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。
<?php header("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 class="brush:php;toolbar:false">"; 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 = "
相关推荐:
以上是PHPCrawl爬虫库实现抓取酷狗歌单的详细内容。更多信息请关注PHP中文网其他相关文章!