看了网络爬虫相关的视频后，手痒痒，想爬点什么。最近Facebook上表情包大战很激烈，就想着把所有表情包都爬下来，却一时没有找到合适的VPN，因此把酷狗最近一月精选歌曲和简单介绍抓取到本地。代码写得有点乱，自己不是很满意，并不想放上来丢人现眼。不过转念一想，这好歹是自己第一次爬虫，于是...就有了如下不堪入目的代码~~~（由于抓取的数据量较小，所以没有考虑多进程什么的，不过我看了一下PHPCrawl的文档，发现PHPCrawl库已经把我能想到的功能都封装好了，实现起来很方便）
<?phpheader("Content-type:text/html;charset=utf-8");// It may take a whils to crawl a site ...set_time_limit(10000);include("libs/PHPCrawler.class.php");class MyCrawler extends PHPCrawler { function handleDocumentInfo($DocInfo) { // Just detect linebreak for output ("\n" in CLI-mode, otherwise "<br>"). if (PHP_SAPI == "cli") $lb = "\n"; else $lb = "<br />"; $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 = "/<span>名称：<\/span>([^(<br)]+)<br/"; $ret = preg_match($pat,$content,$matches); if($ret>0){ $songlistArr['title'] = $matches[1]; }else{ $songlistArr['title'] = ''; } //解析歌曲 $pat = "/<a title=\"([^\"]+)\" hidefocus=\"/"; $matches = array(); preg_match_all($pat,$content,$matches); $songlistArr['songs'] = array(); for($i = 0;$i < count($matches[0]);$i++){ $song_title = $matches[1][$i]; array_push($songlistArr['songs'],array('title'=>$song_title)); } echo "<pre>"; print_r($songlistArr); echo "</pre>"; } }$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 $lb = "<br />";echo "Summary:".$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;?> |
本文来自投稿，不代表科技代码立场，如若转载，请注明出处https://www.cwhello.com/6464.html
如有侵犯您的合法权益请发邮件951076433@qq.com联系删除
