$SqlStr .= '\'' . $cateid . '\',';
//起始标记
$SqlStr .= '`flagstart`=';
$SqlStr .= '\'' . $flagstart . '\',';
//结束标记
$SqlStr .= '`flagend`=';
$SqlStr .= '\'' . $flagend . '\',';
//内容开始标记
$SqlStr .= '`flagcontentstart`=';
$SqlStr .= '\'' . $flagcontentstart . '\',';
//内容结束标记
$SqlStr .= '`flagcontentend`=';
$SqlStr .= '\'' . $flagcontentend . '\',';
//广告开始标记Array
$SqlStr .= '`flagadstart`=';
$SqlStr .= '\'' . EnCodeStr($flagadstartarray) . '\',';
//广告结束标记Array
$SqlStr .= '`flagadend`=';
$SqlStr .= '\'' . EnCodeStr($flagadendarray) . '\',';
//单项替换
$SqlStr .= '`flagsingle`=';
$SqlStr .= '\'' . EnCodeStr($flagsinglearray) . '\',';
//更新日期
$SqlStr .= '`posttime`=';
$SqlStr .= '\'' . date("Y-m-d", time()) . '\'';
$SqlStr .= ' WHERE `id`=' . $id;
query($SqlStr);
$refresh_msg = '采集规则[<font color="#FF0000">' . $title . '</font>]，修改添加成功，返回修改页面。';
$refresh_url = 'source_edit.php?id=' . $id;
require $page_name . '.php';
require '../include/debug.inc.php';
/**
* 远程抓取图片，保存到本地服务器
* @param $content 需要转换的内容
* @return 返回图片替换后的数据
*/
function getContent($Content)
{
$Content = stripslashes($Content);
// echo $Content;
//获取图片路径
// preg_match_all( " <img[^>]*src=[\"|']?(^>+)[\"|']?[^>]*>", $Content, $temp );
// preg_match_all( "/src=(\"|')(.*?)(\"|')/i", DeCodeStr($Content), $temp );
preg_match_all("/src=(\"|')(.*?)(\"|')/i", $Content, $temp);
$imageList = $temp[2];
// echo '<hr>'. print_r($imageList) . '<hr>';
//*/
$ImagePath = date("ym", time()) . '/' . date("d", time());
createFolder(IMAGEPATH, $ImagePath);
//网页上面的路径
$ImageUrl = IMAGEURL . $ImagePath;
for ($i = 0; $i < count($imageList); $i++) {
$fName = saveFile($imageList[$i], $ImagePath, $ImageUrl);
if (!empty($fName)) {
$filename[$i] = $fName;
}
}
for ($i = 0; $i < count($imageList); $i++) {
$Content = str_replace($imageList[$i], $ImageUrl . $filename[$i], $Content);
}
/*
echo '<hr>';
echo $Content;
echo '<hr>';
exit();
//*/
/*
//去掉无用的页面脚本
//去掉js
$cp = preg_replace( "@\<script(.*?)\</script\>@is", "", $cp );
//去掉HTML
//去Table
$cp = preg_replace( "@\<table(.*?)\</table\>@is", "", $cp );
//去Tr
$cp = preg_replace( "@\<tr(.*?)\</tr\>@is", "", $cp );
//去Td
$cp = preg_replace( "@\<td(.*?)\</td\>@is", "", $cp );
//去div
$cp = preg_replace( "@\<div(.*?)\</div\>@is", "", $cp );
//去iframe
$cp = preg_replace( "@\<iframe(.*?)\</iframe\>@is", "", $cp );
//去掉css
//$cp = preg_replace( "@\<style(.*?)\</style\>@is", "", $cp );
*/
//去掉超连接
$Content = preg_replace(EnCodeStr("@\\<a(.*?)\\>@is"), "", $Content);
//去<!-- -->
$Content = preg_replace(EnCodeStr("@\\<!--(.*?)\\--\\>@is"), "", $Content);
return $Content;
}
/**
* 得到一个字符串中的某一部分
* @param $Url 需要抓取的地址
* @param $ArticleId 入库文章编号
* @param $ContentStartFlag 文章内容开始、结束
* @param $ContentEndFlag
