Added epub file processing: currently epub file tokenization is ready

.gitignore

@@ -1 +1,3 @@
-.venv
+.venv
+__pycache__/
+.vscode

app/epub.py

@@ -0,0 +1,59 @@
+import aiofiles as aiof
+from base64 import b64encode
+
+import ebooklib
+from ebooklib import epub
+
+from tempfile import SpooledTemporaryFile
+
+
+async def epub2html(file: SpooledTemporaryFile):
+
+    """
+    Splits epub to tokens and joins them to one html file
+    """
+
+    tokens = await epub_to_tokens(file)
+    ...
+    # TODO: join tokens to HTML
+    html_content = ""
+    ...
+    return html_content
+
+
+async def epub_to_tokens(file: SpooledTemporaryFile) -> dict[str, str]:
+    
+    """
+    Passes file content to ebooklib library and parses epub tokens into dict of the following format:
+
+    "\<file_name\>": "\<file_content\>"
+
+    Where file content is either plain text for xhtml or base64 encoded data for other formats, prepared for embeding to html
+
+    """
+    
+    async with aiof.tempfile.NamedTemporaryFile() as tmp:
+
+        await tmp.write(file.read())
+        await tmp.seek(0)
+        content = await tmp.read()
+
+        try:
+            book = epub.read_epub(tmp.name)
+            tokens = {}
+            for item in book.get_items():
+                item_type = item.get_type()
+                if item_type in (ebooklib.ITEM_COVER, ebooklib.ITEM_IMAGE, ebooklib.ITEM_STYLE, ebooklib.ITEM_VIDEO):
+                    name = item.get_name()
+                    media_type = item.media_type
+                    b64_content = b64encode(item.get_content()).decode()
+
+                    tokens[name] = f'data:{media_type};base64,{b64_content}'
+                elif item_type == ebooklib.ITEM_DOCUMENT:
+                    name = item.get_name()
+                    content = item.get_content()
+
+                    tokens[name] = content
+            return tokens
+        except Exception as e:
+            return 'Error! Wrong epub file format: ' + str(e)

app/main.py

@@ -1,7 +1,20 @@
-from fastapi import FastAPI
+from fastapi import FastAPI, File, UploadFile
+from fastapi.responses import HTMLResponse
+
+from .epub import epub2html
 
 app = FastAPI()
 
 @app.get('/')
 def root():
-    return "Hello, World!"
+    return "Hello, World!"
+
+@app.post('/uploadfile/', )
+async def create_upload_file(file: UploadFile = File(...)):
+    if file.filename.endswith('.epub'):
+        content = await epub2html(file.file)
+    elif file.filename.endswith('.fb2'):
+        content = await fb22html(file.file)
+    else:
+        content = 'Error! Unsupported file type'
+    return HTMLResponse(content=content)

requirements.txt

@@ -1,3 +1,4 @@
+aiofiles==0.7.0
 asgiref==3.4.0
 click==8.0.1
 EbookLib==0.17.1
@@ -5,6 +6,7 @@ fastapi==0.65.2
 h11==0.12.0
 lxml==4.6.3
 pydantic==1.8.2
+python-multipart==0.0.5
 six==1.16.0
 starlette==0.14.2
 typing-extensions==3.10.0.0