62 lines
2.0 KiB
Python
62 lines
2.0 KiB
Python
import httpx
|
|
import os
|
|
|
|
|
|
async def process_pdf_logic(pdf_file):
|
|
"""
|
|
接收 PDF 文件并转发到解析服务
|
|
"""
|
|
# 验证文件类型
|
|
if not pdf_file.content_type.startswith("application/pdf"):
|
|
raise Exception(400, "仅支持 PDF 文件")
|
|
|
|
try:
|
|
# 读取文件内容
|
|
# file_content = await pdf_file.read()
|
|
|
|
# 配置目标接口参数
|
|
target_url = os.getenv("Mineru_URL","http://172.18.30.122:9988")
|
|
target_url = target_url + "/analyze-pdf"
|
|
# target_url = os.getenv("Mineru_URL","http://172.18.127.124:9088/pdf_parse")
|
|
# target_url = "http://172.18.30.122:8998/pdf_parse"
|
|
# params = {
|
|
# "parse_method": "auto",
|
|
# "is_json_md_dump": "true",
|
|
# "output_dir": "output"
|
|
# }
|
|
|
|
# 构建文件上传格式
|
|
files = {
|
|
"file": (pdf_file.filename, pdf_file.file, "application/pdf")
|
|
# "pdf_file": (pdf_file.filename, pdf_file.file, "application/pdf")
|
|
}
|
|
|
|
# 发送请求到解析服务
|
|
async with httpx.AsyncClient(timeout=120.0) as client:
|
|
response = await client.post(
|
|
target_url,
|
|
# params=params,
|
|
files=files,
|
|
headers={"Accept": "application/json"}
|
|
)
|
|
response.raise_for_status()
|
|
result = response.json()
|
|
|
|
content_list = result["data"]["full_content"]
|
|
# markdown_content =""
|
|
# for content in content_list:
|
|
# text = content["text"]
|
|
|
|
return content_list
|
|
|
|
except httpx.RequestError as e:
|
|
raise Exception(503, f"无法连接到解析服务: {str(e)}")
|
|
except Exception as e:
|
|
raise Exception(500, f"服务器内部错误: {str(e)}")
|
|
|
|
if __name__ == "__main__":
|
|
# 测试：传入 PDF 文件路径
|
|
result = process_pdf_logic("邱茜茜.pdf")
|
|
print(result)
|
|
# with open("邱茜茜.md", "w", encoding="utf-8") as f:
|
|
# f.write(result) |