智能抽取 - Textin 智能文档解析

general information extration

curl --request POST \
  --url https://api.textin.com/ai/service/v3/entity_extraction \
  --header 'Content-Type: application/json' \
  --header 'x-ti-app-id: <api-key>' \
  --header 'x-ti-secret-code: <api-key>' \
  --data '
{
  "file": {
    "file_base64": "/9j/4AAQSk...",
    "file_url": "https://example.com/document.pdf",
    "file_name": "document.pdf"
  },
  "schema": {
    "type": "object",
    "properties": {
      "商品": {
        "type": "string",
        "description": "商品名称"
      }
    },
    "required": [
      "商品"
    ]
  },
  "parse_options": {
    "page_start": 1,
    "page_count": 10,
    "get_image": "objects",
    "crop_dewarp": 0,
    "remove_watermark": 0,
    "parse_mode": "scan",
    "formula_level": 0,
    "table_flavor": "html",
    "pdf_pwd": "<string>"
  },
  "extract_options": {
    "generate_citations": true,
    "stamp": true
  }
}
'

import requests

url = "https://api.textin.com/ai/service/v3/entity_extraction"

payload = {
    "file": {
        "file_base64": "/9j/4AAQSk...",
        "file_url": "https://example.com/document.pdf",
        "file_name": "document.pdf"
    },
    "schema": {
        "type": "object",
        "properties": { "商品": {
                "type": "string",
                "description": "商品名称"
            } },
        "required": ["商品"]
    },
    "parse_options": {
        "page_start": 1,
        "page_count": 10,
        "get_image": "objects",
        "crop_dewarp": 0,
        "remove_watermark": 0,
        "parse_mode": "scan",
        "formula_level": 0,
        "table_flavor": "html",
        "pdf_pwd": "<string>"
    },
    "extract_options": {
        "generate_citations": True,
        "stamp": True
    }
}
headers = {
    "x-ti-app-id": "<api-key>",
    "x-ti-secret-code": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {
    'x-ti-app-id': '<api-key>',
    'x-ti-secret-code': '<api-key>',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    file: {
      file_base64: '/9j/4AAQSk...',
      file_url: 'https://example.com/document.pdf',
      file_name: 'document.pdf'
    },
    schema: {
      type: 'object',
      properties: {'商品': {type: 'string', description: '商品名称'}},
      required: ['商品']
    },
    parse_options: {
      page_start: 1,
      page_count: 10,
      get_image: 'objects',
      crop_dewarp: 0,
      remove_watermark: 0,
      parse_mode: 'scan',
      formula_level: 0,
      table_flavor: 'html',
      pdf_pwd: '<string>'
    },
    extract_options: {generate_citations: true, stamp: true}
  })
};

fetch('https://api.textin.com/ai/service/v3/entity_extraction', 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://api.textin.com/ai/service/v3/entity_extraction",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'file' => [
        'file_base64' => '/9j/4AAQSk...',
        'file_url' => 'https://example.com/document.pdf',
        'file_name' => 'document.pdf'
    ],
    'schema' => [
        'type' => 'object',
        'properties' => [
                '商品' => [
                                'type' => 'string',
                                'description' => '商品名称'
                ]
        ],
        'required' => [
                '商品'
        ]
    ],
    'parse_options' => [
        'page_start' => 1,
        'page_count' => 10,
        'get_image' => 'objects',
        'crop_dewarp' => 0,
        'remove_watermark' => 0,
        'parse_mode' => 'scan',
        'formula_level' => 0,
        'table_flavor' => 'html',
        'pdf_pwd' => '<string>'
    ],
    'extract_options' => [
        'generate_citations' => true,
        'stamp' => true
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-ti-app-id: <api-key>",
    "x-ti-secret-code: <api-key>"
  ],
]);

$response = curl_exec($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://api.textin.com/ai/service/v3/entity_extraction"

	payload := strings.NewReader("{\n  \"file\": {\n    \"file_base64\": \"/9j/4AAQSk...\",\n    \"file_url\": \"https://example.com/document.pdf\",\n    \"file_name\": \"document.pdf\"\n  },\n  \"schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"商品\": {\n        \"type\": \"string\",\n        \"description\": \"商品名称\"\n      }\n    },\n    \"required\": [\n      \"商品\"\n    ]\n  },\n  \"parse_options\": {\n    \"page_start\": 1,\n    \"page_count\": 10,\n    \"get_image\": \"objects\",\n    \"crop_dewarp\": 0,\n    \"remove_watermark\": 0,\n    \"parse_mode\": \"scan\",\n    \"formula_level\": 0,\n    \"table_flavor\": \"html\",\n    \"pdf_pwd\": \"<string>\"\n  },\n  \"extract_options\": {\n    \"generate_citations\": true,\n    \"stamp\": true\n  }\n}")

