文档转换成 txt

将文档格式转换成 txt

基本信息

请求路径：POST /api/developer/v1/office/convert/to/txt

目前支持的文档类型

文档类型	扩展名
演示	.pptx .ppt
WPS 文字	.docx .doc
WPS 表格	.xlsx .xls
WPS PDF	.pdf

Header 参数

参数	必须	类型	说明
Date	是	string	使用 RFC1123 时间格式的当前时间
Content-Md5	是	string	HTTP Body 中数据的 MD5 值十六进制表达方式, 必需小写, 如果是 get 请求一律使用 URI 计算 MD5
Content-Type	是	string	目前固定为: application/json
Authorization	是	string	"WPS-2:" + app_id + ":" + sha1( app_key + Content-Md5 + Content-Type + DATE)

Body 参数

参数	必须	类型	说明
url	是	string	文档下载地址
filename	是	string	文档名称，包含扩展名，例如：说明文档.pdf
password	否	string	文档打开密码(如果文档有加密，该项则必填)
long_txt	否	bool	是否转换成长文本，设置为 true 时，可以将需要导出的页中的文字合并导出。默认值为 false，按页导出 txt
hold_line_feed	否	bool	转换 txt 时是否保留文档中的换行符，设置为 true 时，导出内容包含换行符。默认值为 false，导出内容不包含换行。
ranges	否	string	自定义需要转换的分页范围，例如："1,2-4,7"，则表示转换文档的 1、2、3、4、7 页面 (与 from_page和to_page 互斥)
from_page	否	int	转换起始页，从 1 开始计数(与 ranges互斥)
to_page	否	int	转换结束页，需要大于 from_page， (与 ranges互斥)

返回参数

参数	必须	类型	说明
code	是	integer	错误码
+ data	是	data {}	响应数据
task_id	是	string	转换任务 id

示例

请求示例

Shell

curl --request POST \
	--url https://solution.wps.cn/api/developer/v1/office/convert/to/txt \
	--header 'Authorization: WPS-2:******:ac59dac1460772a04b3a97d7ef78409f28241e3a' \
	--header 'Content-Md5: d41d8cd98f00b204e9800998ecf8427e' \
	--header 'Content-Type: application/json' \
	--header 'Date: Wed, 23 Jan 2013 06:43:08 GMT' \
	--data '{"url":"https://***.com/***","filename":"说明文档.pdf","long_txt":true}'

Java

OkHttpClient client = new OkHttpClient();

MediaType mediaType = MediaType.parse("application/json");
RequestBody body = RequestBody.create(mediaType, "{\"url\":\"https://***.com/***\",\"filename\":\"说明文档.pdf\",\"long_txt\":true}");
Request request = new Request.Builder()
	.url("https://solution.wps.cn/api/developer/v1/office/convert/to/txt")
	.post(body)
	.addHeader("Date", "Wed, 23 Jan 2013 06:43:08 GMT")
	.addHeader("Content-Md5", "d41d8cd98f00b204e9800998ecf8427e")
	.addHeader("Content-Type", "application/json")
	.addHeader("Authorization", "WPS-2:******:ac59dac1460772a04b3a97d7ef78409f28241e3a")
	.build();

Response response = client.newCall(request).execute();

Go

package main

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

func main() {

	url := "https://solution.wps.cn/api/developer/v1/office/convert/to/txt"

	payload := strings.NewReader("{\"url\":\"https://***.com/***\",\"filename\":\"说明文档.pdf\",\"long_txt\":true}")

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

	req.Header.Add("Date", "Wed, 23 Jan 2013 06:43:08 GMT")
	req.Header.Add("Content-Md5", "d41d8cd98f00b204e9800998ecf8427e")
	req.Header.Add("Content-Type", "application/json")
	req.Header.Add("Authorization", "WPS-2:******:ac59dac1460772a04b3a97d7ef78409f28241e3a")

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

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

	fmt.Println(res)
	fmt.Println(string(body))

}

Python

import http.client

conn = http.client.HTTPSConnection("solution.wps.cn")

payload = "{\"url\":\"https://***.com/***\",\"filename\":\"说明文档.pdf\",\"long_txt\":true}"

headers = {
    'Date': "Wed, 23 Jan 2013 06:43:08 GMT",
    'Content-Md5': "d41d8cd98f00b204e9800998ecf8427e",
    'Content-Type': "application/json",
    'Authorization': "WPS-2:******:ac59dac1460772a04b3a97d7ef78409f28241e3a"
    }

conn.request("POST", "/api/developer/v1/office/convert/to/txt", payload, headers)

res = conn.getresponse()
data = res.read()

print(data.decode("utf-8"))

PHP

<?php

$curl = curl_init();

curl_setopt_array($curl, [
	CURLOPT_URL => "https://solution.wps.cn/api/developer/v1/office/convert/to/txt",
	CURLOPT_RETURNTRANSFER => true,
	CURLOPT_ENCODING => "",
	CURLOPT_MAXREDIRS => 10,
	CURLOPT_TIMEOUT => 30,
	CURLOPT_HTTP_VERSION => CURL_HTTP_VERSION_1_1,
	CURLOPT_CUSTOMREQUEST => "POST",
	CURLOPT_POSTFIELDS => "{\"url\":\"https://***.com/***\",\"filename\":\"说明文档.pdf\",\"long_txt\":true}",
	CURLOPT_HTTPHEADER => [
		"Authorization: WPS-2:******:ac59dac1460772a04b3a97d7ef78409f28241e3a",
		"Content-Md5: d41d8cd98f00b204e9800998ecf8427e",
		"Content-Type: application/json",
		"Date: Wed, 23 Jan 2013 06:43:08 GMT"
	],
]);

