爬虫是一个很有意思的功能，本文主要介绍了phpcrawl爬虫库实现抓取酷狗歌单的方法,涉及phpcrawl爬虫库的使用及正则匹配相关操作技巧,需要的朋友可以参考下，希望能帮帮助到大家。
").
if (PHP_SAPI == "cli") $lb = "\n";
else $lb = "
";
$url = $DocInfo->url;
$pat = "/http:\/\/www\.kugou\.com\/yy\/special\/single\/\d+\.html/";
if(preg_match($pat,$url) > 0){
$this->parseSonglist($DocInfo);
}
flush();
}
public function parseSonglist($DocInfo){
$content = $DocInfo->content;
$songlistArr = array();
$songlistArr['raw_url'] = $DocInfo->url;
//解析歌曲介绍
$matches = array();
$pat = "/名称：<\/span>([^(0){
$songlistArr['title'] = $matches[1];
}else{
$songlistArr['title'] = '';
}
//解析歌曲
$pat = "/$song_title));
}
echo "";
print_r($songlistArr);
echo "";
}
}
$crawler = new MyCrawler();
// URL to crawl
$start_url="http://www.kugou.com/yy/special/index/1-0-2.html";
$crawler->setURL($start_url);
// Only receive content of files with content-type "text/html"
$crawler->addContentTypeReceiveRule("#text/html#");
//链接扩展
$crawler->addURLFollowRule("#http://www\.kugou\.com/yy/special/single/\d+\.html$# i");
$crawler->addURLFollowRule("#http://www.kugou\.com/yy/special/index/\d+-\d+-2\.html$# i");
// Store and send cookie-data like a browser does
$crawler->enableCookieHandling(true);
// Set the traffic-limit to 1 MB(1000 * 1024) (in bytes,
// for testing we dont want to "suck" the whole site)
//爬取大小无限制
$crawler->setTrafficLimit(0);
// Thats enough, now here we go
$crawler->go();
// At the end, after the process is finished, we print a short
// report (see method getProcessReport() for more information)
$report = $crawler->getProcessReport();
if (PHP_SAPI == "cli") $lb = "\n";
else $lb = "
";
echo "Summary:".$lb;
echo "Links followed: ".$report->links_followed.$lb;
echo "Documents received: ".$report->files_received.$lb;
echo "Bytes received: ".$report->bytes_received." bytes".$lb;
echo "Process runtime: ".$report->process_runtime." sec".$lb;
?>相关推荐：
立即学习“PHP免费学习笔记（深入）”；