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

	req.Header.Add("x-ti-app-id", "<api-key>")
	req.Header.Add("x-ti-secret-code", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.textin.com/ai/service/v3/entity_extraction")
  .header("x-ti-app-id", "<api-key>")
  .header("x-ti-secret-code", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"file\": {\n    \"file_base64\": \"/9j/4AAQSk...\",\n    \"file_url\": \"https://example.com/document.pdf\",\n    \"file_name\": \"document.pdf\"\n  },\n  \"schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"商品\": {\n        \"type\": \"string\",\n        \"description\": \"商品名称\"\n      }\n    },\n    \"required\": [\n      \"商品\"\n    ]\n  },\n  \"parse_options\": {\n    \"page_start\": 1,\n    \"page_count\": 10,\n    \"get_image\": \"objects\",\n    \"crop_dewarp\": 0,\n    \"remove_watermark\": 0,\n    \"parse_mode\": \"scan\",\n    \"formula_level\": 0,\n    \"table_flavor\": \"html\",\n    \"pdf_pwd\": \"<string>\"\n  },\n  \"extract_options\": {\n    \"generate_citations\": true,\n    \"stamp\": true\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.textin.com/ai/service/v3/entity_extraction")

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

request = Net::HTTP::Post.new(url)
request["x-ti-app-id"] = '<api-key>'
request["x-ti-secret-code"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"file\": {\n    \"file_base64\": \"/9j/4AAQSk...\",\n    \"file_url\": \"https://example.com/document.pdf\",\n    \"file_name\": \"document.pdf\"\n  },\n  \"schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"商品\": {\n        \"type\": \"string\",\n        \"description\": \"商品名称\"\n      }\n    },\n    \"required\": [\n      \"商品\"\n    ]\n  },\n  \"parse_options\": {\n    \"page_start\": 1,\n    \"page_count\": 10,\n    \"get_image\": \"objects\",\n    \"crop_dewarp\": 0,\n    \"remove_watermark\": 0,\n    \"parse_mode\": \"scan\",\n    \"formula_level\": 0,\n    \"table_flavor\": \"html\",\n    \"pdf_pwd\": \"<string>\"\n  },\n  \"extract_options\": {\n    \"generate_citations\": true,\n    \"stamp\": true\n  }\n}"

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

{
  "code": 200,
  "message": "Success",
  "version": "v3.0.29_20250819",
  "duration": 8267,
  "x_request_id": "7596b8c9d2ddbc9924b66651e9efc174",
  "status": "finished",
  "result": {
    "success_count": 1,
    "extracted_schema": {
      "商品": "童装 Looney Tunes UT（短袖T恤）女装SUPIMA COTTON圆领T恤（短袖）"
    },
    "citations": {
      "商品": {
        "value": "童装 Looney Tunes UT（短袖T恤）女装SUPIMA COTTON圆领T恤（短袖）",
        "bounding_regions": [
          {
            "page_number": 1,
            "position": [
              137,
              599,
              1129,
              599,
              1129,
              625,
              182,
              625
            ],
            "text": "童装 Looney Tunes UT（短袖T恤）女装SUPIMA COTTON圆领T恤（短袖）"
          }
        ]
      }
    },
    "pages": [
      {
        "page_number": 1,
        "status": "Success",
        "durations": 930.178466796875,
        "image_id": "62bfe3c3a8e9c9cf.jpg",
        "height": 1824,
        "width": 600,
        "angle": 0
      }
    ],
    "stamps": [
      {
        "color": "红色",
        "position": [
          1223,
          995,
          1642,
          1007,
          1630,
          1689,
          1621,
          1677
        ],
        "stamp_shape": "圆章",
        "type": "公章",
        "value": "电力公司专用章"
      }
    ]
  },
  "part_durations": {
    "parse_duration": 1080,
    "retrieve_duration": 0,
    "prompt_duration": 1,
    "llm_duration": 7114,
    "format_duration": 51
  }
}

