同步解析 - SoMark Docs

POST

parse

sync

Python

import json
import requests

url = "https://somark.ai/api/v1/parse/sync"

data = {
    "output_formats": ["markdown", "json"],
    "api_key": "sk-***",
    "element_formats": json.dumps({
        "image": "url",
        "formula": "latex",
        "table": "html",
        "cs": "image",
    }),
    "feature_config": json.dumps({
        "enable_text_cross_page": False,
        "enable_table_cross_page": False,
        "enable_title_level_recognition": False,
        "enable_inline_image": False,
        "enable_table_image": True,
        "enable_image_understanding": True,
        "keep_header_footer": False,
    }),
}

files = {"file": ("example.pdf", open("example.pdf", "rb"))}

response = requests.post(url, data=data, files=files)
print(response.json())

curl -X POST https://somark.ai/api/v1/parse/sync \
  -F "file=@example.pdf" \
  -F "output_formats=markdown" \
  -F "output_formats=json" \
  -F "api_key=sk-***" \
  -F 'element_formats={"image":"url","formula":"latex","table":"html","cs":"image"}' \
  -F 'feature_config={"enable_text_cross_page":false,"enable_table_cross_page":false,"enable_title_level_recognition":false,"enable_inline_image":false,"enable_table_image":true,"enable_image_understanding":true,"keep_header_footer":false}'

const form = new FormData();
form.append('api_key', '<string>');
form.append('file', '<string>');
form.append('file_url', '<string>');
form.append('output_formats[0]', 'markdown');
form.append('output_formats[1]', 'json');
form.append('element_formats', '{
  "image": "url",
  "formula": "latex",
  "table": "html",
  "cs": "image"
}');
form.append('feature_config', '{
  "enable_text_cross_page": false,
  "enable_table_cross_page": false,
  "enable_title_level_recognition": false,
  "enable_inline_image": false,
  "enable_table_image": true,
  "enable_image_understanding": true,
  "keep_header_footer": false
}');

const options = {method: 'POST'};

options.body = form;

fetch('https://somark.ai/api/v1/parse/sync', options)
  .then(res => res.json())
  .then(res => console.log(res))
  .catch(err => console.error(err));

<?php

$curl = curl_init();

curl_setopt_array($curl, [
  CURLOPT_URL => "https://somark.ai/api/v1/parse/sync",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"api_key\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"output_formats%5B0%5D\"\r\n\r\nmarkdown\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"output_formats%5B1%5D\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"element_formats\"\r\n\r\n{\r\n  \"image\": \"url\",\r\n  \"formula\": \"latex\",\r\n  \"table\": \"html\",\r\n  \"cs\": \"image\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"feature_config\"\r\n\r\n{\r\n  \"enable_text_cross_page\": false,\r\n  \"enable_table_cross_page\": false,\r\n  \"enable_title_level_recognition\": false,\r\n  \"enable_inline_image\": false,\r\n  \"enable_table_image\": true,\r\n  \"enable_image_understanding\": true,\r\n  \"keep_header_footer\": false\r\n}\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Content-Type: multipart/form-data; boundary=---011000010111000001101001"
  ],
]);

$response = curl_exec($curl);
$err = curl_error($curl);

curl_close($curl);

if ($err) {
  echo "cURL Error #:" . $err;
} else {
  echo $response;
}

package main

import (
	"fmt"
	"strings"
	"net/http"
	"io"
)

func main() {

	url := "https://somark.ai/api/v1/parse/sync"

	payload := strings.NewReader("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"api_key\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"output_formats%5B0%5D\"\r\n\r\nmarkdown\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"output_formats%5B1%5D\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"element_formats\"\r\n\r\n{\r\n  \"image\": \"url\",\r\n  \"formula\": \"latex\",\r\n  \"table\": \"html\",\r\n  \"cs\": \"image\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"feature_config\"\r\n\r\n{\r\n  \"enable_text_cross_page\": false,\r\n  \"enable_table_cross_page\": false,\r\n  \"enable_title_level_recognition\": false,\r\n  \"enable_inline_image\": false,\r\n  \"enable_table_image\": true,\r\n  \"enable_image_understanding\": true,\r\n  \"keep_header_footer\": false\r\n}\r\n-----011000010111000001101001--")

	req, _ := http.NewRequest("POST", url, payload)

	req.Header.Add("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")

	res, _ := http.DefaultClient.Do(req)

	defer res.Body.Close()
	body, _ := io.ReadAll(res.Body)

