根据 task_id 查询异步任务状态与解析结果
import time
import requests
url = "https://somark.tech/api/v1/parse/async_check"
task_id = "c5e6c983f28a4e6eb5d6c061343a8642"
while True:
response = requests.post(url, data={
"task_id": task_id,
"api_key": "sk-***",
})
result = response.json()
status = result["data"]["status"]
if status == "success":
print(result["data"]["result"])
break
elif status == "failed":
print("解析失败")
break
time.sleep(3){
"code": 0,
"message": "查询成功",
"data": {
"record_id": 12345,
"task_id": "c5e6c983f28a4e6eb5d6c061343a8642",
"status": "success",
"file_name": "document.pdf",
"metadata": {
"page_num": 5,
"file_type": ".pdf"
},
"result": {
"file_name": "document.pdf",
"outputs": {
"markdown": "# 第一章 引言\n\n本文档介绍了...",
"json": {
"pages": [
{
"page_num": 0,
"blocks": [
{
"idx": 0,
"type": "title",
"bbox": [
72,
50,
540,
80
],
"content": "第一章 引言",
"format": "text",
"captions": [],
"img_url": "",
"title_level": 1
},
{
"idx": 1,
"type": "text",
"bbox": [
72,
100,
540,
200
],
"content": "本文档介绍了...",
"format": "text",
"captions": [],
"img_url": ""
}
],
"page_size": {
"h": 1684,
"w": 1190
},
"merge_content_from_pre_page": false
}
]
}
}
}
}
}/extract/async_check 更改为 /parse/async_check。旧路径将于 2026-12-31 停用,请在此之前迁移至新路径。status | 含义 |
|---|---|
queuing | 排队等待处理 |
processing | 解析进行中 |
success | 解析成功,result 字段有值 |
failed | 解析失败 |
status 为 success 或 failed。