* @param $FlagAdStart 过滤广告开始、结束标志
* @param $FlagAdEnd
* @param $FlagSingle 单项过滤
* @param $ImagePath 图片保存地址
* @param $ImageUrl 图片显示地址
*/
function getContent($Url, $id, $ContentStartFlag, $ContentEndFlag, $FlagAdStart, $FlagAdEnd, $FlagSingle, $ImagePath, $ImageUrl, $utf8)
{
//获取源数据
$Content = file_get_contents($Url);
//echo $Content;
$Content = EnCodeStr($Content);
//echo $Content;
/*
Zerolone Add 07-04-28
如果是UTF-8编码的则
//*/
if ($utf8) {
$Content = mb_convert_encoding($Content, "GB2312", "UTF-8");
}
//切割数据
$Content = CutStr($Content, $ContentStartFlag, $ContentEndFlag);
//echo $Content;
//切割广告
//*//
$FlagAdStartArray = explode(",", $FlagAdStart);
$FlagAdEndArray = explode(",", $FlagAdEnd);
for ($i = 0; $i < count($FlagAdStartArray); $i++) {
$Content = CutStr($Content, $FlagAdStartArray[$i], $FlagAdEndArray[$i], 1);
}
//*/
//echo $Content;
//单项替换
$FlagSingleArray = explode(",", $FlagSingle);
for ($i = 0; $i < count($FlagSingleArray); $i++) {
$Content = str_replace($FlagSingleArray[$i], '', $Content);
}
echo $Content;
//获取图片路径
preg_match_all("/src=(\"|')(.*?)(\"|')/i", DeCodeStr($Content), $temp);
$imageList = $temp[2];
//echo $imageList;
//建立文件夹
if (!is_dir($ImagePath)) {
mkdir($ImagePath);
}
$ImagePath .= '/' . date("m", time());
if (!is_dir($ImagePath)) {
mkdir($ImagePath);
}
$ImagePath .= '/' . date("d", time()) . '/';
if (!is_dir($ImagePath)) {
mkdir($ImagePath);
}
//网页上面的路径
$ImageUrl .= date("m", time()) . '/' . date("d", time()) . '/';
for ($i = 0; $i < count($imageList); $i++) {
$fName = saveFile($imageList[$i], $ImagePath, $ImageUrl);
if (!empty($fName)) {
$filename[$i] = $fName;
}
}
for ($i = 0; $i < count($imageList); $i++) {
$Content = str_replace($imageList[$i], $ImageUrl . $filename[$i], $Content);
}
/*
echo '<hr>';
echo decode($TheContent);
echo '<hr>';
exit();
//*/
/*
//去掉无用的页面脚本
//去掉js
$cp = preg_replace( "@\<script(.*?)\</script\>@is", "", $cp );
//去掉HTML
//去Table
$cp = preg_replace( "@\<table(.*?)\</table\>@is", "", $cp );
//去Tr
$cp = preg_replace( "@\<tr(.*?)\</tr\>@is", "", $cp );
//去Td
$cp = preg_replace( "@\<td(.*?)\</td\>@is", "", $cp );
//去div
$cp = preg_replace( "@\<div(.*?)\</div\>@is", "", $cp );
//去iframe
$cp = preg_replace( "@\<iframe(.*?)\</iframe\>@is", "", $cp );
//去掉css
//$cp = preg_replace( "@\<style(.*?)\</style\>@is", "", $cp );
*/
//去掉超连接
$Content = preg_replace(EnCodeStr("@\\<a(.*?)\\>@is"), "", $Content);
//去<!-- -->
$Content = preg_replace(EnCodeStr("@\\<!--(.*?)\\--\\>@is"), "", $Content);
//页面内容入库
$SqlStr = 'UPDATE `' . table_pre . 'article` SET ';
//文章内容
$SqlStr .= '`flag`=1,';
//文章内容
$SqlStr .= '`content`=';
$SqlStr .= '\'' . $Content . '\'';
$SqlStr .= ' WHERE `id`=' . $id;
// echo $SqlStr;
query($SqlStr);
return true;
}