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://somark.ai/api/v1/parse/sync")
  .header("Content-Type", "multipart/form-data; boundary=---011000010111000001101001")
  .body("-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"api_key\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"output_formats%5B0%5D\"\r\n\r\nmarkdown\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"output_formats%5B1%5D\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"element_formats\"\r\n\r\n{\r\n  \"image\": \"url\",\r\n  \"formula\": \"latex\",\r\n  \"table\": \"html\",\r\n  \"cs\": \"image\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"feature_config\"\r\n\r\n{\r\n  \"enable_text_cross_page\": false,\r\n  \"enable_table_cross_page\": false,\r\n  \"enable_title_level_recognition\": false,\r\n  \"enable_inline_image\": false,\r\n  \"enable_table_image\": true,\r\n  \"enable_image_understanding\": true,\r\n  \"keep_header_footer\": false\r\n}\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://somark.ai/api/v1/parse/sync")

http = Net::HTTP.new(url.host, url.port)
http.use_ssl = true

request = Net::HTTP::Post.new(url)
request["Content-Type"] = 'multipart/form-data; boundary=---011000010111000001101001'
request.body = "-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"api_key\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file\"; filename=\"example-file\"\r\nContent-Type: application/octet-stream\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"file_url\"\r\n\r\n<string>\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"output_formats%5B0%5D\"\r\n\r\nmarkdown\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"output_formats%5B1%5D\"\r\n\r\njson\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"element_formats\"\r\n\r\n{\r\n  \"image\": \"url\",\r\n  \"formula\": \"latex\",\r\n  \"table\": \"html\",\r\n  \"cs\": \"image\"\r\n}\r\n-----011000010111000001101001\r\nContent-Disposition: form-data; name=\"feature_config\"\r\n\r\n{\r\n  \"enable_text_cross_page\": false,\r\n  \"enable_table_cross_page\": false,\r\n  \"enable_title_level_recognition\": false,\r\n  \"enable_inline_image\": false,\r\n  \"enable_table_image\": true,\r\n  \"enable_image_understanding\": true,\r\n  \"keep_header_footer\": false\r\n}\r\n-----011000010111000001101001--"

response = http.request(request)
puts response.read_body

{
  "code": 0,
  "message": "任务成功",
  "data": {
    "task_id": "a1b2c3d4e5f6",
    "error": null,
    "metadata": {
      "page_num": 10,
      "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
            }
          ]
        }
      }
    }
  }
}

路径变更：该接口路径已从 /extract/acc_sync 更改为 /parse/sync。旧路径将于 2026-12-31 停用，请在此之前迁移至新路径。参数变更：extract_config 已更名为 feature_config。请将请求中的 extract_config 字段替换为 feature_config。

output_formats

可选输出格式	默认值	说明
`json` / `markdown` / `zip`	`["markdown", "json"]`	可多选，不传时使用默认值；`zip` 将 Markdown 和所有图片文件打包为压缩包；在 `output_formats` 包含 `zip` 时，`element_formats.image` 只能是 `file`

element_formats

配置项	可选输出格式	默认值	说明
`image`	`url` / `base64` / `file` / `none`	`url`	单选，image 设定为`file`时，`output_formats`需包含`zip`；`none`表示不返回图片
`formula`	`latex` / `mathml` / `ascii`	`latex`	单选，指定公式的输出格式
`table`	`markdown` / `html` / `image`	`html`	单选，`markdown` 模式下，合并单元格将自动拆分为独立单元格，并以相同内容填充
`cs`	`image`	`image`	单选，化学结构式输出格式，即将支持`smiles`格式

feature_config

配置项	默认值	说明
`enable_text_cross_page`	`false`	文字跨页拼接：跨页文字段合并为连续段落
`enable_table_cross_page`	`false`	表格跨页拼接：跨页表格合并为完整表格
`enable_title_level_recognition`	`false`	标题层级识别：识别文档标题层级结构（H1/H2/H3…）
`enable_inline_image`	`false`	文中图：返回文字段落中的图片
`enable_table_image`	`true`	表中图：返回表格单元格内的图片
`enable_image_understanding`	`true`	图片理解：对文档内图片进行语义理解和结构化描述
`keep_header_footer`	`false`	保留页眉页脚：默认过滤了页眉页脚，如果使用页眉页脚可开启保留

如果你需要了解鉴权、使用限制和同步/异步选择建议，先看 API 概览。大文件、批处理和后台任务建议改走异步解析 — 提交任务。

请求体

multipart/form-data

api_key

string

必填

API 密钥，格式 sk-***

file

待解析的文档文件（与 file_url 二选一）

file_url

string<uri>

待解析文档的下载链接（与 file 二选一）

output_formats

enum<string>[]

输出格式，可多选。不传时默认为 ["markdown", "json"]。支持 json / markdown / zip，其中 zip 将所有输出文件打包为压缩包

可用选项:

json,

markdown,

zip

element_formats

object

元素格式配置，控制各类元素的格式

Show child attributes

feature_config

object

特色功能配置（参数已从 extract_config 更名为 feature_config）

Show child attributes

响应

200 - application/json

解析成功

code

integer

状态码，0 为成功，非 0 见错误码

示例:

0

message

string

示例:

"任务成功"

data

object

Show child attributes

错误码异步解析 — 提交任务