修改whatshub工单爬虫

This commit is contained in:
root
2026-06-29 04:54:41 +08:00
parent 6130125427
commit 9f2e904fab
14 changed files with 1254 additions and 147 deletions
@@ -41,6 +41,26 @@ class AntiBotConfigBuilder
'sessionKey' => $sessionKey,
'challengeTimeoutMs' => 60000,
'sessionTtlMinutes' => $ttlMinutes,
] + self::postCfReadyExtras($ticketType);
}
/**
* 按工单类型附加 CF 过盾后的业务页就绪等待(仅 Whatshub 等需要的类型)
*
* @return array<string, mixed>
*/
private static function postCfReadyExtras(string $ticketType): array
{
if ($ticketType !== 'whatshub') {
return [];
}
return [
'postCfReadyUrlContains' => 'work-order-sharing',
'postCfReadySelector' => '.el-input__inner',
'postCfReadyTimeoutMs' => 30000,
'postCfSettleMs' => 500,
'postCfSpaWaitMs' => 4000,
];
}
@@ -7,11 +7,12 @@ namespace app\common\library\scrm\spider;
use app\common\library\scrm\AbstractScrmSpider;
use app\common\library\scrm\AntiBotConfigBuilder;
use app\common\library\scrm\UnifiedScrmData;
use app\common\service\SplitTicketSyncLogger;
/**
* Whatshub 云控蜘蛛Real Browser + Turnstile 过盾 + UI 翻页)
* Whatshub 云控蜘蛛
*
* 时序:Cloudflare Turnstile → 密码弹窗 authActions → API 拦截 → UI 翻页
* 时序:detailByShareCode API 直抓(优先)→ 失败则 Real Browser + Turnstile + UI 翻页
*/
class WhatshubSpider extends AbstractScrmSpider
{
@@ -21,9 +22,14 @@ class WhatshubSpider extends AbstractScrmSpider
/** 详情/统计 API 路径 */
private const API_DETAILS = '/api/whatshub-counter/workShare/open/statistics';
/** shareCode + password 直连接口(一次返回全量号码,无需翻页) */
private const API_DETAIL_BY_SHARE_CODE = '/api/whatshub-counter/workShare/open/detailByShareCode';
/** 默认每页条数 */
private const DEFAULT_PER_PAGE_COUNT = 20;
private const API_FETCH_TIMEOUT_SEC = 20;
private string $pageUrl;
private string $account;
@@ -45,6 +51,178 @@ class WhatshubSpider extends AbstractScrmSpider
$this->unifiedData = new UnifiedScrmData();
}
/**
* API 优先:detailByShareCode 直抓;失败则回退 Node 爬虫
*/
public function run(): UnifiedScrmData
{
$apiResult = $this->tryFetchViaShareCodeApi();
if ($apiResult instanceof UnifiedScrmData) {
SplitTicketSyncLogger::log('spider', 'whatshub api path ok', [
'count' => count($apiResult->numbers),
]);
return $apiResult;
}
SplitTicketSyncLogger::log('spider', 'whatshub api skipped or failed, fallback node', [
'pageUrl' => $this->pageUrl,
]);
return parent::run();
}
/**
* 从短链 pageUrl 解析 shareCode,例如 /m/KMYBBInp2066/1 → KMYBBInp2066
*/
private function extractShareCodeFromPageUrl(): ?string
{
$path = (string) parse_url($this->pageUrl, PHP_URL_PATH);
if ($path === '') {
return null;
}
if (preg_match('#/m/([^/]+)/#', $path, $matches)) {
return $matches[1];
}
return null;
}
/**
* 拼接 detailByShareCode 完整 GET URL
*/
private function buildShareCodeApiUrl(string $shareCode): ?string
{
$parsed = parse_url($this->pageUrl);
$scheme = isset($parsed['scheme']) ? (string) $parsed['scheme'] : 'https';
$host = isset($parsed['host']) ? (string) $parsed['host'] : '';
if ($host === '') {
return null;
}
$query = http_build_query([
'shareCode' => $shareCode,
'password' => $this->password,
]);
