同步解析 - Textin 智能文档解析

文档解析

curl --request POST \
  --url https://api.textin.com/api/v1/xparse/parse/sync \
  --header 'Content-Type: multipart/form-data' \
  --header 'x-ti-app-id: <api-key>' \
  --header 'x-ti-secret-code: <api-key>' \
  --form file='@example-file' \
  --form 'file_url=<string>' \
  --form 'config={
  "document": {
    "password": "example-pdf-password"
  },
  "capabilities": {
    "include_hierarchy": true,
    "include_inline_objects": true,
    "include_char_details": true,
    "include_image_data": true,
    "include_table_structure": true,
    "pages": true,
    "title_tree": true,
    "table_view": "html",
    "remove_watermark": true,
    "crop_dewarp": true
  },
  "scope": {
    "page_range": "1-2"
  },
  "config": {
    "force_engine": "textin",
    "engine_params": {
      "parse_mode": "scan",
      "formula_level": 0,
      "image_output_type": "url",
      "recognize_chemical": true
    }
  }
}'

import requests

url = "https://api.textin.com/api/v1/xparse/parse/sync"

files = { "file": ("example-file", open("example-file", "rb")) }
payload = {
    "file_url": "<string>",
    "config": "{
  \"document\": {
    \"password\": \"example-pdf-password\"
  },
  \"capabilities\": {
    \"include_hierarchy\": true,
    \"include_inline_objects\": true,
    \"include_char_details\": true,
    \"include_image_data\": true,
    \"include_table_structure\": true,
    \"pages\": true,
    \"title_tree\": true,
    \"table_view\": \"html\",
    \"remove_watermark\": true,
    \"crop_dewarp\": true
  },
  \"scope\": {
    \"page_range\": \"1-2\"
  },
  \"config\": {
    \"force_engine\": \"textin\",
    \"engine_params\": {
      \"parse_mode\": \"scan\",
      \"formula_level\": 0,
      \"image_output_type\": \"url\",
      \"recognize_chemical\": true
    }
  }
}"
}
headers = {
    "x-ti-app-id": "<api-key>",
    "x-ti-secret-code": "<api-key>"
}

response = requests.post(url, data=payload, files=files, headers=headers)

print(response.text)

const form = new FormData();
form.append('file', '<string>');
form.append('file_url', '<string>');
form.append('config', '{
  "document": {
    "password": "example-pdf-password"
  },
  "capabilities": {
    "include_hierarchy": true,
    "include_inline_objects": true,
    "include_char_details": true,
    "include_image_data": true,
    "include_table_structure": true,
    "pages": true,
    "title_tree": true,
    "table_view": "html",
    "remove_watermark": true,
    "crop_dewarp": true
  },
  "scope": {
    "page_range": "1-2"
  },
  "config": {
    "force_engine": "textin",
    "engine_params": {
      "parse_mode": "scan",
      "formula_level": 0,
      "image_output_type": "url",
      "recognize_chemical": true
    }
  }
}');

const options = {
  method: 'POST',
  headers: {'x-ti-app-id': '<api-key>', 'x-ti-secret-code': '<api-key>'}
};

options.body = form;

fetch('https://api.textin.com/api/v1/xparse/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://api.textin.com/api/v1/xparse/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=\"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=\"config\"\r\n\r\n{\r\n  \"document\": {\r\n    \"password\": \"example-pdf-password\"\r\n  },\r\n  \"capabilities\": {\r\n    \"include_hierarchy\": true,\r\n    \"include_inline_objects\": true,\r\n    \"include_char_details\": true,\r\n    \"include_image_data\": true,\r\n    \"include_table_structure\": true,\r\n    \"pages\": true,\r\n    \"title_tree\": true,\r\n    \"table_view\": \"html\",\r\n    \"remove_watermark\": true,\r\n    \"crop_dewarp\": true\r\n  },\r\n  \"scope\": {\r\n    \"page_range\": \"1-2\"\r\n  },\r\n  \"config\": {\r\n    \"force_engine\": \"textin\",\r\n    \"engine_params\": {\r\n      \"parse_mode\": \"scan\",\r\n      \"formula_level\": 0,\r\n      \"image_output_type\": \"url\",\r\n      \"recognize_chemical\": true\r\n    }\r\n  }\r\n}\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Content-Type: multipart/form-data",
    "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/api/v1/xparse/parse/sync"

