采集网页 python 采集网页文字

搜索热词

经测试代码如下：

/**

*功能:获取页面内容,存储下来阅读;lost63

*
* @param
* @author 编程之家
**/
Class GetUrl{
var $url; //地址
var $result; //结果
var $content; //内容
var $list; //列表
function GetUrl($url){
$this->url=$url;
$this->GetContent();
$this->GetList();
$this->FileSave();
//print_r($this->list[2]);
}
private function GetContent(){
$this->result=fopen($this->url,"r");
while(!feof($this->result)){
$this->content.=fgets($this->result,9999);
}
}
private function GetList(){
preg_match_all('/(.*?)/',$this->content,$this->list);
$this->list[2]=array_unique($this->list[2]); //移除相同的值
while(list($key,$value)=each($this->list[2])){
if(strpos($value,".html")==0||strpos($value,"jiaocheng")==0){
unset($this->list[2][$key]);
}else{
$this->list[2][$key]=substr($value,strpos($value,".html")).".html"; //去掉不需要的标签
}
}
}
private function FileSave(){
foreach($this->list[2] as $value){
$this->url=$value; //重新赋值
$this->content=null;
$this->GetContent(); //提取内容
preg_match_all('/
(.*?)/',$files); //取标题 
 
$filename=$files[1][0].".html"; //存储名
$content=$this->str_cut($this->content,'http://pagead2.googlesyndication.com/pagead/show_ads.js','
 
 
$file=fopen($filename,"w");
fwrite($file,$content);
fclose($file);
echo $filename."保存 OK
n";}
}
function str_cut($str,$start,$end) {
$content = strstr( $str,$start );
$content = substr( $content,strlen( $start ),strpos( $content,$end ) - strlen( $start ) );
return $content;
}
}
$w=new GetUrl("http://jb51.cc /jiaocheng/javaｓｃｒｉｐｔ-jiaocheng-352.html");
?>