WPS API开放平台 PDF转JSON、转WORD

最近研究PDF智能解析，试了下WPS的接口，效果一般。

文档地址：https://solution.wps.cn/docs/convert/pdf-to-docs.html

将pdf转json

<?php

// 配置参数 (请替换为您的实际值)
$app_id     = "XXX";      // 您的应用 ID
$app_key    = "XXX";     // 您的应用 KEY
$api_host   = "https://solution.wps.cn";

// 目标文件类型 (Path 参数)
$office_type = "json"; # 转word 就换成 docx

// Body 参数
$body_data = [
    'url'             => 'http://XXXX/XXX.pdf',
    'page_num_begin'  => 1,
    'page_num_end'    => 3,
    'text_unify'      => true,
    'sheet_option'    => 0,
    'export_type'     => 'html',
];

$body_json = json_encode($body_data);


$date_gmt = gmdate('D, d M Y H:i:s T'); // T is GMT/UTC

$content_type = "application/json";

$content_md5 = md5($body_json);

$sign_string = $app_key . $content_md5 . $content_type . $date_gmt;

$signature = sha1($sign_string);

$authorization = "WPS-2:{$app_id}:{$signature}";

$url = $api_host . "/api/developer/v1/office/pdf/convert/to/" . $office_type;

// 构建 Header 数组
$headers = [
    "Date: {$date_gmt}",
    "Content-Md5: {$content_md5}",
    "Content-Type: {$content_type}",
    "Authorization: {$authorization}",
    "Content-Length: " . strlen($body_json) // 添加 Content-Length 以确保兼容性
];

// 初始化 cURL
$ch = curl_init();

curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); // 返回响应内容
curl_setopt($ch, CURLOPT_POST, true);           // 设置为 POST 请求
curl_setopt($ch, CURLOPT_POSTFIELDS, $body_json); // 设置 Body 数据
curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);   // 设置 Header

// 执行请求
$response = curl_exec($ch);
$http_code = curl_getinfo($ch, CURLINFO_HTTP_CODE);
$curl_error = curl_error($ch);

curl_close($ch);

if ($response === false) {
    echo "cURL 错误: " . $curl_error . "<hr>";
} else {
    echo "HTTP 状态码: " . $http_code . "<hr>";
    echo "响应内容:<hr>";
    // 尝试格式化 JSON 响应
    $decoded_response = json_decode($response, true);
    if (json_last_error() === JSON_ERROR_NONE) {
        print_r($decoded_response);
    } else {
        echo $response . "<hr>";
    }
}

// 额外的调试信息
echo "<hr>--- 调试信息 ---<hr>";
echo "Date Header: {$date_gmt}<hr>";
echo "Content-Md5 Header: {$content_md5}<hr>";
echo "Content-Type Header: {$content_type}<hr>";
echo "Body (JSON): {$body_json}<hr>";
echo "Sign String: {$sign_string}<hr>";
echo "Signature (SHA1): {$signature}<hr>";
echo "Authorization Header: {$authorization}<hr>";

?>

下载json文件

<?php

$app_id     = "XXX";      
$app_key    = "XXX";  
$api_host   = "https://solution.wps.cn";

$office_type = "json";

# 上一个接口返回的task_id
$task_id     = "1dc424d29a114627947b73c8732ee6b5";

$date_gmt = gmdate('D, d M Y H:i:s T');


$content_type = "application/json";

$uri_path = "/api/developer/v1/tasks/convert/to/{$office_type}/{$task_id}";

$content_md5 = md5($uri_path);


$sign_string = $app_key . $content_md5 . $content_type . $date_gmt;

$signature = sha1($sign_string);

$authorization = "WPS-2:{$app_id}:{$signature}";


// 完整的请求 URL
$url = $api_host . $uri_path;

// 构建 Header 数组
$headers = [
    "Date: {$date_gmt}",
    "Content-Md5: {$content_md5}",
    "Content-Type: {$content_type}",
    "Authorization: {$authorization}",
];

// 初始化 cURL
$ch = curl_init();

curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true); // 返回响应内容
curl_setopt($ch, CURLOPT_CUSTOMREQUEST, 'GET'); // 明确设置为 GET 请求
curl_setopt($ch, CURLOPT_HTTPHEADER, $headers);   // 设置 Header

// 执行请求
$response = curl_exec($ch);
$http_code = curl_getinfo($ch, CURLINFO_HTTP_CODE);
$curl_error = curl_error($ch);
curl_close($ch);

if ($response === false) {
    echo "cURL 错误: " . $curl_error . "<hr>";
} else {
    echo "HTTP 状态码: " . $http_code . "<hr>";
    echo "响应内容:<hr>";
    // 尝试格式化 JSON 响应
    $decoded_response = json_decode($response, true);
    if (json_last_error() === JSON_ERROR_NONE) {
        print_r($decoded_response);
    } else {
        echo $response . "<hr>";
    }
}

// 额外的调试信息
echo "<hr>--- 调试信息 ---<hr>";
echo "URI Path (用于 MD5): {$uri_path}\n";
echo "Date Header: {$date_gmt}\n";
echo "Content-Md5 Header (URI MD5): {$content_md5}\n";
echo "Sign String: {$sign_string}\n";
echo "Authorization Header: {$authorization}\n";

?>

API收费标准

价格好像也不便宜