百度搜藏的导出方法

第一步,将全部私有搜藏变成公开搜藏,

第二步,退出搜藏的登录

第三步,访问 http://cang.baidu.com/用户名称

第四步,写个小脚本分析页面,获得全部搜藏数据

附: 简单写了一个php程序, 输出的格式没有定 , 有兴趣的朋友自己填写一下output 这个函数 export_bd_cang.php

 <?php $username = "georgehoul"; $page_no = 1; $array_bd_cang = array(); run_page(); print_r($array_bd_cang); function run_page() { global $username; global $array_bd_cang; global $page_no; $base_url = "http://cang.baidu.com/$username/page/"; $url = $base_url.$page_no; print($url."<br />/n"); $content = file_get_contents ( $url); $onclick = "οnclick=/"return c/(this.href/)/""; $tb = "target=/"_blank/""; $pattern = "/<a $onclick href="/" mce_href="/""(.*?)/" $tb><font size=/"3/" id=/"lnk/d+/">(.*?)<//font><//a>.*?(/d+-/d+-/d+) <//font> - <a href="/" mce_href="/""(.*?)/" $tb class=/"RsLnkCg/">快照<//a>/"; //.*?showATags/(/"$username/",/"(.*?)/",/".*?/"/);<//script><//font>.*?/"; $pattern2 = "/showATags/(/"$username/",/"(.*?)/",/".*?/"/);/"; preg_match_all ( $pattern, $content, $matches ); preg_match_all ( $pattern2,$content, $matches2 ); $i = 0; foreach ($matches[1] as $m) { $item = new baidu_cang($matches[1][$i],$matches[2][$i],$matches[3][$i],"http://cang.baidu.com".$matches[4][$i],$matches2[1][$i]); array_push($array_bd_cang,$item); $item->output(); $i++; } $pattern3 = "/<a href="/" mce_href="/""//$username//page///d+/"><font>尾页<//font>/"; if (preg_match($pattern3,$content)) { $page_no++; run_page(); } } class baidu_cang { public $url; public $title; public $dt; public $bd_snap; public $tags; function baidu_cang($url='',$title='',$dt='',$bd_snap='',$tags='') { $this->url = $url; $this->title = $title; $this->dt = $dt; $this->bd_snap = $bd_snap; $this->tags = $tags; } function output() { print ""; } } ?>