Collection forum program: simulate login, capture page_PHP tutorial

// 吴燕军 // 2009-06-27 // 采集程序php set_time_limit(0);

//cookie保存目录 $cookie_jar = /tmp/cookie.tmp;

/*函数------------------------------------------------------------------------------------------------------------*/

//模拟请求数据 function request($url,$postfields,$cookie_jar,$referer){ $ch = curl_init(); $options = array(CURLOPT_URL => $url, CURLOPT_HEADER => 0, CURLOPT_NOBODY => 0, CURLOPT_PORT => 80, CURLOPT_POST => 1, CURLOPT_POSTFIELDS => $postfields, CURLOPT_RETURNTRANSFER => 1, CURLOPT_FOLLOWLOCATION => 1, CURLOPT_COOKIEJAR => $cookie_jar, CURLOPT_COOKIEFILE => $cookie_jar, CURLOPT_REFERER => $referer ); curl_setopt_array($ch, $options); $code = curl_exec($ch); curl_close($ch); return $code; }

//获取帖子列表 function getThreadsList($code){ preg_match_all(/ return $threads[1]; }

//判断该帖子是否存在 function isExits($code){ preg_match(/ 指定的主题不存在或已被删除或正在被审核，请返回。

/,$code,$error); return isset($error[0])?false:true; }

//获取帖子标题 function getTitle($code){ preg_match(/ [^ ]*/,$code,$title_tmp); $title = $title_tmp[0]; return $title; }

//获取帖子作者: function getAuthor($code){ preg_match(/ .+/,$code,$author_tmp); $author = strip_tags($author_tmp[0]); return $author; }

//获取楼主发表的内容 function getContents($code){ preg_match(/ (.|| )*? /,$code,$contents_tmp); $contents = preg_replace(/images//,http://bbs.war3.cn/images/,$contents_tmp[0]); return $contents; }

//Print post title function printTitle($title){ echo " Post title: ",strip_tags($title),"

"; }

//Output the post author function printAuthor($author){ echo " Post author: ",strip_tags($author),"

"; }

//Print post content function printContents($contents){ echo " Content published by the author: ",$contents," "; }

//Error function printError(){ echo " This post does not exist! "; }

/*Function listend--------------------------------------------- -------------------------------------------------- -------*/

/*Log in to the forum begin*/ $url = http://bbs.war3.cn/logging.php?action=login; $postfields=loginfield=username&username=1nject10n&password=xxxxxx&questionid=0&cookietime=315360000&referer=http://bbs.war3.cn/&loginsubmit=Submit; request($url,$postfields,$cookie_jar,); unset($postfields,$url); /*Log in to the forum end*/

/*Get the post list (posts on the first page) begin*/ $url = http://bbs.war3.cn/forumdisplay.php?fid=57; $code = request($url,,$cookie_jar,); $threadsList = getThreadsList($code); /*Get the post list end*/

//Post sequence $rows = 0;

/*Loop to grab the source code of all posts begin*/ foreach($threadsList as $list){ $url = "http://bbs.war3.cn/viewthread.php?tid=$list";

if(isExits($code)){ $code = request($url,,$cookie_jar,); $color = $rows%2==0?#00CCFF:#FFFF33; echo " "; echo " th",($rows+1),"Post: "; $author = getAuthor($code); printAuthor($author);

$title = getTitle($code); printTitle($title);

$contents = getContents($code); printContents($contents); echo " "; $rows++; } else printError();

echo "------------------------------------------------ -----------------------------------------------

"; } /*Grab source code end*/ ?>

http://www.bkjia.com/PHPjc/486512.html www.bkjia.com true http: //www.bkjia.com/PHPjc/486512.html TechArticle ?php // Wu Yanjun // 2009-06-27 // Collection program php set_time_limit(0); / /cookie saving directory $cookie_jar = /tmp/cookie.tmp; /*Function--------------------------------- ------------------...