MinerU解析本地文件（二）

一、精准解析 API（需 Token，适合正式场景）

适用场景

• 文件较大（≤ 200MB，≤ 200 页）

• 需要高精度解析

• 支持批量上传（单次 ≤ 50 个）

核心接口

流程

Python 示例

import requests token = "API管理页面自定创建的token" url = "https://mineru.net/api/v4/file-urls/batch" header = { "Content-Type": "application/json", "Authorization": f"Bearer {token}" } data = { "files": [ {"name": "demo.pdf", "data_id": "abcd"} ], "model_version": "vlm" } file_path = ["demo.pdf"] try: # 第一步：申请上传链接 response = requests.post(url, headers=header, json=data) if response.status_code == 200: result = response.json() if result["code"] == 0: batch_id = result["data"]["batch_id"] urls = result["data"]["file_urls"] print(f"batch_id: {batch_id}") # 第二步：上传文件 for i in range(len(urls)): with open(file_path[i], 'rb') as f: res_upload = requests.put(urls[i], data=f) if res_upload.status_code == 200: print(f"{urls[i]} 上传成功") else: print(f"{urls[i]} 上传失败") else: print(f"申请上传链接失败: {result['msg']}") else: print(f"请求失败: {response.status_code}") except Exception as err: print(err)

查询结果

batch_id = "上一步返回的 batch_id" url = f"https://mineru.net/api/v4/extract-results/batch/{batch_id}" header = { "Content-Type": "application/json", "Authorization": f"Bearer {token}" } res = requests.get(url, headers=header) print(res.json())

结果状态：

二、Agent 轻量解析 API（免 Token，适合 Agent 场景）

适用场景

• 文件较小（≤ 10MB，≤ 20 页）

• 快速解析，无需高精度

• 无需登录，IP 限频

• 仅输出 Markdown

核心接口

流程

Python 示例

import requests import time BASE_URL = "https://mineru.net/api/v1/agent" def parse_by_file(file_path, language="ch", page_range=None, enable_table=True, is_ocr=False, enable_formula=True): """通过文件上传提交文档解析任务并等待结果。""" file_name = file_path.split("/")[-1].split("\\")[-1] # 1. 获取签名上传 URL data = { "file_name": file_name, "language": language, "enable_table": enable_table, "is_ocr": is_ocr, "enable_formula": enable_formula } if page_range: data["page_range"] = page_range resp = requests.post(f"{BASE_URL}/parse/file", json=data) result = resp.json() if result["code"] != 0: print(f"获取上传链接失败: {result['msg']}") return None task_id = result["data"]["task_id"] file_url = result["data"]["file_url"] print(f"任务已创建, task_id: {task_id}") # 2. PUT 上传文件到 OSS with open(file_path, "rb") as f: put_resp = requests.put(file_url, data=f) if put_resp.status_code not in (200, 201): print(f"文件上传失败, HTTP {put_resp.status_code}") return None print("文件上传成功，等待解析...") # 3. 轮询等待结果 return poll_result(task_id) def poll_result(task_id, timeout=300, interval=3): """轮询查询解析结果。""" state_labels = { "pending": "排队中", "running": "解析中", "waiting-file": "等待文件上传", } start = time.time() while time.time() - start < timeout: resp = requests.get(f"{BASE_URL}/parse/{task_id}") result = resp.json() state = result["data"]["state"] elapsed = int(time.time() - start) if state == "done": markdown_url = result["data"]["markdown_url"] print(f"[{elapsed}s] 解析完成, Markdown 链接: {markdown_url}") md_resp = requests.get(markdown_url) return md_resp.text if state == "failed": print(f"[{elapsed}s] 解析失败: {result['data'].get('err_msg')}") return None print(f"[{elapsed}s] {state_labels.get(state, state)}...") time.sleep(interval) print(f"轮询超时，请手动查询 task_id: {task_id}") return None # 使用 content = parse_by_file("./document.pdf")

常见错误码