POST

service

entity_extraction

general information extration

curl --request POST \
  --url https://api.textin.com/ai/service/v3/entity_extraction \
  --header 'Content-Type: application/json' \
  --header 'x-ti-app-id: <api-key>' \
  --header 'x-ti-secret-code: <api-key>' \
  --data '
{
  "file": {
    "file_base64": "/9j/4AAQSk...",
    "file_url": "https://example.com/document.pdf",
    "file_name": "document.pdf"
  },
  "schema": {
    "type": "object",
    "properties": {
      "商品": {
        "type": "string",
        "description": "商品名称"
      }
    },
    "required": [
      "商品"
    ]
  },
  "parse_options": {
    "page_start": 1,
    "page_count": 10,
    "get_image": "objects",
    "crop_dewarp": 0,
    "remove_watermark": 0,
    "parse_mode": "scan",
    "formula_level": 0,
    "table_flavor": "html",
    "pdf_pwd": "<string>"
  },
  "extract_options": {
    "generate_citations": true,
    "stamp": true
  }
}
'

import requests

url = "https://api.textin.com/ai/service/v3/entity_extraction"

payload = {
    "file": {
        "file_base64": "/9j/4AAQSk...",
        "file_url": "https://example.com/document.pdf",
        "file_name": "document.pdf"
    },
    "schema": {
        "type": "object",
        "properties": { "商品": {
                "type": "string",
                "description": "商品名称"
            } },
        "required": ["商品"]
    },
    "parse_options": {
        "page_start": 1,
        "page_count": 10,
        "get_image": "objects",
        "crop_dewarp": 0,
        "remove_watermark": 0,
        "parse_mode": "scan",
        "formula_level": 0,
        "table_flavor": "html",
        "pdf_pwd": "<string>"
    },
    "extract_options": {
        "generate_citations": True,
        "stamp": True
    }
}
headers = {
    "x-ti-app-id": "<api-key>",
    "x-ti-secret-code": "<api-key>",
    "Content-Type": "application/json"
}

response = requests.post(url, json=payload, headers=headers)

print(response.text)

const options = {
  method: 'POST',
  headers: {
    'x-ti-app-id': '<api-key>',
    'x-ti-secret-code': '<api-key>',
    'Content-Type': 'application/json'
  },
  body: JSON.stringify({
    file: {
      file_base64: '/9j/4AAQSk...',
      file_url: 'https://example.com/document.pdf',
      file_name: 'document.pdf'
    },
    schema: {
      type: 'object',
      properties: {'商品': {type: 'string', description: '商品名称'}},
      required: ['商品']
    },
    parse_options: {
      page_start: 1,
      page_count: 10,
      get_image: 'objects',
      crop_dewarp: 0,
      remove_watermark: 0,
      parse_mode: 'scan',
      formula_level: 0,
      table_flavor: 'html',
      pdf_pwd: '<string>'
    },
    extract_options: {generate_citations: true, stamp: true}
  })
};

fetch('https://api.textin.com/ai/service/v3/entity_extraction', 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://api.textin.com/ai/service/v3/entity_extraction",
  CURLOPT_RETURNTRANSFER => true,
  CURLOPT_ENCODING => "",
  CURLOPT_MAXREDIRS => 10,
  CURLOPT_TIMEOUT => 30,
  CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
  CURLOPT_CUSTOMREQUEST => "POST",
  CURLOPT_POSTFIELDS => json_encode([
    'file' => [
        'file_base64' => '/9j/4AAQSk...',
        'file_url' => 'https://example.com/document.pdf',
        'file_name' => 'document.pdf'
    ],
    'schema' => [
        'type' => 'object',
        'properties' => [
                '商品' => [
                                'type' => 'string',
                                'description' => '商品名称'
                ]
        ],
        'required' => [
                '商品'
        ]
    ],
    'parse_options' => [
        'page_start' => 1,
        'page_count' => 10,
        'get_image' => 'objects',
        'crop_dewarp' => 0,
        'remove_watermark' => 0,
        'parse_mode' => 'scan',
        'formula_level' => 0,
        'table_flavor' => 'html',
        'pdf_pwd' => '<string>'
    ],
    'extract_options' => [
        'generate_citations' => true,
        'stamp' => true
    ]
  ]),
  CURLOPT_HTTPHEADER => [
    "Content-Type: application/json",
    "x-ti-app-id: <api-key>",
    "x-ti-secret-code: <api-key>"
  ],
]);