	payload := strings.NewReader("-----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=\"config\"\r\n\r\n{\r\n  \"document\": {\r\n    \"password\": \"example-pdf-password\"\r\n  },\r\n  \"capabilities\": {\r\n    \"include_hierarchy\": true,\r\n    \"include_inline_objects\": true,\r\n    \"include_char_details\": true,\r\n    \"include_image_data\": true,\r\n    \"include_table_structure\": true,\r\n    \"pages\": true,\r\n    \"title_tree\": true,\r\n    \"table_view\": \"html\",\r\n    \"remove_watermark\": true,\r\n    \"crop_dewarp\": true\r\n  },\r\n  \"scope\": {\r\n    \"page_range\": \"1-2\"\r\n  },\r\n  \"config\": {\r\n    \"force_engine\": \"textin\",\r\n    \"engine_params\": {\r\n      \"parse_mode\": \"scan\",\r\n      \"formula_level\": 0,\r\n      \"image_output_type\": \"url\",\r\n      \"recognize_chemical\": true\r\n    }\r\n  }\r\n}\r\n-----011000010111000001101001--")

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

	req.Header.Add("x-ti-app-id", "<api-key>")
	req.Header.Add("x-ti-secret-code", "<api-key>")

	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/api/v1/xparse/parse/sync")
  .header("x-ti-app-id", "<api-key>")
  .header("x-ti-secret-code", "<api-key>")
  .body("-----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=\"config\"\r\n\r\n{\r\n  \"document\": {\r\n    \"password\": \"example-pdf-password\"\r\n  },\r\n  \"capabilities\": {\r\n    \"include_hierarchy\": true,\r\n    \"include_inline_objects\": true,\r\n    \"include_char_details\": true,\r\n    \"include_image_data\": true,\r\n    \"include_table_structure\": true,\r\n    \"pages\": true,\r\n    \"title_tree\": true,\r\n    \"table_view\": \"html\",\r\n    \"remove_watermark\": true,\r\n    \"crop_dewarp\": true\r\n  },\r\n  \"scope\": {\r\n    \"page_range\": \"1-2\"\r\n  },\r\n  \"config\": {\r\n    \"force_engine\": \"textin\",\r\n    \"engine_params\": {\r\n      \"parse_mode\": \"scan\",\r\n      \"formula_level\": 0,\r\n      \"image_output_type\": \"url\",\r\n      \"recognize_chemical\": true\r\n    }\r\n  }\r\n}\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.textin.com/api/v1/xparse/parse/sync")

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.body = "-----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=\"config\"\r\n\r\n{\r\n  \"document\": {\r\n    \"password\": \"example-pdf-password\"\r\n  },\r\n  \"capabilities\": {\r\n    \"include_hierarchy\": true,\r\n    \"include_inline_objects\": true,\r\n    \"include_char_details\": true,\r\n    \"include_image_data\": true,\r\n    \"include_table_structure\": true,\r\n    \"pages\": true,\r\n    \"title_tree\": true,\r\n    \"table_view\": \"html\",\r\n    \"remove_watermark\": true,\r\n    \"crop_dewarp\": true\r\n  },\r\n  \"scope\": {\r\n    \"page_range\": \"1-2\"\r\n  },\r\n  \"config\": {\r\n    \"force_engine\": \"textin\",\r\n    \"engine_params\": {\r\n      \"parse_mode\": \"scan\",\r\n      \"formula_level\": 0,\r\n      \"image_output_type\": \"url\",\r\n      \"recognize_chemical\": true\r\n    }\r\n  }\r\n}\r\n-----011000010111000001101001--"

