时间:2021-07-01 10:21:17 帮助过:17人阅读
(1)下面这段代码是实现抓取多个URL,然后将抓取的URL的页面代码写入指定的文件
$urls = array(
'http://www.scutephp.com/',
'http://www.google.com/',
'http://www.example.com/'
); // 设置要抓取的页面URL
$save_to='/test.txt'; // 把抓取的代码写入该文件
$st = fopen($save_to,"a");
$mh = curl_multi_init();
foreach ($urls as $i => $url) {
$conn[$i] = curl_init($url);
curl_setopt($conn[$i], CURLOPT_USERAGENT, "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)");
curl_setopt($conn[$i], CURLOPT_HEADER ,0);
curl_setopt($conn[$i], CURLOPT_CONNECTTIMEOUT,60);
curl_setopt($conn[$i], CURLOPT_FILE,$st); // 将爬取的代码写入文件
curl_multi_add_handle ($mh,$conn[$i]);
} // 初始化
do {
curl_multi_exec($mh,$active);
} while ($active); // 执行
foreach ($urls as $i => $url) {
curl_multi_remove_handle($mh,$conn[$i]);
curl_close($conn[$i]);
} // 结束清理
curl_multi_close($mh);fclose($st);
(2)下面这段代码和上面差不多意思,只不过这个地方是将获得的代码先放入变量,然后再将获取到的内容写入指定的文件
$urls = array(
'http://www.scutephp.com/',
'http://www.google.com/',
'http://www.example.com/'
);
$save_to='/test.txt'; // 把抓取的代码写入该文件
$st = fopen($save_to,"a");
$mh = curl_multi_init();
foreach ($urls as $i => $url) {
$conn[$i] = curl_init($url);
curl_setopt($conn[$i], CURLOPT_USERAGENT, "Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)");
curl_setopt($conn[$i], CURLOPT_HEADER ,0);
curl_setopt($conn[$i], CURLOPT_CONNECTTIMEOUT,60);
curl_setopt($conn[$i],CURLOPT_RETURNTRANSFER,true); // 不将爬取代码写到浏览器,而是转化为字符串
curl_multi_add_handle ($mh,$conn[$i]);
}
do {
curl_multi_exec($mh,$active);
} while ($active);
foreach ($urls as $i => $url) {
$data = curl_multi_getcontent($conn[$i]); // 获得爬取的代码字符串
fwrite($st,$data); // 将字符串写入文件
} // 获得数据变量,并写入文件
foreach ($urls as $i => $url) {
curl_multi_remove_handle($mh,$conn[$i]);
curl_close($conn[$i]);
}
curl_multi_close($mh);fclose($st);
(3)下面这段代码实现的是利用 PHP 的 Curl Functions 实现并发多线程下载文件
$urls=array(
'http://www.scutephp.com/5w.zip',
'http://www.scutephp.com/5w.zip',
'http://www.scutephp.com/5w.zip'
);
$save_to='./home/';
$mh=curl_multi_init();
foreach($urls as $i=>$url){
$g=$save_to.basename($url);
if(!is_file($g)){
$conn[$i]=curl_init($url);
$fp[$i]=fopen($g,"w");
curl_setopt($conn[$i],CURLOPT_USERAGENT,"Mozilla/4.0(compatible; MSIE 7.0; Windows NT 6.0)");
curl_setopt($conn[$i],CURLOPT_FILE,$fp[$i]);
curl_setopt($conn[$i],CURLOPT_HEADER ,0);
curl_setopt($conn[$i],CURLOPT_CONNECTTIMEOUT,60);
curl_multi_add_handle($mh,$conn[$i]);
}
}
do{
$n=curl_multi_exec($mh,$active);
}while($active);
foreach($urls as $i=>$url){
curl_multi_remove_handle($mh,$conn[$i]);
curl_close($conn[$i]);
fclose($fp[$i]);
}
curl_multi_close($mh);$urls=array(
'http://www.scutephp.com/5w.zip',
'http://www.scutephp.com/5w.zip',
'http://www.scutephp.com/5w.zip'
);
$save_to='./home/';
$mh=curl_multi_init();
foreach($urls as $i=>$url){
$g=$save_to.basename($url);
if(!is_file($g)){
$conn[$i]=curl_init($url);
$fp[$i]=fopen($g,"w");
curl_setopt($conn[$i],CURLOPT_USERAGENT,"Mozilla/4.0(compatible; MSIE 7.0; Windows NT 6.0)");
curl_setopt($conn[$i],CURLOPT_FILE,$fp[$i]);
curl_setopt($conn[$i],CURLOPT_HEADER ,0);
curl_setopt($conn[$i],CURLOPT_CONNECTTIMEOUT,60);
curl_multi_add_handle($mh,$conn[$i]);
}
}
do{
$n=curl_multi_exec($mh,$active);
}while($active);
foreach($urls as $i=>$url){
curl_multi_remove_handle($mh,$conn[$i]);
curl_close($conn[$i]);
fclose($fp[$i]);
}
curl_multi_close($mh);