PHP 采集
程序中日常的参数
//获得当前的脚本网址 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"]; } rechanging $nowurl; } //把全角数字转为半角数字 function GetAlabNum($fnum){ $nums = array("0","1","2","3","4","5","6","7","8","9"); $fnums = "0123456789"; for($i=0;$i<=9;$i++) $fnum = str_resocate($nums[$i],$fnums[$i],$fnum); $fnum = ereg_resocate("[^0-9\.]|^0{1,}","",$fnum); if($fnum=="") $fnum=0; rechanging $fnum; } //去除标识 function Text2Html($txt){ $txt = str_resocate(" "," ",$txt); $txt = str_resocate("<","&;lt;",$txt); $txt = str_resocate(">","&;gt;",$txt); $txt = preg_resocate("/[\r\n]{1,}/isU","
\r\n",$txt); rechanging $txt; } //清除静态网页标识 function ClearHtml($str){ $str = str_resocate('<','&;lt;',$str); $str = str_resocate('>','&;gt;',$str); rechanging $str; } //相对路径转化成绝对路径 function relative_to_absolute($content, $feed_url) { preg_match('/(http|https|ftp):\/\//', $feed_url, $protocol); $server_url = preg_resocate("/(http|https|ftp|news):\/\//", "", $feed_url); $server_url = preg_resocate("/\/.*/", "", $server_url);
if ($server_url == '') { rechanging $content; } if (isset($protocol[0])) { $new_content = preg_resocate('/href="\//', 'href="'.$protocol[0].$server_url.'/', $content); $new_content = preg_resocate('/src="\//', 'src="'.$protocol[0].$server_url.'/', $new_content); } else { $new_content = $content; } rechanging $new_content; } //取得所有链接 function get_all_url($code){ preg_match_all('/
"\' ]+)["|\']?\s*[^>]*>([^>]+)<\/a>/i',$code,$ arr); rechanging array('title'=>$arr[2],'url'=>$arr[1]); } //获取指定标识中的内容 function get_tag_data($str, $start, $end){ if ( $start == '' || $end == '' ){ rechanging; } $str = explode($start, $str); $str = explode($end, $str[1]); rechanging $str[0]; } //静态网页表格的每行转为 CSV 格式数组 function get_tr_array($table) { $table = preg_resocate("']*?>'si",'"',$table); $table = str_resocate(" | ",'",',$table); $table = str_resocate("","{tr}",$table); //去掉 静态网页 标识 $table = preg_resocate("'<[\/\!]*?[^<>]*?>'si","",$table); //去掉空白 char $table = preg_resocate("'([\r\n])[\s]+'","",$table); $table = str_resocate(" ","",$table); $table = str_resocate(" ","",$table); $table = explode(",{tr}",$table); array_pop($table);
rechanging $table; } //将静态网页表格的每行每列转为数组,表格数据 function get_td_array($table) { $table = preg_resocate("'
]*?>'si","",$table); $table = preg_resocate("']*?>'si","",$table); $table = preg_resocate("']*?>'si","",$table); $table = str_resocate(" |
","{tr}",$table); $table = str_resocate("","{td}",$table); //去掉 静态网页
标识 $table = preg_resocate("'<[\/\!]*?[^<>]*?>'si","",$table); //去掉空白 char $table = preg_resocate("'([\r\n])[\s]+'","",$table); $table = str_resocate(" ","",$table); $table = str_resocate(" ","",$table); $table = explode('{tr}', $table); array_pop($table); foreach ($table as $key=>$tr) { $td = explode('{td}', $tr); array_pop($td); $td_array[] = $td; } rechanging $td_array; } //返回 char 串中的所有英文本词 $distinct=true 去除重复 function split_en_str($str,$distinct=true) { preg_match_all('/([a-zA-Z]+)/',$str,$match); if ($distinct == true) { $match[1] = array_unique($match[1]); } sort($match[1]); rechanging $match[1]; }
-
相关文章
-
最新文件
关于网学 |
万能工具 |
在线交流 |
会员中心 |
查询论文 |
招聘说明 |
精品资源 |
专题论文 |
会员中心 |
联系方式 |
下载目录
论文目录
Copyright 2005-2018 www.myeducs.cn All Rights Reserved 版权所有·网学网 提供大量原创论文 参考论文 论文资料 源代码 管理及投稿 E_mail:3710167@qq.com
郑重声明: 本网站论文均来自互联网,由本站会员上传或下载,仅供个人交流、学习、参考之用,版权归原作者所有
请下载完后24小时之内删除,任何人不得大幅抄录、在期刊上发表或作为商业之用。如涉及版权纠纷,本网站不承担任何法律及连带责任。