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

{
  "code": 200,
  "message": "success",
  "data": {
    "schema_version": "1.4.0",
    "file_id": "doc_7f3a2b",
    "job_id": "job_x9k2m",
    "success_count": 2,
    "metadata": {
      "filename": "quarterly_report.pdf",
      "filetype": "application/pdf",
      "page_count": 2,
      "data_source": {
        "record_locator": {
          "protocol": "file",
          "remote_file_path": "/projects/demo/quarterly_report.pdf"
        },
        "url": "file:///projects/demo/quarterly_report.pdf"
      }
    },
    "markdown": "# 检验结果\n\n<table>\n  <thead>\n    <tr><th>项目</th><th>公式项</th><th>参考范围</th></tr>\n  </thead>\n  <tbody>\n    <tr><td>空腹血糖</td><td>x^2+1</td><td>3.9-6.1</td></tr>\n  </tbody>\n</table>\n\n乙方签字：李四\n\n设违约金函数f(x)=x^2+1。\n该违约金函数适用于逾期超过30日的场景。",
    "elements": [
      {
        "element_id": "el_001",
        "type": "Title",
        "text": "检验结果",
        "page_number": 1,
        "coordinates": [
          0.1,
          0.12,
          0.32,
          0.12,
          0.32,
          0.16,
          0.1,
          0.16
        ],
        "metadata": {
          "category_depth": 0,
          "children_ids": [
            "el_002",
            "el_003",
            "el_004",
            "el_005"
          ],
          "is_continuation": false,
          "data_source": {
            "record_locator": {
              "protocol": "file",
              "remote_file_path": "/projects/demo/quarterly_report.pdf"
            },
            "url": "file:///projects/demo/quarterly_report.pdf"
          }
        }
      },
      {
        "element_id": "el_002",
        "type": "Table",
        "text": "项目 公式项 参考范围\n空腹血糖 x^2+1 3.9-6.1",
        "page_number": 1,
        "coordinates": [
          0.1,
          0.2,
          0.82,
          0.2,
          0.82,
          0.36,
          0.1,
          0.36
        ],
        "metadata": {
          "parent_id": "el_001",
          "ref_element_id": "el_001",
          "is_continuation": false,
          "data_source": {
            "record_locator": {
              "protocol": "file",
              "remote_file_path": "/projects/demo/quarterly_report.pdf"
            },
            "url": "file:///projects/demo/quarterly_report.pdf"
          }
        },
        "table_structure": {
          "rows": 2,
          "cols": 3,
          "cells": [
            {
              "cell_id": "tbl_001_r1_c1",
              "row": 1,
              "col": 1,
              "row_span": 1,
              "col_span": 1,
              "content_type": "text",
              "text": "项目",
              "coordinates": [
                0.1,
                0.2,
                0.26,
                0.2,
                0.26,
                0.24,
                0.1,
                0.24
              ]
            },
            {
              "cell_id": "tbl_001_r2_c2",
              "row": 2,
              "col": 2,
              "row_span": 1,
              "col_span": 1,
              "content_type": "formula",
              "text": "x^2+1",
              "coordinates": [
                0.33,
                0.24,
                0.52,
                0.24,
                0.52,
                0.28,
                0.33,
                0.28
              ],
              "char_details": [
                {
                  "index": 0,
                  "text": "x",
                  "coordinates": [
                    0.33,
                    0.24,
                    0.34,
                    0.24,
                    0.34,
                    0.28,
                    0.33,
                    0.28
                  ],
                  "recognition": {
                    "confidence": 0.998,
                    "candidates": [
                      {
                        "text": "8",
                        "confidence": 0.998
                      }
                    ]
                  }
                }
              ]
            }
          ]
        }
      },
      {
        "element_id": "el_003",
        "type": "Image",
        "sub_type": "diagram",
        "text": "",
        "page_number": 1,
        "coordinates": [
          0.56,
          0.2,
          0.8,
          0.2,
          0.8,
          0.34,
          0.56,
          0.34
        ],
        "image_data": {
          "image_url": "https://example.com/fig-1.png",
          "mime_type": "image/png"
        },
        "metadata": {
          "parent_id": "el_001",
          "width": 640,
          "height": 360,
          "data_source": {
            "record_locator": {
              "protocol": "file",
              "remote_file_path": "/projects/demo/quarterly_report.pdf"
            },
            "url": "file:///projects/demo/quarterly_report.pdf"
          }
        }
      },
      {
        "element_id": "el_004",
        "type": "NarrativeText",
        "text": "乙方签字：李四",
        "page_number": 1,
        "coordinates": [
          0.1,
          0.4,
          0.3,
          0.4,
          0.3,
          0.46,
          0.1,
          0.46
        ],
        "metadata": {
          "parent_id": "el_001",
          "has_inline_objects": true,
          "inline_object_types": [
            "handwriting"
          ],
          "is_continuation": false,
          "data_source": {
            "record_locator": {
              "protocol": "file",
              "remote_file_path": "/projects/demo/quarterly_report.pdf"
            },
            "url": "file:///projects/demo/quarterly_report.pdf"
          }
        },
        "objects": [
          {
            "object_id": "obj_001",
            "type": "handwriting",
            "text": "李四",
            "text_range": [
              5,
              7
            ],
            "coordinates": [
              0.18,
              0.4,
              0.26,
              0.4,
              0.26,
              0.46,
              0.18,
              0.46
            ],
            "metadata": {}
          }
        ],
        "char_details": [
          {
            "index": 0,
            "text": "乙",
            "coordinates": [
              0.1,
              0.4,
              0.11,
              0.4,
              0.11,
              0.46,
              0.1,
              0.46
            ],
            "recognition": {
              "confidence": 0.997,
              "candidates": [
                {
                  "text": "乙",
                  "confidence": 0.997
                }
              ]
            }
          }
        ]
      },
      {
        "element_id": "el_005",
        "type": "NarrativeText",
        "text": "设违约金函数f(x)=x^2+1。",
        "page_number": 1,
        "coordinates": [
          0.1,
          0.48,
          0.36,
          0.48,
          0.36,
          0.54,
          0.1,
          0.54
        ],
        "metadata": {
          "parent_id": "el_001",
          "is_continuation": false,
          "has_inline_objects": true,
          "inline_object_types": [
            "formula"
          ],
          "data_source": {
            "record_locator": {
              "protocol": "file",
              "remote_file_path": "/projects/demo/quarterly_report.pdf"
            },
            "url": "file:///projects/demo/quarterly_report.pdf"
          }
        },
        "objects": [
          {
            "object_id": "obj_002",
            "type": "formula",
            "text": "x^2+1",
            "text_range": [
              11,
              16
            ],
            "coordinates": [
              0.22,
              0.48,
              0.3,
              0.48,
              0.3,
              0.54,
              0.22,
              0.54
            ],
            "metadata": {
              "display_mode": "inline"
            }
          }
        ],
        "char_details": [
          {
            "index": 0,
            "text": "设",
            "coordinates": [
              0.1,
              0.48,
              0.11,
              0.48,
              0.11,
              0.54,
              0.1,
              0.54
            ],
            "recognition": {
              "confidence": 0.999,
              "candidates": [
                {
                  "text": "设",
                  "confidence": 0.999
                }
              ]
            }
          }
        ]
      },
      {
        "element_id": "el_006",
        "type": "NarrativeText",
        "text": "该违约金函数适用于逾期超过30日的场景。",
        "page_number": 2,
        "coordinates": [
          0.1,
          0.1,
          0.44,
          0.1,
          0.44,
          0.16,
          0.1,
          0.16
        ],
        "metadata": {
          "is_continuation": true,
          "continuation_of": "el_005",
          "data_source": {
            "record_locator": {
              "protocol": "file",
              "remote_file_path": "/projects/demo/quarterly_report.pdf"
            },
            "url": "file:///projects/demo/quarterly_report.pdf"
          }
        }
      }
    ],
    "title_tree": [
      {
        "element_id": "el_001",
        "title": "检验结果",
        "level": 1,
        "page_number": 1,
        "children": []
      }
    ],
    "pages": [
      {
        "page_number": 1,
        "page_width": 1576,
        "page_height": 1683,
        "page_image_url": "https://example.com/page-1.jpg",
        "element_ids": [
          "el_001",
          "el_002",
          "el_003",
          "el_004",
          "el_005"
        ],
        "dpi": 144,
        "angle": 0,
        "status": "Success"
      },
      {
        "page_number": 2,
        "page_width": 1576,
        "page_height": 1683,
        "page_image_url": "https://example.com/page-2.jpg",
        "element_ids": [
          "el_006"
        ],
        "dpi": 144,
        "angle": 0,
        "status": "Success"
      }
    ],
    "summary": {
      "duration_ms": 812
    }
  }
}

