PHP Forum Acquisition Program simulation Landing, crawl page implementation code _php instance

Copy Code code as follows:

<?php
Wu Yanjun
2009-06-27
Acquisition program PHP
Set_time_limit (0);
Cookie Save Directory
$cookie _jar = '/tmp/cookie.tmp ';
/* Function------------------------------------------------------------------------------------------------------------ */
Simulate request data
function request ($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 $code;
}
Get a list of posts
function Getthreadslist ($code) {
Preg_match_all ('/<!--[. | \r|\n]*? <a href=\ "viewthread.php\?tid= (\d+)/', $code, $threads);
return $threads [1];
}
Determine if the post exists
function Isexits ($code) {
Preg_match ('/<p> The specified topic does not exist or has been deleted or is being audited, please return. <\/p>/', $code, $error);
return isset ($error [0]) false:true;
}
Get post title
function GetTitle ($code) {
Preg_match ('/$title = $title _tmp[0];
return $title;
}
Get post Author:
function Getauthor ($code) {
Preg_match ('/<a href=\ ' space.php\?uid=\d+\ "target=\" _blank\ "id=\" userinfo\d+\ "onmouseover=\" showMenu\ (this\. id\) \ ">.+/', $code, $author _tmp);"
$author = Strip_tags ($author _tmp[0]);
return $author;
}
Get the content published by the landlord
function getcontents ($code) {
Preg_match ('/<div id=\ "postmessage_\d+\" class=\ "t_msgfont\" > (. | \r|\n) *? <\/div>/', $code, $contents _tmp);
$contents = preg_replace ('/images\//', ' http://bbs.war3.cn/images/', $contents _tmp[0]);
return $contents;
}
Print post title
function PrintTitle ($title) {
echo "<strong> }
Output Post author
function Printauthor ($author) {
echo "<strong> }
Print post Content
function Printcontents ($contents) {
echo "<strong> }
Error
function Printerror () {
echo "<i> The post does not exist! </i> ";
}
/* Function List End---------------------------------------------------------------------------------------------------* *
/* Login Forum begin*/
$url = ' Http://bbs.war3.cn/logging.php?action=login ';
$postfields = ' loginfield=username&username=1nject10n& password=xxxxxx&questionid=0&cookietime= 315360000& referer=http://bbs.war3.cn/&loginsubmit= submission ';
Request ($url, $postfields, $cookie _jar, ");
Unset ($postfields, $url);
/* Login Forum end*/
/* Get a list of posts (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
$rows = 0;
/* Loop Crawl all posts source code begin*/
foreach ($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 "<div style= ' background-color: $color ' >";
echo "$author = Getauthor ($code);
Printauthor ($author);
$title = GetTitle ($code);
PrintTitle ($title);
$contents = getcontents ($code);
Printcontents ($contents);
echo "</div>";
$rows + +;
}
Else
Printerror ();
echo "-----------------------------------------------------------------------------------------<br/> < Br/> ";
}
/* Crawl Source code end*/
?>