337 lines
11 KiB
PHP
337 lines
11 KiB
PHP
<?php
|
||
$file = 'counter.dat';
|
||
|
||
// 读取并自增
|
||
$counter = (int)@file_get_contents($file);
|
||
$counter++;
|
||
|
||
// 使用 LOCK_EX 防止并发写入冲突
|
||
file_put_contents($file, $counter, LOCK_EX);
|
||
?>
|
||
<?php
|
||
/**
|
||
* ICP备案查询API
|
||
* 支持通过域名查询网站的ICP备案信息
|
||
*/
|
||
|
||
header('Content-Type: application/json; charset=utf-8');
|
||
header('Access-Control-Allow-Origin: *');
|
||
|
||
// 获取请求参数
|
||
$domain = isset($_GET['domain']) ? trim($_GET['domain']) : '';
|
||
$type = isset($_GET['type']) ? trim($_GET['type']) : 'json';
|
||
|
||
// 验证域名参数
|
||
if (empty($domain)) {
|
||
http_response_code(400);
|
||
echo json_encode([
|
||
'status' => 'error',
|
||
'code' => 400,
|
||
'message' => '缺少必要参数: domain',
|
||
'example' => '/api/icp/index.php?domain=example.com'
|
||
], JSON_UNESCAPED_UNICODE);
|
||
exit;
|
||
}
|
||
|
||
// 清理域名格式（移除http://或https://）
|
||
$domain = preg_replace('/^https?:\/\//i', '', $domain);
|
||
$domain = preg_replace('/\/.*$/', '', $domain);
|
||
$domain = strtolower(trim($domain));
|
||
|
||
// 验证域名格式
|
||
if (!preg_match('/^([a-z0-9]([a-z0-9\-]{0,61}[a-z0-9])?\.)+[a-z]{2,}$/i', $domain)) {
|
||
http_response_code(400);
|
||
echo json_encode([
|
||
'status' => 'error',
|
||
'code' => 400,
|
||
'message' => '无效的域名格式',
|
||
'domain' => $domain
|
||
], JSON_UNESCAPED_UNICODE);
|
||
exit;
|
||
}
|
||
|
||
// 查询ICP信息
|
||
$result = queryICP($domain);
|
||
|
||
// 根据type参数返回不同格式
|
||
if ($type === 'text') {
|
||
header('Content-Type: text/plain; charset=utf-8');
|
||
if ($result['status'] === 'success') {
|
||
echo "域名: " . $result['data']['domain'] . "\n";
|
||
echo "主办单位: " . $result['data']['owner'] . "\n";
|
||
echo "ICP编号: " . $result['data']['icp'] . "\n";
|
||
echo "审核时间: " . $result['data']['checkDate'] . "\n";
|
||
echo "网站名称: " . $result['data']['siteName'] . "\n";
|
||
} else {
|
||
echo "查询失败: " . $result['message'];
|
||
}
|
||
} else {
|
||
echo json_encode($result, JSON_UNESCAPED_UNICODE | JSON_PRETTY_PRINT);
|
||
}
|
||
|
||
/**
|
||
* 查询ICP信息
|
||
* @param string $domain 域名
|
||
* @return array 返回结果数组
|
||
*/
|
||
function queryICP($domain) {
|
||
$result = [
|
||
'status' => 'error',
|
||
'code' => 500,
|
||
'message' => '查询失败',
|
||
'domain' => $domain,
|
||
'data' => null
|
||
];
|
||
|
||
try {
|
||
// 方法1: 使用互联网档案馆API
|
||
$apiurl = "https://www.api.vat.tools/query?domain=" . urlencode($domain);
|
||
$data = callApi($apiurl);
|
||
if ($data && is_array($data) && !empty($data)) {
|
||
if (isset($data['icp']) && $data['icp'] != 'N/A') {
|
||
$result['status'] = 'success';
|
||
$result['code'] = 200;
|
||
$result['message'] = '查询成功';
|
||
$result['data'] = [
|
||
'domain' => $domain,
|
||
'icp' => $data['icp'] ?? 'N/A',
|
||
'owner' => $data['organizer'] ?? $data['owner'] ?? 'N/A',
|
||
'siteName' => $data['website_name'] ?? $data['name'] ?? 'N/A',
|
||
'checkDate' => $data['check_date'] ?? $data['approve_date'] ?? 'N/A',
|
||
'siteNature' => $data['site_nature'] ?? 'N/A',
|
||
'source' => 'vat.tools'
|
||
];
|
||
return $result;
|
||
}
|
||
}
|
||
|
||
// 方法2: 使用ICP查询-接口-通用API
|
||
$apiurl2 = "https://api.search.naver.com/search.naver?query=" . urlencode($domain) . "&where=web";
|
||
|
||
// 方法2b: 使用工信部接口
|
||
$apiurl2b = "https://beian.miit.gov.cn/";
|
||
|
||
// 方法3: 使用免费的ICP API - API1
