转载请联系作者:Email: pengwuwang@21cn.com darlingpeng@sina.com 在工作中,经常需要对网页上的表格内容进行处理,但是,由于表格内容制作过程中的随意性,跨行跨列经常发生,所以我作了这几个函数,以获取表格的内容,程序中重要的地方已作了注解,所以在此不再重复说明,经过测试,非常成功.所以拿出来供大家共享. //作者: 王朋武 //日期: 2005,3,31 //目的: 获取网页上(任意跨行跨列的)表格中的内容 function fun_proc_rowspan($l_str) { $l_a = explode("\n", $l_str); for($i=count($l_a)-1; $i>=0; $i--) { $l_str = trim($l_a[$i]); if(empty($l_str)) continue; $l_str = eregi_replace(" | $l_b = explode("", $l_str); //如有n个,则分成(n+1)个组,最开始一项为空. for($j=0; $j +----+----+----+----+----+----+----+此一行保存7格, 前6格都有rowspan=2 +-----------------------------+----+此一行只保存2格 +----------------------------------+此一行只保存1格 */ $l_str = trim($l_b[$j]); if(eregi("rowspan", $l_str)) { $rowspan = preg_replace("/^ $l_a = fun_add_row_td($l_a, $i, $j, $rowspan, $rowcont); $l_str = implode("\n", $l_a); return $l_str; } }//end of for j }//end of for i return $l_str; } function fun_add_row_td($l_a, $r, $l, $add_n, $add_cont) //l_a是数组, r是插入的开始行,l是开始的列, add_n是跨多少行, add_cont是加的内容 { for($i=$r; $i<$r+$add_n; $i++) { if($i == $r) { $l_str = eregi_replace(" $l_b = explode("", $l_str); | $l_c = ""; for($j=1; $j else $l_c .= $l_b[$j]; } $l_a[$i] = $l_c; continue; } $l_str = eregi_replace(" 分隔符 | $l_b = explode("", $l_str); //以分组 $l_c = ""; for($j=1; $j<$l+$add_n; $j++) { //略过开始的空项,从1开始 if($j == $l) { $l_c .= " ".$add_cont." | ";} $l_c .= $l_b[$j]; }//end of for j $l_a[$i] = $l_c; //更新后的新内容 }//end of for i return $l_a; } function fun_proc_colspan($l_str) { $l_a = explode("\n", $l_str); for($i=0; $i if(empty($l_str)) continue; $l_str = eregi_replace(" $l_b = explode("", $l_str); //如有n个,则分成(n+1)个组,最开始一项为空. | for($j=1; $j if(eregi(" $l_a = fun_add_col_td($l_a, $i, $j, $colspan, $colcont); $l_str = implode("\n", $l_a); return $l_str; } }//end of for j }//end of for i return $l_str; } function fun_add_col_td($l_a, $r, $l, $add_n, $add_cont) //l_a是数组, r是插入的开始行,l是开始的列, add_n是跨多少列, add_cont是加的内容 { $l_str = eregi_replace(" 分隔符 | $l_b = explode("", $l_str); //以分组 $l_c = ""; for($j=1; $j<=count($l_b); $j++) { //略过开始的空项,从1开始 if($j == $l) { $l_c .= eregi_replace("colspan", "", $l_b[$j]); //去掉colspan continue; } if($j == $l+1) { for($k=0; $k<$add_n-1; $k++) $l_c .= " ".$add_cont." | ";} $l_c .= $l_b[$j]; }//end of for j $l_a[$r] = $l_c; //更新后的新内容 return $l_a; } $l_str = file_get_contents("test.htm"); //获取网页内容 $l_str = eregi_replace(".* $l_str = eregi_replace("\r", "", $l_str); //去掉\r $l_str = eregi_replace("\n", "", $l_str); //去掉\n $l_str = eregi_replace(" | "); //只保留 | , | HTML表记
1 | 2 | 3 | 4 | 5 | 6 | 7 |
a1 | 22 | a2 | a3 | |||
b1 | b2 | b3 | b4 | 33 | ||
c1 | c2 | c3 | c4 | 44 | ||
d1 | d2 | d3 | d4 | |||
e1 | e2 | e3 | e4 | e5 | ||
f1 | f2 | f3 | ||||
g1 | g2 | |||||
h1 | ||||||
i1 | i2 | i3 | i4 | i5 | ||
j1 | j2 | j3 | j4 | |||
k1 | k2 | |||||
l1 | l2 | |||||
m1 | m2 | m3 |
1 | 2 | 3 | 4 | 5 | 6 | 7 |
a1 | 22 | a2 | a3 | a3 | a3 | a3 |
b1 | 22 | b2 | b2 | b3 | b4 | 33 |
c1 | 22 | c2 | c3 | c4 | 44 | 33 |
d1 | 22 | d2 | d3 | d4 | 44 | 33 |
e1 | 22 | e2 | e3 | e4 | e5 | 33 |
f1 | 22 | f2 | f3 | f3 | f3 | f3 |
g1 | 22 | g2 | g2 | g2 | g2 | g2 |
h1 | h1 | h1 | h1 | h1 | h1 | h1 |
i1 | i2 | i2 | i2 | i3 | i4 | i5 |
j1 | j2 | j2 | j2 | j3 | j4 | j4 |
k1 | k1 | k1 | k1 | k1 | k1 | k2 |
l1 | l1 | l1 | l1 | l1 | l1 | l2 |
m1 | m1 | m1 | m1 | m1 | m2 | m3 |
|小黑屋|最新主题|手机版|微赢网络技术论坛 ( 苏ICP备08020429号 )
GMT+8, 2024-9-30 09:37 , Processed in 0.091161 second(s), 12 queries , Gzip On, MemCache On.
Powered by Discuz! X3.5
© 2001-2023 Discuz! Team.