|
|
 |
PHP采集程序常用函数大全 |
热 ★★★ |
|
PHP采集程序常用函数大全 |
|
作者：闵涛 文章来源：闵涛的学习笔记 点击数：1561 更新时间：2010/3/22 22:16:50  |
|
|
当前的脚本网址
function get_php_url(){
if(!empty($_SERVER["REQUEST_URI"])){
$scriptName = $_SERVER["REQUEST_URI"];
$nowurl = $scriptName;
}else{
$scriptName = $_SERVER["PHP_SELF"];
if(empty($_SERVER["QUERY_STRING"])) $nowurl = $scriptName;
else $nowurl = $scriptName."?".$_SERVER["QUERY_STRING"];
}
return $nowurl;
}
//把全角数字转为半角数字
function GetAlabNum($fnum){
$nums = array("０","１","２","３","４","５","６","７","８","９");
$fnums = "0123456789";
for($i=0;$i<=9;$i++) $fnum = str_replace($nums[$i],$fnums[$i],$fnum);
$fnum = ereg_replace("[^0-9\.]|^0{1,}","",$fnum);
if($fnum=="") $fnum=0;
return $fnum;
}
//去除HTML标记
function Text2Html($txt){
$txt = str_replace(" "," ",$txt);
$txt = str_replace("<","<",$txt);
$txt = str_replace(">",">",$txt);
$txt = preg_replace("/[\r\n]{1,}/isU","<br/>\r\n",$txt);
return $txt;
}
//清除HTML标记
function ClearHtml($str){
$str = str_replace('<','<',$str);
$str = str_replace('>','>',$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];
}
[MySql]PHP存取 Mysql 数据乱码终极解决方案 [Web开发]PHP提示Notice: Undefined variable的解决办法
[Web开发]PHP 大小写函数 [Web开发]帝国cms内容页上一篇和下一篇调用方法大全
[Web开发]PHP的sleep函数关闭窗口后是否继续运行？ [聊天工具]MSN群功能使用帮助及MSN快捷键大全
[互联动态]Godaddy域名注册及空间服务器2010优惠码大全 [电脑技术]windows7快捷键使用大全
[Web开发]教你如何在PHP开启gzip页面压缩实例介绍 [Web开发]PHP过滤HTML字符串的常用函数使用方法介绍
|
|
| 教程录入：mintao 责任编辑：mintao |
|
|
上一篇教程： 关于C#排序算法的总结
下一篇教程： 巧妙运用PHP函数实现采集器的制作 |
|
|
| 【字体：小 大】【发表评论】【加入收藏】【告诉好友】【打印此文】【关闭窗口】 |
|
 注：本站部分文章源于互联网，版权归原作者所有！如有侵权，请原作者与本站联系，本站将立即删除！ 本站文章除特别注明外均可转载，但需注明出处！ [MinTao学以致用网] |
| 网友评论：（只显示最新10条。评论内容只代表网友观点，与本站立场无关！） |
| |
|
|
|
|
|
 |
同类栏目 |
 |
|
赞助链接 |
|
|
500 - 内部服务器错误。
|
|
|
|
|
|