POST

api

xparse

parse

sync

文档解析

curl --request POST \
  --url https://api.textin.com/api/v1/xparse/parse/sync \
  --header 'Content-Type: multipart/form-data' \
  --header 'x-ti-app-id: <api-key>' \
  --header 'x-ti-secret-code: <api-key>' \
  --form file='@example-file' \
  --form 'file_url=<string>' \
  --form 'config={
  "document": {
    "password": "example-pdf-password"
  },
  "capabilities": {
    "include_hierarchy": true,
    "include_inline_objects": true,
    "include_char_details": true,
    "include_image_data": true,
    "include_table_structure": true,
    "pages": true,
    "title_tree": true,
    "table_view": "html",
    "remove_watermark": true,
    "crop_dewarp": true
  },
  "scope": {
    "page_range": "1-2"
  },
  "config": {
    "force_engine": "textin",
    "engine_params": {
      "parse_mode": "scan",
      "formula_level": 0,
      "image_output_type": "url",
      "recognize_chemical": true
    }
  }
}'

import requests

url = "https://api.textin.com/api/v1/xparse/parse/sync"

files = { "file": ("example-file", open("example-file", "rb")) }
payload = {
    "file_url": "<string>",
    "config": "{
  \"document\": {
    \"password\": \"example-pdf-password\"
  },
  \"capabilities\": {
    \"include_hierarchy\": true,
    \"include_inline_objects\": true,
    \"include_char_details\": true,
    \"include_image_data\": true,
    \"include_table_structure\": true,
    \"pages\": true,
    \"title_tree\": true,
    \"table_view\": \"html\",
    \"remove_watermark\": true,
    \"crop_dewarp\": true
  },
  \"scope\": {
    \"page_range\": \"1-2\"
  },
  \"config\": {
    \"force_engine\": \"textin\",
    \"engine_params\": {
      \"parse_mode\": \"scan\",
      \"formula_level\": 0,
      \"image_output_type\": \"url\",
      \"recognize_chemical\": true
    }
  }
}"
}
headers = {
    "x-ti-app-id": "<api-key>",
    "x-ti-secret-code": "<api-key>"
}

response = requests.post(url, data=payload, files=files, headers=headers)

print(response.text)

const form = new FormData();
form.append('file', '<string>');
form.append('file_url', '<string>');
form.append('config', '{
  "document": {
    "password": "example-pdf-password"
  },
  "capabilities": {
    "include_hierarchy": true,
    "include_inline_objects": true,
    "include_char_details": true,
    "include_image_data": true,
    "include_table_structure": true,
    "pages": true,
    "title_tree": true,
    "table_view": "html",
    "remove_watermark": true,
    "crop_dewarp": true
  },
  "scope": {
    "page_range": "1-2"
  },
  "config": {
    "force_engine": "textin",
    "engine_params": {
      "parse_mode": "scan",
      "formula_level": 0,
      "image_output_type": "url",
      "recognize_chemical": true
    }
  }
}');

const options = {
  method: 'POST',
  headers: {'x-ti-app-id': '<api-key>', 'x-ti-secret-code': '<api-key>'}
};

options.body = form;

fetch('https://api.textin.com/api/v1/xparse/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://api.textin.com/api/v1/xparse/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=\"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=\"config\"\r\n\r\n{\r\n  \"document\": {\r\n    \"password\": \"example-pdf-password\"\r\n  },\r\n  \"capabilities\": {\r\n    \"include_hierarchy\": true,\r\n    \"include_inline_objects\": true,\r\n    \"include_char_details\": true,\r\n    \"include_image_data\": true,\r\n    \"include_table_structure\": true,\r\n    \"pages\": true,\r\n    \"title_tree\": true,\r\n    \"table_view\": \"html\",\r\n    \"remove_watermark\": true,\r\n    \"crop_dewarp\": true\r\n  },\r\n  \"scope\": {\r\n    \"page_range\": \"1-2\"\r\n  },\r\n  \"config\": {\r\n    \"force_engine\": \"textin\",\r\n    \"engine_params\": {\r\n      \"parse_mode\": \"scan\",\r\n      \"formula_level\": 0,\r\n      \"image_output_type\": \"url\",\r\n      \"recognize_chemical\": true\r\n    }\r\n  }\r\n}\r\n-----011000010111000001101001--",
  CURLOPT_HTTPHEADER => [
    "Content-Type: multipart/form-data",
    "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/api/v1/xparse/parse/sync"

	payload := strings.NewReader("-----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=\"config\"\r\n\r\n{\r\n  \"document\": {\r\n    \"password\": \"example-pdf-password\"\r\n  },\r\n  \"capabilities\": {\r\n    \"include_hierarchy\": true,\r\n    \"include_inline_objects\": true,\r\n    \"include_char_details\": true,\r\n    \"include_image_data\": true,\r\n    \"include_table_structure\": true,\r\n    \"pages\": true,\r\n    \"title_tree\": true,\r\n    \"table_view\": \"html\",\r\n    \"remove_watermark\": true,\r\n    \"crop_dewarp\": true\r\n  },\r\n  \"scope\": {\r\n    \"page_range\": \"1-2\"\r\n  },\r\n  \"config\": {\r\n    \"force_engine\": \"textin\",\r\n    \"engine_params\": {\r\n      \"parse_mode\": \"scan\",\r\n      \"formula_level\": 0,\r\n      \"image_output_type\": \"url\",\r\n      \"recognize_chemical\": true\r\n    }\r\n  }\r\n}\r\n-----011000010111000001101001--")

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

	req.Header.Add("x-ti-app-id", "<api-key>")
	req.Header.Add("x-ti-secret-code", "<api-key>")

