PHP实现的一个简单的爬虫
程序员文章站
2022-05-16 16:46:10
...
这个小爬虫的功能是抓取目标网页的url,并实现递归爬。这个小demo是参照网友的代码然后自己改了一下,由于网上版本太多,我就不@原来的作者了(我不知道谁才是真正的作者)
下面是代码:
//爬虫类classCrawler{private$url;
publicfunction__construct($url){if(!preg_match("/^(http)s?/", $url)){
$url = "http://".$url;
}
$this->url = $url;
}
//从给定的url中获取html内容protectedfunction_getUrlContent($url){
@$handle = fopen($url, "r");
if(error_get_last()){//捕获异常(不一定是错误)$err = newException("你的URL好像不对!要不换一个?");
echo$err->getMessage();
return;
}
if($handle){
$content = stream_get_contents($handle,1024*1024);//将资源流读入字符串return$content;
}else{
returnfalse;
}
}
//从html内容中筛选链接protectedfunction_filterUrl($web_content){$reg_tag_a = '/\'\"\ ]*).*?>/';
$result = preg_match_all($reg_tag_a,$web_content,$match_result);
if($result){
return$match_result[1];
}
}
//判断是否是完整的urlprotectedfunction_judgeURL($url){$url_info = parse_url($url);
if(isset($url_info['scheme'])||isset($url_info['host'])){
returntrue;
}
returnfalse;
}
//修正相对路径protectedfunction_reviseUrl($base_url,$url_list){$url_info = parse_url($base_url);//分解url中的各个部分unset($base_url);
$base_url = isset($url_info["scheme"])?$url_info["scheme"].'://':"";//$url_info["scheme"]为http、ftp等if(isset($url_info["user"]) && isset($url_info["pass"])){//记录用户名及密码的url$base_url .= $url_info["user"].":".$url_info["pass"]."@";
}
$base_url .= isset($url_info["host"])?$url_info["host"]:"";//$url_info["host"]域名if(isset($url_info["port"])){//$url_info["port"]端口,8080等$base_url .= ":".$url_info["port"];
}
$base_url .= isset($url_info["path"])?$url_info["path"]:"";//$url_info["path"]路径//目前为止,绝对路径前面已经组装完if(is_array($url_list)){
foreach ($url_listas$url_item) {
// if(preg_match('/^(http)s?/',$url_item)){if($this->_judgeURL($url_item)){
//已经是完整的url$result[] = $url_item;
}else {
//不完整的url$real_url = $base_url.$url_item;
$result[] = $real_url;
}
}
return$result;
}else {
return;
}
}
//爬虫publicfunctioncrawler(){$content = $this->_getUrlContent($this->url);
if($content){
$url_list = $this->_reviseUrl($this->url,$this->_filterUrl($content));
if($url_list){
return$url_list;
}else {
return ;
}
}else{
return ;
}
}
}
$fp_puts = fopen("url.txt","ab");//记录url列表$fp_gets = fopen("url.txt","r");//保存url列表$current_url = "www.baidu.com";
do{
$Crawler = new Crawler($current_url);
$url_arr = $Crawler->crawler();
if($url_arr){
foreach ($url_arras$url) {
fputs($fp_puts,$url."\n");
}
}
}while ($current_url = fgets($fp_gets,1024));//不断获得url// echo "";
// var_dump($url_arr);// echo "";?>
由于在循环的时候要new的对象可能会很多,当时想的是用单例模式解决,以免内存开销太大,后来嫌麻烦就不了了之了。。。。
').addClass('pre-numbering').hide(); $(this).addClass('has-numbering').parent().append($numbering); for (i = 1; i ').text(i)); }; $numbering.fadeIn(1700); }); });以上就介绍了PHP实现的一个简单的爬虫,包括了方面的内容,希望对PHP教程有兴趣的朋友有所帮助。