$response = curl_exec($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://api.textin.com/ai/service/v3/entity_extraction"

	payload := strings.NewReader("{\n  \"file\": {\n    \"file_base64\": \"/9j/4AAQSk...\",\n    \"file_url\": \"https://example.com/document.pdf\",\n    \"file_name\": \"document.pdf\"\n  },\n  \"schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"商品\": {\n        \"type\": \"string\",\n        \"description\": \"商品名称\"\n      }\n    },\n    \"required\": [\n      \"商品\"\n    ]\n  },\n  \"parse_options\": {\n    \"page_start\": 1,\n    \"page_count\": 10,\n    \"get_image\": \"objects\",\n    \"crop_dewarp\": 0,\n    \"remove_watermark\": 0,\n    \"parse_mode\": \"scan\",\n    \"formula_level\": 0,\n    \"table_flavor\": \"html\",\n    \"pdf_pwd\": \"<string>\"\n  },\n  \"extract_options\": {\n    \"generate_citations\": true,\n    \"stamp\": true\n  }\n}")

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

	req.Header.Add("x-ti-app-id", "<api-key>")
	req.Header.Add("x-ti-secret-code", "<api-key>")
	req.Header.Add("Content-Type", "application/json")

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

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

	fmt.Println(string(body))

}

HttpResponse<String> response = Unirest.post("https://api.textin.com/ai/service/v3/entity_extraction")
  .header("x-ti-app-id", "<api-key>")
  .header("x-ti-secret-code", "<api-key>")
  .header("Content-Type", "application/json")
  .body("{\n  \"file\": {\n    \"file_base64\": \"/9j/4AAQSk...\",\n    \"file_url\": \"https://example.com/document.pdf\",\n    \"file_name\": \"document.pdf\"\n  },\n  \"schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"商品\": {\n        \"type\": \"string\",\n        \"description\": \"商品名称\"\n      }\n    },\n    \"required\": [\n      \"商品\"\n    ]\n  },\n  \"parse_options\": {\n    \"page_start\": 1,\n    \"page_count\": 10,\n    \"get_image\": \"objects\",\n    \"crop_dewarp\": 0,\n    \"remove_watermark\": 0,\n    \"parse_mode\": \"scan\",\n    \"formula_level\": 0,\n    \"table_flavor\": \"html\",\n    \"pdf_pwd\": \"<string>\"\n  },\n  \"extract_options\": {\n    \"generate_citations\": true,\n    \"stamp\": true\n  }\n}")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.textin.com/ai/service/v3/entity_extraction")

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

request = Net::HTTP::Post.new(url)
request["x-ti-app-id"] = '<api-key>'
request["x-ti-secret-code"] = '<api-key>'
request["Content-Type"] = 'application/json'
request.body = "{\n  \"file\": {\n    \"file_base64\": \"/9j/4AAQSk...\",\n    \"file_url\": \"https://example.com/document.pdf\",\n    \"file_name\": \"document.pdf\"\n  },\n  \"schema\": {\n    \"type\": \"object\",\n    \"properties\": {\n      \"商品\": {\n        \"type\": \"string\",\n        \"description\": \"商品名称\"\n      }\n    },\n    \"required\": [\n      \"商品\"\n    ]\n  },\n  \"parse_options\": {\n    \"page_start\": 1,\n    \"page_count\": 10,\n    \"get_image\": \"objects\",\n    \"crop_dewarp\": 0,\n    \"remove_watermark\": 0,\n    \"parse_mode\": \"scan\",\n    \"formula_level\": 0,\n    \"table_flavor\": \"html\",\n    \"pdf_pwd\": \"<string>\"\n  },\n  \"extract_options\": {\n    \"generate_citations\": true,\n    \"stamp\": true\n  }\n}"

