pdf识别

README.md

@@ -1 +1,6 @@
-#执行版本 pip install --no-cache-dir -r requirements.txt
+#执行版本 
+
+pip install --no-cache-dir -r requirements.txt
+
+
+pip freeze > requirements.txt

main.py

@@ -1,5 +1,5 @@
 import uvicorn
-from fastapi import FastAPI
+from fastapi import FastAPI,Form
 from pydantic import BaseModel
 
 from tool.pdf2md import pdf2ai
@@ -65,12 +65,12 @@ async def pdf2md(item: Pdf2md, q: str = None):
 
     return result
 
-@app.put("/pdf2md")
-async def saved2text(item: Saved2text, q: str = None):
+@app.put("/md2html")
+async def saved2text(htmlContent: str = Form(...), fileName: str = Form(...)):
     pdf_url = 'http://42.194.163.46:9007/ywd/%E6%89%AB%E6%8F%8F%E5%85%A8%E8%83%BD%E7%8E%8B%202025-03-20%2021.38.pdf'
     prompt = "提取有效信息，只输出图片有效信息无效信息不用。"
 
-    result = save_html_to_file(item.htmlContent, item.fileName)
+    result = save_html_to_file(htmlContent, fileName)
 
     return result
 

utils/text_to_html.py

@@ -1,20 +1,24 @@
+from datetime import datetime
+
+
 def save_html_to_file(html_content, file_name):
     import os
     # 保存 HTML 文件的路径，假设保存到 /home 目录下
-    file_path = f"/home/aihtml"
+
+    current_time = datetime.now().strftime("%Y%m%d%H%M%S")
+    file_path = f"/home/aihtml/{file_name}_{current_time}.html"
     directory = os.path.dirname(file_path)
     if not os.path.exists(directory):
         os.makedirs(directory)
-    rs_name = f"{file_path}/{file_name}.html"
     try:
         # 打开文件并写入 HTML 内容
-        with open(rs_name, "w", encoding="utf-8") as file:
+        with open(file_path, "w", encoding="utf-8") as file:
             file.write(html_content)
-        print(f"HTML 文件已成功保存到 {rs_name}")
+        print(f"HTML 文件已成功保存到 {file_path}")
     except Exception as e:
         print(f"保存文件时出现错误: {e}")
 
-    return f"{file_name}.html"
+    return f"{file_name}_{current_time}.html"
 
 
 if __name__ == "__main__":