	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/api/v1/xparse/parse/sync")
  .header("x-ti-app-id", "<api-key>")
  .header("x-ti-secret-code", "<api-key>")
  .body("-----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=\"config\"\r\n\r\n{\r\n  \"document\": {\r\n    \"password\": \"example-pdf-password\"\r\n  },\r\n  \"capabilities\": {\r\n    \"include_hierarchy\": true,\r\n    \"include_inline_objects\": true,\r\n    \"include_char_details\": true,\r\n    \"include_image_data\": true,\r\n    \"include_table_structure\": true,\r\n    \"pages\": true,\r\n    \"title_tree\": true,\r\n    \"table_view\": \"html\",\r\n    \"remove_watermark\": true,\r\n    \"crop_dewarp\": true\r\n  },\r\n  \"scope\": {\r\n    \"page_range\": \"1-2\"\r\n  },\r\n  \"config\": {\r\n    \"force_engine\": \"textin\",\r\n    \"engine_params\": {\r\n      \"parse_mode\": \"scan\",\r\n      \"formula_level\": 0,\r\n      \"image_output_type\": \"url\",\r\n      \"recognize_chemical\": true\r\n    }\r\n  }\r\n}\r\n-----011000010111000001101001--")
  .asString();

require 'uri'
require 'net/http'

url = URI("https://api.textin.com/api/v1/xparse/parse/sync")

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.body = "-----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=\"config\"\r\n\r\n{\r\n  \"document\": {\r\n    \"password\": \"example-pdf-password\"\r\n  },\r\n  \"capabilities\": {\r\n    \"include_hierarchy\": true,\r\n    \"include_inline_objects\": true,\r\n    \"include_char_details\": true,\r\n    \"include_image_data\": true,\r\n    \"include_table_structure\": true,\r\n    \"pages\": true,\r\n    \"title_tree\": true,\r\n    \"table_view\": \"html\",\r\n    \"remove_watermark\": true,\r\n    \"crop_dewarp\": true\r\n  },\r\n  \"scope\": {\r\n    \"page_range\": \"1-2\"\r\n  },\r\n  \"config\": {\r\n    \"force_engine\": \"textin\",\r\n    \"engine_params\": {\r\n      \"parse_mode\": \"scan\",\r\n      \"formula_level\": 0,\r\n      \"image_output_type\": \"url\",\r\n      \"recognize_chemical\": true\r\n    }\r\n  }\r\n}\r\n-----011000010111000001101001--"

