, --help            show this help message and exit
   -i, --illustration    include illustrations
   -o <file>, --output <file>
-                        output file name
+                        output file name; if not specified, ${novel_id}.epub is used
 ```
 
 Example:
 
 ```sh
 $ nepub xxxx
-noval_id: xxxx, output: default.epub
+noval_id: xxxx, illustration: False, output: xxxx.epub
 3 episodes found.
 Start downloading...
 Downloading (1/3): https://ncode.syosetu.com/xxxx/1/
 Downloading (2/3): https://ncode.syosetu.com/xxxx/2/
 Downloading (3/3): https://ncode.syosetu.com/xxxx/3/
 Download is complete!
-Created default.epub.
+Created xxxx.epub.
 ```
 
 ※ xxxx の部分には小説ページの URL の末尾部分 (`https://ncode.syosetu.com/{ここの文字列}/`) に置き換えてください。

nepub/__main__.py

@@ -18,12 +18,15 @@ def main():
         "-o",
         "--output",
         metavar="<file>",
-        help="output file name",
+        help="output file name; if not specified, ${novel_id}.epub is used",
         type=str,
-        default="default.epub",
     )
     args = parser.parse_args()
-    convert_narou_to_epub(args.novel_id, args.illustration, args.output)
+    if args.output:
+        output = args.output
+    else:
+        output = f"{args.novel_id}.epub"
+    convert_narou_to_epub(args.novel_id, args.illustration, output)
 
 
 def convert_narou_to_epub(novel_id: str, illustration: bool, output: str):
@@ -73,13 +76,24 @@ def convert_narou_to_epub(novel_id: str, illustration: bool, output: str):
 
     print("Download is complete!")
 
+    # deduplicate images
+    deduplicated_images = []
+    image_md5s = set()
+    for image in images:
+        if image["id"] not in image_md5s:
+            deduplicated_images.append(image)
+            image_md5s.add(image["id"])
+
     # files
     files: List[Tuple[str, str | bytes]] = []
     files.append(("mimetype", "application/epub+zip"))
     files.append(("META-INF/container.xml", container()))
     files.append(("src/style.css", style()))
     files.append(
-        ("src/content.opf", content(title, author, created_at, episodes, images))
+        (
+            "src/content.opf",
+            content(title, author, created_at, episodes, deduplicated_images),
+        )
     )
     files.append(("src/navigation.xhtml", nav(chapters)))
     for episode in episodes:
@@ -89,7 +103,7 @@ def convert_narou_to_epub(novel_id: str, illustration: bool, output: str):
                 text(episode["title"], episode["paragraphs"]),
             )
         )
-    for image in images:
+    for image in deduplicated_images:
         files.append((f'src/image/{image["name"]}', image["data"]))
     compose(output, files)
 

setup.py

@@ -13,7 +13,7 @@
 
 setup(
     name="nepub",
-    version="1.1.0",
+    version="1.1.1",
     description="Small tool to convert Narou Novels to vertically written EPUBs.",
     long_description=readme,
     author="[email protected]",