提供一款免费的php 问问采集代码哦,如果你正想采集问问,但是又不知道怎么写采集程序,这里为你提供一款经典的问问采集程序哦。
提供一款免费的php教程 问问采集代码哦,如果你正想采集问问,但是又不知道怎么写采集程序,这里为你提供一款经典的问问采集程序哦。
session_start();
header("content-type:text/html;charset=utf-8");
require("stole_config.php");
require("conn.php");
require("keyword.php");
if(!empty($_post['ask']))
{
$ask=urlencode(trim($_post['ask']));//获取表单提交的问题
$sp="s".$ask;
}else
{
$sp=urlencode($_get['sp']);
}
if(empty($_get['jl']))
{
$_get['jl']=1;
}
$jl=$_get['jl'];
$pg=intval($_get['pg']);//获取页数
$rs=intval($_get['rs']);//获得 记录的参数
if($rs>9)
{
$rs=0;
$pg++;
}
if($pg>51)
{
echo "采集完毕! 总共采集 ".urldecode($sp)." ".$jl."条记录";
exit();
}
if($sp)//有设定答案才开始
{
$str=@file_get_contents("http://wenwen.soso.com/z/search.e?sp={$sp}&pg={$pg}");
@preg_match("/(.*)
/ius",$str,$asklist);//获取问答列表
//echo $asklist[1];
$url="/@preg_match_all($url,$asklist[1],$urllist);//获取 所有的问题
$t=$urllist[1][$rs];
$uid=$t;
$suid="ww{$uid}";
$sct=mysql教程_query("select count(*) from {$table_prefix}c_article where suid='$suid' ");
$sct=mysql_fetch_array($sct);
$sct=$sct[0];
if($sct==0)
{
$html=@file_get_contents("http://wenwen.soso.com/z/${t}");
$html=str_replace("","",str_replace("","",$html));
$html=str_replace("
","
",$html);
//echo $html;
@preg_match("/.*(.*)
/ius",$html,$ask_title);
$art_title=$ask_title[1];
@preg_match("/(.*)/ius",$html,$answer);
$j=count($answer)-1;
$art_content="";//Product details
for($i=$j; $i>=1;$i--)
{
if(strlen($answer[$i])>$min_t1)
{
$art_content .= $answer[$i ];
}
}
$art_content=trim($art_content);
$s1="/()(.*)/ius ";
$art_content=preg_replace($s1,${2},trim($art_content));
$word_arr=explode(",",iconv("gbk","utf-8",$ cj_word));
$word_allow=false;//Whether initialization allows collection
$word_count=count($word_arr);//Total number
for($i=0;$i<$word_count;$ i++)
{
if(substr_count($art_title,$word_arr[$i])>0)
{
$word_allow=1;
$i=$word_count;
}
}
if($word_allow)//If legal
{ //Start processing database tutorial
if(strlen($art_content)>$min_t2)
{
echo "Adding......................
";
echo $art_title."
";
$art_title=iconv('utf-8','gbk', $art_title);
$title_ct=mysql_query("select count(*) from {$table_prefix}c_article where art_title ="$art_title" ");//Check whether the title is repeated
$title_ct=@mysql_fetch_array($title_ct);
$title_ct=$title_ct[0];
if($title_ct>0)
{
$art_title .="{$same_title}{$title_ct}";
}
$art_content=iconv('utf-8','gbk' ,str_replace("rn","
",$art_content));
$art_content=strtr($art_content,$keyword);
$art_time=date("y-m-d");
$sql="insert into {$table_prefix}c_article(art_title,art_content,art_time,art_author,suid) values('$art_title','$art_content','$art_time','$art_author','$suid')" ;//Insert collection table
mysql_query($sql);
if(empty($t_catx_id))//If no classification
{
$sql2="insert into {$t_table}({ $t_art_title},{$t_art_content},{$t_art_time},{$t_artx_author}) values('$art_title','$art_content','$art_time','$art_author')";
}else
{
$sql2="insert into {$t_table}({$t_art_title},{$t_art_content},{$t_art_time},{$t_artx_author},{$t_catx_id}) values('$art_title','$ art_content','$art_time','$art_author','$cat_id')";
}
mysql_query($sql2);//Insert into the article table
$jl++;//If stored in the database Then add 1 to the record
//End of database processing
}else
{
echo "The length is not enough";
}
}else
{
echo "The subject is not enough" Meets the requirements";
}
}else
{
echo "Already exists";
}
$rs++;
//Record the status of this collection
$f_tt= urldecode($sp)."--Number of pages".$pg." Number of records".$jl;
file_put_contents("ss.txt",$f_tt);
echo "< script>location.href='wenwen.php?jl=".$jl."&sp=".$sp."&pg=".$pg."&rs=".$rs." '; ";
exit();
}
?>
RecommendationKnow Ask Collection Plug-in< /h1>
Collection settings Uninstall collection View collection record Collection Help Know the collection Ask the collection< ;/td>