Added translators mention.

main.py

@@ -10,6 +10,7 @@ import json
 import re
 from requests_tor import RequestsTor
 import requests
+import hashlib
 
 IMAGE_REMOVE_REGEX = re.compile(r"""<img\s+.*src\s*=\s*\"(?P<src>https?.*)\".*/>""")
 
@@ -28,9 +29,17 @@ class BookMedia(BaseModel):
     summary: str
 
 
+class BranchTeam(BaseModel):
+    name: str
+
+
 class Branch(BaseModel):
     id: int
     branchId: int
+    teams: list[BranchTeam]
+
+
+IMG_HASHES: dict[bytes, str] = {}
 
 
 def process_text(text_obj: dict):
@@ -53,6 +62,18 @@ class Chapter(BaseModel):
     branches: list[Branch]
     withBranches: bool
 
+    def get_translators(self, base_dir: Path) -> list[str]:
+        if len(self.branches) == 1:
+            return [team.name for team in self.branches[0].teams]
+        for branch in self.branches:
+            branch_zip = (
+                base_dir
+                / f"v{self.volume}-n{self.number}-{self.id}-b{branch.branchId}.zip"
+            )
+            if branch_zip.exists():
+                return [team.name for team in branch.teams]
+        return []
+
     def get_zip_path(self, base_dir: Path) -> Path | None:
         nobranch_zip = base_dir / f"v{self.volume}-n{self.number}-{self.id}.zip"
         if nobranch_zip.exists():
@@ -83,6 +104,7 @@ class Chapter(BaseModel):
         if zip_path is None:
             raise FileNotFoundError(f"Chapter for `{self}` not found")
         zip = zipfile.ZipFile(zip_path)
+        print(f"Loaded {zip.filename}")
         data = zip.read("data.txt")
         try:
             content = json.loads(data)
@@ -99,7 +121,6 @@ class Chapter(BaseModel):
         output = []
         extras = []
 
-        print(f"parsing {zip.filename}")
         output.append(f"<h2>Глава {self.number}</h2>")
         for item in content["content"]:
             if item["type"] in {"paragraph", "heading"}:
@@ -189,12 +210,27 @@ class Chapter(BaseModel):
                 new_content = new_content.replace(target_str, "")  # type: ignore
                 continue
 
+            md5 = hashlib.md5(resp).digest()
+            final_path = None
+            if md5 in IMG_HASHES:
+                similar_path = IMG_HASHES[md5]
+                img_bytes = (cache / similar_path).read_bytes()
+                if img_bytes == resp:
+                    print("Found identical image in cache")
+                    final_path = similar_path
+            else:
+                IMG_HASHES[md5] = strip_path
+
+            if final_path is None:
                 img = epub.EpubImage(
                     file_name=strip_path,
                     content=resp,
                 )
                 replaces.append(img)
-            newiimage = f'<img src="../{strip_path}" />'
+                final_path = strip_path
+
+            newiimage = f'<img loading="lazy" src="../{final_path}" />'
+            print(target_str, newiimage)
             new_content = new_content.replace(target_str, newiimage)  # type: ignore
 
         page.content = new_content
@@ -298,7 +334,7 @@ def main():
     book.set_title(info.rusName)
     book.add_metadata(namespace="DC", name="description", value=info.summary)
 
-    book.spine = []
+    book.spine = ["translators"]
     if cover:
         book.spine.insert(0, "cover")
         book.set_cover(args.cover.name, cover)
@@ -314,8 +350,25 @@ def main():
         print("Using default client")
         client = requests.Session()
 
+    translators_page = epub.EpubHtml(
+        file_name="translators.xhtml",
+        title="Translators",
+        lang="ru",
+    )
+    book.add_item(translators_page)
+    book.toc.append(translators_page)
+    book.spine.append(translators_page)  # type: ignore
+
+    translators = set()
     for chapter in chapters:
         chapter.add_to_book(book, args.input, args.fetch_images, client, args.cache)
+        translators.update(chapter.get_translators(args.input))
+
+    translators_content = '<h2 align="center">Переводчики:</h2>\n<ul>\n'
+    for translator in sorted(translators):
+        translators_content += f"<li>{translator}</li>\n"
+    translators_content += "</ul>\n"
+    translators_page.content = translators_content
 
     book.add_item(epub.EpubNcx())