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

{
  "code": 200,
  "message": "success",
  "data": {
    "schema_version": "1.4.0",
    "file_id": "doc_7f3a2b",
    "job_id": "job_x9k2m",
    "success_count": 2,
    "metadata": {
      "filename": "quarterly_report.pdf",
      "filetype": "application/pdf",
      "page_count": 2,
      "data_source": {
        "record_locator": {
          "protocol": "file",
          "remote_file_path": "/projects/demo/quarterly_report.pdf"
        },
        "url": "file:///projects/demo/quarterly_report.pdf"
      }
    },
    "markdown": "# 检验结果\n\n<table>\n  <thead>\n    <tr><th>项目</th><th>公式项</th><th>参考范围</th></tr>\n  </thead>\n  <tbody>\n    <tr><td>空腹血糖</td><td>x^2+1</td><td>3.9-6.1</td></tr>\n  </tbody>\n</table>\n\n乙方签字：李四\n\n设违约金函数f(x)=x^2+1。\n该违约金函数适用于逾期超过30日的场景。",
    "elements": [
      {
        "element_id": "el_001",
        "type": "Title",
        "text": "检验结果",
        "page_number": 1,
        "coordinates": [
          0.1,
          0.12,
          0.32,
          0.12,
          0.32,
          0.16,
          0.1,
          0.16
        ],
        "metadata": {
          "category_depth": 0,
          "children_ids": [
            "el_002",
            "el_003",
            "el_004",
            "el_005"
          ],
          "is_continuation": false,
          "data_source": {
            "record_locator": {
              "protocol": "file",
              "remote_file_path": "/projects/demo/quarterly_report.pdf"
            },
            "url": "file:///projects/demo/quarterly_report.pdf"
          }
        }
      },
      {
        "element_id": "el_002",
        "type": "Table",
        "text": "项目 公式项 参考范围\n空腹血糖 x^2+1 3.9-6.1",
        "page_number": 1,
        "coordinates": [
          0.1,
          0.2,
          0.82,
          0.2,
          0.82,
          0.36,
          0.1,
          0.36
        ],
        "metadata": {
          "parent_id": "el_001",
          "ref_element_id": "el_001",
          "is_continuation": false,
          "data_source": {
            "record_locator": {
              "protocol": "file",
              "remote_file_path": "/projects/demo/quarterly_report.pdf"
            },
            "url": "file:///projects/demo/quarterly_report.pdf"
          }
        },
        "table_structure": {
          "rows": 2,
          "cols": 3,
          "cells": [
            {
              "cell_id": "tbl_001_r1_c1",
              "row": 1,
              "col": 1,
              "row_span": 1,
              "col_span": 1,
              "content_type": "text",
              "text": "项目",
              "coordinates": [
                0.1,
                0.2,
                0.26,
                0.2,
                0.26,
                0.24,
                0.1,
                0.24
              ]
            },
            {
              "cell_id": "tbl_001_r2_c2",
              "row": 2,
              "col": 2,
              "row_span": 1,
              "col_span": 1,
              "content_type": "formula",
              "text": "x^2+1",
              "coordinates": [
                0.33,
                0.24,
                0.52,
                0.24,
                0.52,
                0.28,
                0.33,
                0.28
              ],
              "char_details": [
                {
                  "index": 0,
                  "text": "x",
                  "coordinates": [
                    0.33,
                    0.24,
                    0.34,
                    0.24,
                    0.34,
                    0.28,
                    0.33,
                    0.28
                  ],
                  "recognition": {
                    "confidence": 0.998,
                    "candidates": [
                      {
                        "text": "8",
                        "confidence": 0.998
                      }
                    ]
                  }
                }
              ]
            }
          ]
        }
      },
      {
        "element_id": "el_003",
        "type": "Image",
        "sub_type": "diagram",
        "text": "",
        "page_number": 1,
        "coordinates": [
          0.56,
          0.2,
          0.8,
          0.2,
          0.8,
          0.34,
          0.56,
          0.34
        ],
        "image_data": {
          "image_url": "https://example.com/fig-1.png",
          "mime_type": "image/png"
        },
        "metadata": {
          "parent_id": "el_001",
          "width": 640,
          "height": 360,
          "data_source": {
            "record_locator": {
              "protocol": "file",
              "remote_file_path": "/projects/demo/quarterly_report.pdf"
            },
            "url": "file:///projects/demo/quarterly_report.pdf"
          }
        }
      },
      {
        "element_id": "el_004",
        "type": "NarrativeText",
        "text": "乙方签字：李四",
        "page_number": 1,
        "coordinates": [
