bsp; } 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); $ |