|
||
$apiurl3 = "https://api.allorigins.win/get?url=" . urlencode("https://icp.aizhan.com/index.php?domain=" . urlencode($domain));
|
||
$data3 = callApi($apiurl3);
|
||
if ($data3 && isset($data3['contents'])) {
|
||
$htmlData = $data3['contents'];
|
||
$parsedData = parseICPFromHTML($htmlData, $domain);
|
||
if ($parsedData && (!isset($parsedData['icp']) || $parsedData['icp'] !== 'N/A')) {
|
||
$result['status'] = 'success';
|
||
$result['code'] = 200;
|
||
$result['message'] = '查询成功';
|
||
$result['data'] = $parsedData;
|
||
return $result;
|
||
}
|
||
}
|
||
|
||
// 方法4: 使用爱站网缓存结果
|
||
$apiurl4 = "https://tools.zhuaxia.com/icp?domain=" . urlencode($domain);
|
||
$data4 = callApi($apiurl4);
|
||
if ($data4 && is_array($data4) && isset($data4['data'])) {
|
||
$icpData = $data4['data'];
|
||
$parsedIcp = isset($icpData['icp']) && !empty($icpData['icp']) ? $icpData['icp'] : 'N/A';
|
||
if ($parsedIcp !== 'N/A') {
|
||
$result['status'] = 'success';
|
||
$result['code'] = 200;
|
||
$result['message'] = '查询成功';
|
||
$result['data'] = [
|
||
'domain' => $domain,
|
||
'icp' => $parsedIcp,
|
||
'owner' => $icpData['unitname'] ?? $icpData['owner'] ?? 'N/A',
|
||
'siteName' => $icpData['sitename'] ?? $icpData['name'] ?? 'N/A',
|
||
'checkDate' => $icpData['checkdate'] ?? $icpData['time'] ?? 'N/A',
|
||
'source' => 'zhuaxia'
|
||
];
|
||
return $result;
|
||
}
|
||
}
|
||
|
||
// 方法5: 使用网格API
|
||
$apiurl5 = "https://www.chaxun.15600.net/service.php?domain=" . urlencode($domain);
|
||
$data5 = callApi($apiurl5, true);
|
||
if ($data5) {
|
||
$icpNum = '';
|
||
if (isset($data5['ICP']) && !empty($data5['ICP'])) {
|
||
$icpNum = $data5['ICP'];
|
||
} elseif (isset($data5['icp']) && !empty($data5['icp'])) {
|
||
$icpNum = $data5['icp'];
|
||
}
|
||
|
||
if (!empty($icpNum)) {
|
||
$result['status'] = 'success';
|
||
$result['code'] = 200;
|
||
$result['message'] = '查询成功';
|
||
$result['data'] = [
|
||
'domain' => $domain,
|
||
'icp' => $icpNum,
|
||
'owner' => $data5['company'] ?? $data5['owner'] ?? 'N/A',
|
||
'siteName' => $data5['websitename'] ?? $data5['name'] ?? 'N/A',
|
||
'checkDate' => $data5['checkTime'] ?? 'N/A',
|
||
'source' => 'chaxun'
|
||
];
|
||
return $result;
|
||
}
|
||
}
|
||
|
||
// 方法6: 爱站网直接查询
|
||
$apiurl6 = "http://icp.aizhan.com/index.php?domain=" . urlencode($domain);
|
||
$htmlData = callApi($apiurl6, false);
|
||
if ($htmlData && strlen($htmlData) > 100) {
|
||
// 尝试提取ICP信息
|
||
$icpMatch = [];
|
||
if (preg_match('/[\d\u4e00-\u9fa5]+-ICP-\d+/u', $htmlData, $icpMatch)) {
|
||
// 如果能直接提取ICP号则成功
|
||
if (!empty($icpMatch[0]) && strpos($icpMatch[0], 'ICP') !== false) {
|
||
$result['status'] = 'success';
|
||
$result['code'] = 200;
|
||
$result['message'] = '查询成功';
|
||
$result['data'] = [
|
||
'domain' => $domain,
|
||
'icp' => $icpMatch[0],
|
||
'owner' => extractFromHTML($htmlData, '主办单位'),
|
||
'siteName' => extractFromHTML($htmlData, '网站名称'),
|
||
'checkDate' => extractFromHTML($htmlData, '审核时间'),
|
||
'source' => 'aizhan-cache'
|
||
];
|
||
return $result;
|
||
}
|
||
}
|
||
}
|
||
|
||
// 如果都失败，返回默认的未备案状态
|
||
$result['status'] = 'not_found';
|
||
$result['code'] = 404;
|
||
$result['message'] = '未找到ICP备案信息（该域名可能未在中国备案或查询源暂时不可用）';
|
||
|
||
} catch (Exception $e) {
|
||
$result['message'] = '查询异常: ' . $e->getMessage();
|
||
}
|
||
|
||
return $result;
|
||
