app.py

from fastapi import FastAPI, File, UploadFile
from fastapi.responses import HTMLResponse
import pdfplumber
import re
from fastapi.templating import Jinja2Templates
from fastapi import Request

app = FastAPI()

# 設定 HTML 模板目錄
templates = Jinja2Templates(directory="templates")

# 定義篩選中文字符的正則表達式
chinese_char_pattern = re.compile(r'[\u4e00-\u9fff]')
# 定義篩選英文字符的正則表達式
english_char_pattern = re.compile(r'[A-Za-z]')

# 統計中文和英文字符數的函數
def count_chinese_and_english_characters_in_pdf(file_path):
    total_chinese_chars = 0
    total_english_chars = 0
    page_counts = []

    # 使用 pdfplumber 打開 PDF 文件
    with pdfplumber.open(file_path) as pdf:
        # 遍歷每一頁
        for page_num, page in enumerate(pdf.pages, start=1):
            # 提取頁面的文本
            text = page.extract_text()
            if text:
                # 找到所有中文字符
                chinese_chars = chinese_char_pattern.findall(text)
                chinese_char_count = len(chinese_chars)

                # 找到所有英文字符
                english_chars = english_char_pattern.findall(text)
                english_char_count = len(english_chars)

                # 累加每頁的字符數到總數
                total_chinese_chars += chinese_char_count
                total_english_chars += english_char_count

                # 保存每頁的字符數
                page_counts.append({
                    "page_num": page_num,
                    "chinese_count": chinese_char_count,
                    "english_count": english_char_count
                })

    # 返回每頁的字數及總字數
    return {
        "page_counts": page_counts,
        "total_chinese_chars": total_chinese_chars,
        "total_english_chars": total_english_chars,
        "total_chars": total_chinese_chars + total_english_chars
    }

# 顯示上傳表單的首頁
@app.get("/", response_class=HTMLResponse)
async def show_form(request: Request):
    return templates.TemplateResponse("upload_form.html", {"request": request})

# 上傳並處理文件的 API
@app.post("/uploadfile/")
async def upload_file(request: Request, file: UploadFile = File(...)):
    if file.content_type == "application/pdf":
        # 將上傳的文件存儲在本地
        file_name = file.filename
        with open(f"{file_name}", "wb") as f:
            f.write(await file.read())

        # 計算字符數
        result = count_chinese_and_english_characters_in_pdf(file_name)

        # 返回結果，並顯示在前端，包括檔案名稱
        return templates.TemplateResponse("upload_form.html", {
            "request": request,
            "file_name": file_name,
            "page_counts": result["page_counts"],
            "total_chinese": result["total_chinese_chars"],
            "total_english": result["total_english_chars"],
            "total_chars": result["total_chars"]
        })
    else:
        return {"error": "只接受 PDF 文件"}