作者 刘锟

update

... ... @@ -41,7 +41,7 @@ class HtmlCollect extends Command
public function handle()
{
while (true) {
$this->start_collect();
$this->start_collect();
}
}
... ... @@ -268,6 +268,14 @@ class HtmlCollect extends Command
$check_vc_b && $source[] = $check_vc_b;
}
//a标签下载资源
preg_match_all('/<a\s+[^>]*?href\s*=\s*(\'|\")(.*?)\\1[^>]*?\/?\s*>/i', $html, $result_a);
$down = $result_a[2] ?? [];
foreach ($down as $vd) {
$check_vd = $this->url_check($vd, $project_id, $domain, $web_url_domain, $home_url);
$check_vd && $source[] = $check_vd;
}
return $source;
}
... ... @@ -286,7 +294,7 @@ class HtmlCollect extends Command
(empty($host) || $host == $web_url_domain || $host == $home_url)
&& $path
&& (strpos($path, '.') !== false)
&& (end($path_arr) != 'html')
&& (!in_array(end($path_arr), ['html', 'com', 'xml']))
) {
$source = CollectSource::where('project_id', $project_id)->where('origin', $url)->first();
if (!$source) {
... ...