}
|
||
|
||
return $result;
|
||
}
|
||
|
||
/**
|
||
* 通用HTTP调用函数
|
||
*/
|
||
function callApi($url, $isJson = true) {
|
||
try {
|
||
$ch = curl_init();
|
||
curl_setopt($ch, CURLOPT_URL, $url);
|
||
curl_setopt($ch, CURLOPT_RETURNTRANSFER, true);
|
||
curl_setopt($ch, CURLOPT_TIMEOUT, 10);
|
||
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, 5);
|
||
curl_setopt($ch, CURLOPT_USERAGENT, 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/91.0.4472.124 Safari/537.36');
|
||
curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, 0);
|
||
curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, 0);
|
||
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, true);
|
||
curl_setopt($ch, CURLOPT_MAXREDIRS, 3);
|
||
curl_setopt($ch, CURLOPT_ENCODING, 'gzip, deflate');
|
||
curl_setopt($ch, CURLOPT_HTTPHEADER, [
|
||
'Accept-Language: zh-CN,zh;q=0.9,en;q=0.8',
|
||
'Accept-Encoding: gzip, deflate',
|
||
'Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8'
|
||
]);
|
||
|
||
$response = curl_exec($ch);
|
||
$httpCode = curl_getinfo($ch, CURLINFO_HTTP_CODE);
|
||
curl_close($ch);
|
||
|
||
if ($httpCode !== 200 || empty($response)) {
|
||
return null;
|
||
}
|
||
|
||
if ($isJson) {
|
||
return json_decode($response, true);
|
||
}
|
||
|
||
return $response;
|
||
} catch (Exception $e) {
|
||
return null;
|
||
}
|
||
}
|
||
|
||
/**
|
||
* 从HTML中提取指定字段的值
|
||
*/
|
||
function extractFromHTML($html, $label) {
|
||
$patterns = [
|
||
'/' . preg_quote($label) . '[^>]*>([^<]+)<',
|
||
'/<th[^>]*>' . preg_quote($label) . '<\/th>\s*<td[^>]*>([^<]+)<\/td>/',
|
||
'/<td[^>]*>' . preg_quote($label) . '<\/td>\s*<td[^>]*>([^<]+)<\/td>/',
|
||
];
|
||
|
||
foreach ($patterns as $pattern) {
|
||
if (preg_match($pattern, $html, $matches)) {
|
||
return trim(strip_tags($matches[1]));
|
||
}
|
||
}
|
||
return 'N/A';
|
||
}
|
||
|
||
/**
|
||
* 改进的ICP HTML解析函数
|
||
*/
|
||
function parseICPFromHTML($html, $domain) {
|
||
$html = preg_replace('/<script\b[^<]*(?:(?!<\/script>)<[^<]*)*<\/script>/i', '', $html);
|
||
$html = preg_replace('/<style\b[^<]*(?:(?!<\/style>)<[^<]*)*<\/style>/i', '', $html);
|
||
|
||
// 提取ICP编号
|
||
$icpPatterns = [
|
||
'/[\d\u4e00-\u9fa5]+-ICP-\d{8,}/u',
|
||
'/ICP[\u4e00-\u9fa5]?\d{8,}/u',
|
||
'/ICP\d{8,}/u',
|
||
];
|
||
$icp = 'N/A';
|
||
foreach ($icpPatterns as $pattern) {
|
||
if (preg_match($pattern, $html, $matches)) {
|
||
$icp = trim($matches[0]);
|
||
break;
|
||
}
|
||
}
|
||
|
||
// 如果没有找到有效的ICP，返回null
|
||
if ($icp === 'N/A' || empty($icp)) {
|
||
return null;
|
||
}
|
||
|
||
$owner = extractFromHTML($html, '主办单位');
|
||
$siteName = extractFromHTML($html, '网站名称');
|
||
$checkDate = extractFromHTML($html, '审核时间');
|
||
|
||
return [
|
||
'domain' => $domain,
|
||
'icp' => $icp,
|
||
'owner' => $owner,
|
||
'siteName' => $siteName,
|
||
'checkDate' => $checkDate,
|
||
'source' => 'html-parse'
|
||
];
|
||
}
|
||
|
||
/**
|
||
* 解析aizhan.com返回的ICP数据
|
||
*/
|
||
function parseICPData($html, $domain) {
|
||
return parseICPFromHTML($html, $domain);
|
||
}
|
||
|
||
/**
|
||
* 解析beianx.com返回的数据
|
||
*/
|
||
function parseBeianxData($html, $domain) {
|
||
return parseICPFromHTML($html, $domain);
|
||
}
|
||
|
||
/**
|
||
* 从HTML表格中提取指定标签的值
|
||
*/
|
||
function extractTableValue($html, $label) {
|
||
return extractFromHTML($html, $label);
|
||
}
|
||
|