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

curl_close($curl);

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

JS

const data = JSON.stringify({
	"url": "https://***.com/***",
	"filename": "说明文档.pdf",
	"long_txt": true
});

const xhr = new XMLHttpRequest();
xhr.withCredentials = true;

xhr.addEventListener("readystatechange", function () {
	if (this.readyState === this.DONE) {
		console.log(this.responseText);
	}
});

xhr.open("POST", "https://solution.wps.cn/api/developer/v1/office/convert/to/txt");
xhr.setRequestHeader("Date", "Wed, 23 Jan 2013 06:43:08 GMT");
xhr.setRequestHeader("Content-Md5", "d41d8cd98f00b204e9800998ecf8427e");
xhr.setRequestHeader("Content-Type", "application/json");
xhr.setRequestHeader("Authorization", "WPS-2:******:ac59dac1460772a04b3a97d7ef78409f28241e3a");

xhr.send(data);

Node.js

const http = require("https");

const options = {
	"method": "POST",
	"hostname": "solution.wps.cn",
	"port": null,
	"path": "/api/developer/v1/office/convert/to/txt",
	"headers": {
		"Date": "Wed, 23 Jan 2013 06:43:08 GMT",
		"Content-Md5": "d41d8cd98f00b204e9800998ecf8427e",
		"Content-Type": "application/json",
		"Authorization": "WPS-2:******:ac59dac1460772a04b3a97d7ef78409f28241e3a"
	}
};

const req = http.request(options, function (res) {
	const chunks = [];

	res.on("data", function (chunk) {
		chunks.push(chunk);
	});

	res.on("end", function () {
		const body = Buffer.concat(chunks);
		console.log(body.toString());
	});
});

req.write(JSON.stringify({url: 'https://***.com/***', filename: '说明文档.pdf', long_txt: true}));
req.end();

C

CURL *hnd = curl_easy_init();

curl_easy_setopt(hnd, CURLOPT_CUSTOMREQUEST, "POST");
curl_easy_setopt(hnd, CURLOPT_URL, "https://solution.wps.cn/api/developer/v1/office/convert/to/txt");

struct curl_slist *headers = NULL;
headers = curl_slist_append(headers, "Date: Wed, 23 Jan 2013 06:43:08 GMT");
headers = curl_slist_append(headers, "Content-Md5: d41d8cd98f00b204e9800998ecf8427e");
headers = curl_slist_append(headers, "Content-Type: application/json");
headers = curl_slist_append(headers, "Authorization: WPS-2:******:ac59dac1460772a04b3a97d7ef78409f28241e3a");
curl_easy_setopt(hnd, CURLOPT_HTTPHEADER, headers);

curl_easy_setopt(hnd, CURLOPT_POSTFIELDS, "{\"url\":\"https://***.com/***\",\"filename\":\"说明文档.pdf\",\"long_txt\":true}");

CURLcode ret = curl_easy_perform(hnd);

C#

var client = new RestClient("https://solution.wps.cn/api/developer/v1/office/convert/to/txt");
var request = new RestRequest(Method.POST);
request.AddHeader("Date", "Wed, 23 Jan 2013 06:43:08 GMT");
request.AddHeader("Content-Md5", "d41d8cd98f00b204e9800998ecf8427e");
request.AddHeader("Content-Type", "application/json");
request.AddHeader("Authorization", "WPS-2:******:ac59dac1460772a04b3a97d7ef78409f28241e3a");
request.AddParameter("application/json", "{\"url\":\"https://***.com/***\",\"filename\":\"说明文档.pdf\",\"long_txt\":true}", ParameterType.RequestBody);
IRestResponse response = client.Execute(request);

返回示例

{
  "code": 0,
  "data": {
    "task_id": "open:zjsiwfuotpbqblrlfwtkfkioargjbla"
  },
  "result": "ok"
}

查询异步任务结果

携带 task_id查询结果

其中 result 对象说明

参数	必须	类型	说明
+ txts	否	txts[]	转换后的 txt 文件列表
url	是	string	转换后的 txt 文件下载地址(半小时有效)
size	是	int	转换后的 txt 文件大小(以字节为单位)

返回示例

{
  "code": 0,
  "data": {
    "status": "success",
    "progress": 100,
    "result": {
      "txts": [
        {
          "url": "https://***.com/***",
          "size": 70154
        },
        {
          "url": "https://***.com/***",
          "size": 112172
        },
        {
          "url": "https://***.com/***",
          "size": 954
        },
        {
          "url": "https://***.com/***",
          "size": 35327
        }
      ],
      "task":{"elapsed":7892,"resource_size":1070216}
    }
  }
}

错误码

请参考错误码说明