          0.1,
          0.4,
          0.3,
          0.4,
          0.3,
          0.46,
          0.1,
          0.46
        ],
        "metadata": {
          "parent_id": "el_001",
          "has_inline_objects": true,
          "inline_object_types": [
            "handwriting"
          ],
          "is_continuation": false,
          "data_source": {
            "record_locator": {
              "protocol": "file",
              "remote_file_path": "/projects/demo/quarterly_report.pdf"
            },
            "url": "file:///projects/demo/quarterly_report.pdf"
          }
        },
        "objects": [
          {
            "object_id": "obj_001",
            "type": "handwriting",
            "text": "李四",
            "text_range": [
              5,
              7
            ],
            "coordinates": [
              0.18,
              0.4,
              0.26,
              0.4,
              0.26,
              0.46,
              0.18,
              0.46
            ],
            "metadata": {}
          }
        ],
        "char_details": [
          {
            "index": 0,
            "text": "乙",
            "coordinates": [
              0.1,
              0.4,
              0.11,
              0.4,
              0.11,
              0.46,
              0.1,
              0.46
            ],
            "recognition": {
              "confidence": 0.997,
              "candidates": [
                {
                  "text": "乙",
                  "confidence": 0.997
                }
              ]
            }
          }
        ]
      },
      {
        "element_id": "el_005",
        "type": "NarrativeText",
        "text": "设违约金函数f(x)=x^2+1。",
        "page_number": 1,
        "coordinates": [
          0.1,
          0.48,
          0.36,
          0.48,
          0.36,
          0.54,
          0.1,
          0.54
        ],
        "metadata": {
          "parent_id": "el_001",
          "is_continuation": false,
          "has_inline_objects": true,
          "inline_object_types": [
            "formula"
          ],
          "data_source": {
            "record_locator": {
              "protocol": "file",
              "remote_file_path": "/projects/demo/quarterly_report.pdf"
            },
            "url": "file:///projects/demo/quarterly_report.pdf"
          }
        },
        "objects": [
          {
            "object_id": "obj_002",
            "type": "formula",
            "text": "x^2+1",
            "text_range": [
              11,
              16
            ],
            "coordinates": [
              0.22,
              0.48,
              0.3,
              0.48,
              0.3,
              0.54,
              0.22,
              0.54
            ],
            "metadata": {
              "display_mode": "inline"
            }
          }
        ],
        "char_details": [
          {
            "index": 0,
            "text": "设",
            "coordinates": [
              0.1,
              0.48,
              0.11,
              0.48,
              0.11,
              0.54,
              0.1,
              0.54
            ],
            "recognition": {
              "confidence": 0.999,
              "candidates": [
                {
                  "text": "设",
                  "confidence": 0.999
                }
              ]
            }
          }
        ]
      },
      {
        "element_id": "el_006",
        "type": "NarrativeText",
        "text": "该违约金函数适用于逾期超过30日的场景。",
        "page_number": 2,
        "coordinates": [
          0.1,
          0.1,
          0.44,
          0.1,
          0.44,
          0.16,
          0.1,
          0.16
        ],
        "metadata": {
          "is_continuation": true,
          "continuation_of": "el_005",
          "data_source": {
            "record_locator": {
              "protocol": "file",
              "remote_file_path": "/projects/demo/quarterly_report.pdf"
            },
            "url": "file:///projects/demo/quarterly_report.pdf"
          }
        }
      }
    ],
    "title_tree": [
      {
        "element_id": "el_001",
        "title": "检验结果",
        "level": 1,
        "page_number": 1,
        "children": []
      }
    ],
    "pages": [
      {
        "page_number": 1,
        "page_width": 1576,
        "page_height": 1683,
        "page_image_url": "https://example.com/page-1.jpg",
        "element_ids": [
          "el_001",
          "el_002",
          "el_003",
          "el_004",
          "el_005"
        ],
        "dpi": 144,
        "angle": 0,
        "status": "Success"
      },
      {
        "page_number": 2,
        "page_width": 1576,
        "page_height": 1683,
        "page_image_url": "https://example.com/page-2.jpg",
        "element_ids": [
          "el_006"
        ],
        "dpi": 144,
        "angle": 0,
        "status": "Success"
      }
    ],
    "summary": {
      "duration_ms": 812
    }
  }
}