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

{
  "code": 200,
  "message": "Success",
  "version": "v3.0.29_20250819",
  "duration": 8267,
  "x_request_id": "7596b8c9d2ddbc9924b66651e9efc174",
  "status": "finished",
  "result": {
    "success_count": 1,
    "extracted_schema": {
      "商品": "童装 Looney Tunes UT（短袖T恤）女装SUPIMA COTTON圆领T恤（短袖）"
    },
    "citations": {
      "商品": {
        "value": "童装 Looney Tunes UT（短袖T恤）女装SUPIMA COTTON圆领T恤（短袖）",
        "bounding_regions": [
          {
            "page_number": 1,
            "position": [
              137,
              599,
              1129,
              599,
              1129,
              625,
              182,
              625
            ],
            "text": "童装 Looney Tunes UT（短袖T恤）女装SUPIMA COTTON圆领T恤（短袖）"
          }
        ]
      }
    },
    "pages": [
      {
        "page_number": 1,
        "status": "Success",
        "durations": 930.178466796875,
        "image_id": "62bfe3c3a8e9c9cf.jpg",
        "height": 1824,
        "width": 600,
        "angle": 0
      }
    ],
    "stamps": [
      {
        "color": "红色",
        "position": [
          1223,
          995,
          1642,
          1007,
          1630,
          1689,
          1621,
          1677
        ],
        "stamp_shape": "圆章",
        "type": "公章",
        "value": "电力公司专用章"
      }
    ]
  },
  "part_durations": {
    "parse_duration": 1080,
    "retrieve_duration": 0,
    "prompt_duration": 1,
    "llm_duration": 7114,
    "format_duration": 51
  }
}

授权

x-ti-app-id

string

header

必填

请登录Textin后前往 "工作台-账号设置-开发者信息" 查看 x-ti-app-id

x-ti-secret-code

string

header

必填

请登录Textin后前往 "工作台-账号设置-开发者信息" 查看 x-ti-secret-code

请求体

application/json

支持的文件格式：png, jpg, jpeg, pdf, bmp, tiff, webp, doc, docx, html, mhtml, xls, xlsx, csv, ppt, pptx, txt, ofd；

支持schema模式的结构化信息抽取，通过定义字段结构进行精确抽取。

file

object

必填

文件信息

Show child attributes

schema

object

必填

抽取数据结构，参考JSON schema说明

示例:

{
  "type": "object",
  "properties": {
    "商品": { "type": "string", "description": "商品名称" }
  },
  "required": ["商品"]
}

parse_options

object

解析阶段参数

Show child attributes

extract_options

object

高级抽取控制

Show child attributes

响应

200 - application/json

返回结果

code

enum<integer>

必填

状态码

200: Success (成功)
40101: x-ti-app-id 或 x-ti-secret-code 为空
40102: x-ti-app-id 或 x-ti-secret-code 无效，验证失败
40103: 客户端IP不在白名单
40003: 余额不足，请充值后再使用
40004: Parameter error (参数错误，请检查入参）
40007: 机器人不存在或未发布
40008: 机器人未开通，请至市场开通后重试
40302: 上传文件大小不符，文件大小不超过 50M
40303: 文件类型不支持，接口会返回实际检测到的文件类型，如“当前文件类型为.gif”
40304: 图片尺寸不符，长宽比小于2的图片宽高需在20～20000像素范围内，其他图片的宽高需在20～10000像素范围内
40305: File not uploaded (识别文件未上传）
40306: qps超过限制
40400: 无效的请求链接，请检查链接是否正确
40422: The file is corrupted (文件损坏)
40423: Password required or incorrect password (PDF密码错误)
40424: Page number out of range (页面设置超出文件范围）
40425: The input file format is not supported (输入文件格式不支持）
40428: Process office file failed (word和ppt转pdf失败或者超时)
500: Engine failed (服务器内部错误）
50011: LLM Connection Failed （访问大模型超时）
50012: LLM Engine Failed (大模型引擎错误）
50207: Partial failed (部分页面解析失败)

可用选项:

200,

40101,

40102,

40103,

40003,

40004,

40007,

40008,

40302,

40303,

40304,

40305,

40306,

40400,

40422,

40423,

40424,

40425,

40428,

500,

50011,

50012,

50207

示例:

200

message

string

必填

成功或错误信息

示例:

"Success"

version

string

必填

版本号

示例:

"v3.0.29_20250819"

duration

integer

总耗时(ms)

示例:

8267

x_request_id

string

请求ID

示例:

"7596b8c9d2ddbc9924b66651e9efc174"

status

string

处理状态

示例:

"finished"

result

object

Show child attributes

part_durations

object

各阶段耗时统计

Show child attributes

⌘I