return $scheme . '://' . $host . self::API_DETAIL_BY_SHARE_CODE . '?' . $query;
}
/**
* 尝试通过 shareCode API 抓取;成功返回 UnifiedScrmData,否则返回 null
*/
private function tryFetchViaShareCodeApi(): ?UnifiedScrmData
{
if ($this->password === '') {
SplitTicketSyncLogger::log('spider', 'whatshub api skip: empty password', []);
return null;
}
$shareCode = $this->extractShareCodeFromPageUrl();
if ($shareCode === null || $shareCode === '') {
SplitTicketSyncLogger::log('spider', 'whatshub api skip: cannot parse shareCode', [
'pageUrl' => $this->pageUrl,
]);
return null;
}
$apiUrl = $this->buildShareCodeApiUrl($shareCode);
if ($apiUrl === null) {
SplitTicketSyncLogger::log('spider', 'whatshub api skip: invalid pageUrl host', [
'pageUrl' => $this->pageUrl,
]);
return null;
}
SplitTicketSyncLogger::log('spider', 'whatshub api request', [
'url' => preg_replace('/password=[^&]+/', 'password=***', $apiUrl),
]);
$ch = curl_init($apiUrl);
if ($ch === false) {
SplitTicketSyncLogger::log('spider', 'whatshub api curl init failed', []);
return null;
}
curl_setopt_array($ch, [
CURLOPT_RETURNTRANSFER => true,
CURLOPT_CONNECTTIMEOUT => 5,
CURLOPT_TIMEOUT => self::API_FETCH_TIMEOUT_SEC,
CURLOPT_HTTPHEADER => [
'Accept: application/json',
'User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36',
],
]);
$response = curl_exec($ch);
$httpCode = (int) curl_getinfo($ch, CURLINFO_HTTP_CODE);
$curlErr = curl_error($ch);
curl_close($ch);
if ($response === false || $curlErr !== '') {
SplitTicketSyncLogger::log('spider', 'whatshub api curl failed', [
'error' => $curlErr,
]);
return null;
}
if ($httpCode !== 200) {
SplitTicketSyncLogger::log('spider', 'whatshub api http error', [
'httpCode' => $httpCode,
]);
return null;
}
$payload = json_decode((string) $response, true);
if (!is_array($payload)) {
SplitTicketSyncLogger::log('spider', 'whatshub api invalid json', []);
return null;
}
if ((int) ($payload['code'] ?? 0) !== 200) {
SplitTicketSyncLogger::log('spider', 'whatshub api business error', [
'code' => $payload['code'] ?? null,
'msg' => $payload['msg'] ?? '',
]);
return null;
}
if (!isset($payload['data']) || !is_array($payload['data'])) {
SplitTicketSyncLogger::log('spider', 'whatshub api invalid data field', []);
return null;
}
return $this->parseShareCodeApiResponse($payload);
}
/**
* 将 detailByShareCode 响应映射为 UnifiedScrmData
*
* @param array<string, mixed> $payload
*/
private function parseShareCodeApiResponse(array $payload): UnifiedScrmData
{
$unifiedData = new UnifiedScrmData();
$todayNewSum = 0;
foreach ($payload['data'] as $item) {
if (!is_array($item) || empty($item['account'])) {
continue;
}
$number = (string) $item['account'];
$isOnline = isset($item['isOnline']) && (int) $item['isOnline'] === 1;
$dayNewFans = (int) ($item['dayNewFans'] ?? 0);
$unifiedData->addNumber($number, $isOnline, $dayNewFans);
$todayNewSum += $dayNewFans;
}
$unifiedData->todayNewCount = $todayNewSum;
$unifiedData->total = count($unifiedData->numbers);
return $unifiedData;
}
/** @return array<string, mixed> */
protected function getSpiderConfig(): array
{