网站采集器介绍

常用的网络采集器主要分为桌面版和服务器版：桌面版是基于window等平台，通过本地带宽来进行资料采集与发布程序，主要代表有“火车头网站采集器”和 “EditorTools”；服务器版是采用PHP或ASP编程，运行于Linux或windows主机，通过服务器带宽来进行资料采集与发布程序，主要 代表有“小蜜蜂网站采集器”。两大类采集器孰优孰劣不言而喻

PHP采集程序中常用的函数

<?php
//去除HTML标记
function Text2Html($txt){
	$txt = str_replace("  ","　",$txt);
	$txt = str_replace("<","&lt;",$txt);
	$txt = str_replace(">","&gt;",$txt);
	$txt = preg_replace("/[\r\n]{1,}/isU","<br/>\r\n",$txt);
	return $txt;
}

//清除HTML标记
function ClearHtml($str){
	$str = str_replace('<','&lt;',$str);
	$str = str_replace('>','&gt;',$str);
	return $str;
}
//相对路径转化成绝对路径
function relative_to_absolute($content, $feed_url) {
	preg_match('/(http|https|ftp):\/\//', $feed_url, $protocol);
	$server_url = preg_replace("/(http|https|ftp|news):\/\//", "", $feed_url);
	$server_url = preg_replace("/\/.*/", "", $server_url);

	if ($server_url == '') {
		return $content;
	}

	if (isset($protocol[0])) {
		$new_content = preg_replace('/href="\//', 'href="'.$protocol[0].$server_url.'/', $content);
		$new_content = preg_replace('/src="\//', 'src="'.$protocol[0].$server_url.'/', $new_content);
	} else {
		$new_content = $content;
	}
	return $new_content;
}
//取得所有链接
function get_all_url($code){
	preg_match_all('/<a\s+href=["|\']?([^>"\' ]+)["|\']?\s*[^>]*>([^>]+)<\/a>/i',$code,$arr);
	return array('name'=>$arr[2],'url'=>$arr[1]);
}

//获取指定标记中的内容
function get_tag_data($str, $start, $end){
	if ( $start == '' || $end == '' ){
		return;
	}
	$str = explode($start, $str);
	$str = explode($end, $str[1]);
	return $str[0];
}
//HTML表格的每行转为CSV格式数组
function get_tr_array($table) {
	$table = preg_replace("'<td[^>]*?>'si",'"',$table);
	$table = str_replace("</td>",'",',$table);
	$table = str_replace("</tr>","{tr}",$table);
	//去掉 HTML 标记
	$table = preg_replace("'<[\/\!]*?[^<>]*?>'si","",$table);
	//去掉空白字符
	$table = preg_replace("'([\r\n])[\s]+'","",$table);
	$table = str_replace(" ","",$table);
	$table = str_replace(" ","",$table);

	$table = explode(",{tr}",$table);
	array_pop($table);
	return $table;
}

//将HTML表格的每行每列转为数组，采集表格数据
function get_td_array($table) {
	$table = preg_replace("'<table[^>]*?>'si","",$table);
	$table = preg_replace("'<tr[^>]*?>'si","",$table);
	$table = preg_replace("'<td[^>]*?>'si","",$table);
	$table = str_replace("</tr>","{tr}",$table);
	$table = str_replace("</td>","{td}",$table);
	//去掉 HTML 标记
	$table = preg_replace("'<[\/\!]*?[^<>]*?>'si","",$table);
	//去掉空白字符
	$table = preg_replace("'([\r\n])[\s]+'","",$table);
	$table = str_replace(" ","",$table);
	$table = str_replace(" ","",$table);

	$table = explode('{tr}', $table);
	array_pop($table);
	foreach ($table as $key=>$tr) {
		$td = explode('{td}', $tr);
		array_pop($td);
		$td_array[] = $td;
	}
	return $td_array;
}

//返回字符串中的所有单词 $distinct=true 去除重复
function split_en_str($str,$distinct=true) {
	preg_match_all('/([a-zA-Z]+)/',$str,$match);
	if ($distinct == true) {
		$match[1] = array_unique($match[1]);
	}
	sort($match[1]);
	return $match[1];
}