程序|网页
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
//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(" ", $l_str);
for($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 如 +----+----+----+----+----+----+----+
+----+----+----+----+----+----+----+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("/^ $rowcont = preg_replace("/^(.+)/", "\1", $l_str);
$l_a = fun_add_row_td($l_a, $i, $j, $rowspan, $rowcont);
$l_str = implode(" ", $l_a);
return $l_str;
}
}//end of for j
}//end of for i
return $l_str;
}
{
$l_a = explode(" ", $l_str);
for($i=count($l_a)-1; $i>=0; $i--) {
$l_str = trim($l_a[$i]);
if(empty($l_str)) continue;
$l_str = eregi_replace("
for($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(" ", $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; $i if($i == $r) {
$l_str = eregi_replace(" $l_b = explode("", $l_str);
$l_c = "";
for($j=1; $j if($j == $l) $l_c .= eregi_replace("rowspan", "", $l_b[$j]); //去掉rowspan
else $l_c .= $l_b[$j];
}
$l_a[$i] = $l_c;
continue;
}
Untitled Document
{
for($i=$r; $i if($i == $r) {
$l_str = eregi_replace("
$l_c = "";
for($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; $j if($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;
}
$l_b = explode("", $l_str); //以分组
$l_c = "";
for($j=1; $j if($j == $l) {
$l_c .= "
}
$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(" ", $l_str);
for($i=0; $i $l_str = trim($l_a[$i]);
if(empty($l_str)) continue;
{
$l_a = explode(" ", $l_str);
for($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 $l_str = trim($l_b[$j]);
if(eregi(" $colspan = preg_replace("/^ $colcont = preg_replace("/^(.+)/", "\1", $l_str);
$l_a = fun_add_col_td($l_a, $i, $j, $colspan, $colcont);
$l_str = implode(" ", $l_a);
return $l_str;
}
}//end of for j
}//end of for i
return $l_str;
}
", "
", $l_str); //给每一格之间加上标记
$l_str = strip_tags($l_str, "
");
for($j=1; $j
if(eregi("
$l_a = fun_add_col_td($l_a, $i, $j, $colspan, $colcont);
$l_str = implode(" ", $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; $j if($j == $l) {
$l_c .= eregi_replace("colspan", "", $l_b[$j]); //去掉colspan
continue;
}
if($j == $l+1) {
for($k=0; $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
{
$l_str = eregi_replace("
$l_b = explode("", $l_str); //以分组
$l_c = "";
for($j=1; $j if($j == $l) {
$l_c .= eregi_replace("colspan", "", $l_b[$j]); //去掉colspan
continue;
}
if($j == $l+1) {
for($k=0; $k $l_c .= "
}
$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("
.*", "", $l_str);
$l_str = eregi_replace(" ", "", $l_str); //去掉
$l_str = eregi_replace(" ", "", $l_str); //去掉
$l_str = eregi_replace("", " ", $l_str); //使表格的一行成为一行数据
$l_str = strip_tags($l_str, ""); //只保留
, HTML表记
$l_str = eregi_replace(" ", "", $l_str); //去掉
$l_str = eregi_replace(" ", "", $l_str); //去掉
$l_str = eregi_replace("", " ", $l_str); //使表格的一行成为一行数据
$l_str = strip_tags($l_str, "
while(eregi("while(eregi("/////至此,表格处理已完成.
$l_str = eregi_replace("
", $l_str); //给每一格之间加上标记
$l_str = strip_tags($l_str, "
");
$l_a = explode("
", $l_str);
for($i=0; $i $l_str = trim($l_a[$i]);
if(empty($l_str)) continue;
$l_b = explode("
", $l_str);
foreach($l_b as $val) {
echo $val." "; //表格每列内容间加空格
}
echo "
"; //表格的一行显示为一行
}
for($i=0; $i
if(empty($l_str)) continue;
$l_b = explode("
", $l_str);
foreach($l_b as $val) {
echo $val." "; //表格每列内容间加空格
}
echo "
"; //表格的一行显示为一行
}
//附测试用例和测试结果:
/***********测试用表格*************************************************************