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

multipart/form-data

file

上传文档文件，与 file_url 二选一

file_url

string

文档 URL，与 file 二选一

config

object

解析参数配置

Show child attributes

示例:

{
  "document": { "password": "example-pdf-password" },
  "capabilities": {
    "include_hierarchy": true,
    "include_inline_objects": true,
    "include_char_details": true,
    "include_image_data": true,
    "include_table_structure": true,
    "pages": true,
    "title_tree": true,
    "table_view": "html",
    "remove_watermark": true,
    "crop_dewarp": true
  },
  "scope": { "page_range": "1-2" },
  "config": {
    "force_engine": "textin",
    "engine_params": {
      "parse_mode": "scan",
      "formula_level": 0,
      "image_output_type": "url",
      "recognize_chemical": true
    }
  }
}

响应

解析结果

code

enum<integer>

必填

状态码

200: 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: 参数错误，请查看技术文档，检查传参
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
40301: 图片类型不支持
40302: 上传文件大小不符，文件大小不超过 500M
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: 识别文件未上传
40306: qps超过限制
40307: 今日免费额度已用完
40422: 文件损坏（The file is corrupted.）
40423: PDF密码错误（Password required or incorrect password.）
40424: 页数设置超出文件范围（Page number out of range.）
40425: 文件格式不支持（The input file format is not supported.）
40427: DPI参数不在支持列表中（Input DPI is not in the allowed DPIs list(72,144,216).）
40428: word和ppt转pdf失败或者超时（Process office file failed.）
40429: 不支持的引擎（Unsupported Engine.）
50207: 部分页面解析失败（Partial failed）
40400: 无效的请求链接，请检查链接是否正确
30203: 基础服务故障，请稍后重试
500: 服务器内部错误

可用选项:

200,

40101,

40102,

40103,

40003,

40004,

40007,

40008,

40301,

40302,

40303,

40304,

40305,

40306,

40307,

40422,

40423,

40424,

40425,

40427,

40428,

40429,

50207,

40400,

30203,

500

示例:

200

message

string

必填

状态信息

示例:

"success"

location

object

错误定位信息，仅在解析错误时返回

Show child attributes

data

object

Show child attributes

⌘I