<?php
include_once('simple_html_dom.php');
function parse_html($url)
{
$opts = array(
'http'=>array(
'method'=>"GET",
'timeout'=>20,
)
);
//设置超时
$context = stream_context_create($opts);
//从一个URL或者文件创建一个DOM对象
$html = file_get_html($url, false, $context);
if($html == false)
{
echo "404";
}
// 寻找所有的img标签
foreach($html->find('.xxx') as $element)
{
foreach($lf5_g_pic->find('a') as $g_pic)
echo $g_pic->href."\n";
foreach($lf5_g_pic->find('img') as $img_s)
echo $img_s->src."\n\n\n";
}
}
parse_html('http://www.google.com');
?>
在simple_html_dom.php中需要注意超时一定次数便认为此链接不可访问,代码如下
function file_get_html($url, $use_include_path = false, $context=null, $offset = -1, $maxLen=-1, $lowercase = true, $forceTag
sClosed=true, $target_charset = DEFAULT_TARGET_CHARSET, $stripRN=true, $defaultBRText=DEFAULT_BR_TEXT)
{
// We DO force the tags to be terminated.
$dom = new simple_html_dom(null, $lowercase, $forceTagsClosed, $target_charset, $defaultBRText);
// For sourceforge users: uncomment the next line and comment the retreive_url_contents line 2 lines down if it is not already done.
//add by cleanfield
$cnt=0;
while($cnt < 3 && ($contents = file_get_contents($url, $use_include_path, $context, $offset))===FALSE)
{
$cnt++;
}
//$contents = file_get_contents($url, $use_include_path, $context, $offset);
......
}
在抓取页面时,一般都是批量任务,所以一定要注意设置每次拉取页面的超时时间,同时也要有重试。
附:
http://simplehtmldom.sourceforge.net/manual.htm simplehtmldom说明文档