函数描述及例子 php采集程序中常用的函数 查询关键字 php采集程序中常用的函数//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]; } 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;$i]*>([^>]+)/i',$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) { $table = preg_replace(']*?>'si,'',$table); $table = str_replace(,',',$table); $table = str_replace(,{tr},$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) { $table = preg_replace(']*?>'si,,$table); $table = preg_replace(']*?>'si,,$table); $table = preg_replace(']*?>'si,,$table); $table = str_replace(,{tr},$table); $table = str_replace(,{td},$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 $match[1]; } 函数描述及例子 php采集程序中常用的函数查询关键字 php采集程序中常用的函数,>,$txt); $txt = preg_replace(/[\r\n]{1,}/isu,\r\n,$txt); return $txt; }//清除html标记 function clearhtml($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('/\' ]+)[|\']?\s*[^>]*>([^>]+)/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) { $table = preg_replace(']*?>'si,'',$table); $table = str_replace(,',',$table); $table = str_replace(,{tr},$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) { $table = preg_replace(']*?>'si,,$table); $table = preg_replace(']*?>'si,,$table); $table = preg_replace(']*?>'si,,$table); $table = str_replace(,{tr},$table); $table = str_replace(,{td},$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 $match[1]; }
http://www.bkjia.com/phpjc/446999.htmlwww.bkjia.comtruehttp://www.bkjia.com/phpjc/446999.htmltecharticle函数描述及例子 php采集程序中常用的函数 查询关键字 php采集程序中常用的函数 //获得当前的脚本网址 function get_php_url(){ if(!empty($_server[re...