简单的爬虫爬的完整的<img>标签，修改正则即可修改爬取内容

简单的爬虫爬的完整的<img>标签，生成<img>标签结果文件与爬虫经历的网页。

<?php
/*
* 从给定的url获取html内容
*
*
*/
function _getUrlContent($url){
$handle = fopen($url, "r");
if($handle){
$content = stream_get_contents($handle,1024*1024);
return $content;
}else{
return false;
}
}
/**
* 从html内容中筛选链接
*
*/
function _filterUrl($web_content){
$reg_tag_a = '/<[a|A].*?href=[\'\"]{0,1}([^>\'\"\ ]*).*?>/';
$reg_tag_b = '/<\s*img\s+[^>]*?src\s*=\s*(\'|\")(.*?)\\1[^>]*?\/?\s*>/i'; //修改这个就可以修改爬取内容
$result = preg_match_all($reg_tag_a,$web_content,$match_result);
$result1 = preg_match_all($reg_tag_b,$web_content,$match_result1);
if($result){

//var_dump($match_result1);
foreach ($match_result1 as $img) {
if(is_string($img))
{
$file = fopen("img.txt","a");
fputs($file,$img."\r\n");

}
else
{
foreach ($img as $img1)
{
if(is_string($img1))
{
$file = fopen("img.txt","a");
fputs($file,$img1."\r\n");

}
else
{
foreach ($img1 as $img2)
{
if(is_string($img2))
{
$file = fopen("img.txt","a");
fputs($file,$img2."\r\n");

}
else
{
foreach ($img2 as $img3)
{
if(is_string($img3))
{
$file = fopen("img.txt","a");
fputs($file,$img3."\r\n");

}
}
}
}
}
}
}

}

return $match_result[1];
}
}
/**
* 修正相对路径
*
*
*/
function _reviseUrl($base_url,$url_list){
$url_info = parse_url($base_url);
$base_url = $url_info["scheme"].'://';
if($url_info["user"]&&$url_info["pass"]){
$base_url .= $url_info["user"].":".$url_info["pass"]."@";
}
$base_url .= $url_info["host"];
if($url_info["port"]){
$base_url .= ":".$url_info["port"];
}
$base_url .= $url_info["path"];
print_r($base_url);
if(is_array($url_list)){
foreach ($url_list as $url_item) {
if(preg_match('/^http/',$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
*
* @param string $url
* @return array
*/
function crawler($url){
$content = _getUrlContent($url);
if($content){
$url_list = _reviseUrl($url,_filterUrl($content));
if($url_list){
return $url_list;
}else {
return ;
}
}else{
return ;
}
}
/**
* 测试用主程序
*
*/
function main(){
$current_url = "https://www.baidu.com/";//初始url
$fp_puts = fopen("url.txt","ab");//记录url列表
$fp_gets = fopen("url.txt","r");//保存url列表
do{
$result_url_arr = crawler($current_url);
if($result_url_arr){
foreach ($result_url_arr as $url) {
fputs($fp_puts,$url."\r\n");
}
}
}while ($current_url = fgets($fp_gets,1024));//不断获得url
}
main();
?>

巴特西

简单的爬虫爬的完整的<img>标签，修改正则即可修改爬取内容

最新文章

热门文章