<?php
/**
* 采集类
* @author Milkcy
* @copyright (C) 2012-2015 TCCMS.COM
* @lastmodify 2012-07-10 14:00
*/
class gather {
public $pagestring = '';
private $db;
function __construct() {
global $db;
$this->db = $db;
}
function geturlfile($url) {
$url = trim($url);
$content = '';
if (extension_loaded('curl')) {
$ch = curl_init();
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
curl_setopt($ch, CURLOPT_HEADER, 0);
$content = curl_exec($ch);
curl_close($ch);
} else {
$content = file_get_contents($url);
}
return trim($content);
}
function get_all_url($code) {
preg_match_all('/<a.+?href=["|\\']?([^>"\\' ]+)["|\\']?\\s*[^>]*>([^>]+)<\\/a>/is', $code, $arr);
return array('name' => $arr[2], 'url' => $arr[1]);
}
function get_sub_content($str, $start, $end) {
$start = trim($start);
$end = trim($end);
if ($start == '' || $end == '') {
return $str;
}
$str = explode($start, $str);
$str = explode($end, $str[1]);
return $str[0];
}
function vd($var) {
echo "<div style=\\"border:1px solid #ddd;background:#F7F7F7;padding:5px 10px;\\">\\r\\n";
echo "<pre style=\\"font-family:Arial,Vrinda;font-size:14px;\\">\\r\\n";
var_dump($var);
echo "\\r\\n</pre>\\r\\n";
echo "</div>";
}
}
?>
<?php
define('ROOT_PATH', str_replace('\\\\', '/', dirname(__FILE__)));
include ROOT_PATH."/gather.class.php";
set_time_limit(0);
header("Content-type: text/html; charset=gb2312");
//目标网址
$url = 'http://news.163.com/special/00013C0O/guojibjtj_03.html';
//实例化采集机器
$gather = new gather();
//获取目标网址HTML
$html = $gather->geturlfile($url);
//定义采集列表区间
$start = '<div class="bd clearfix">';
$end = '<div class="pages-1 mt25">';
//获取区间内的文章URL和TITLE
$code = $gather->get_sub_content($html, $start, $end);
$newsAry = $gather->get_all_url($code);
//打印出结果
//$gather->vd($newsAry);
$tarGetUrl = $newsAry['url'][0];
//获取目标网址HTML
$html = $gather->geturlfile($tarGetUrl);
//定义采集列表区间
$start = '<div id="endText">';
$end = '<span class="cDGray right" style="white-space:nowrap;">';
//获取区间内的文章URL和TITLE
$code = $gather->get_sub_content($html, $start, $end);
$killHtml = '<iframe src="http://g.163.com/r?site=netease&affiliate=news&cat=article&type=tvscreen200x300&location=1" width="200" height="300" frameborder="no" border="0" marginwidth="0" marginheight="0" scrolling="no"></iframe>';
$killHtml2 = '<a href="http://news.163.com/"><img src="http://img1.cache.netease.com/cnews/img07/end_i.gif" alt="netease" width="12" height="11" border="0" class="icon" /></a>';
$code = str_replace($killHtml, "", $code);
$code = str_replace($killHtml2, "", $code);
$gather->vd($code);
?>
//该片段来自于http://outofmemory.cn
php 文章采集正则代码
//采集html
function getwebcontent($url){
$ch = curl_init();
$timeout = 10;
curl_setopt($ch, CURLOPT_URL, $url);
curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
curl_setopt($ch, CURLOPT_CONNECTTIMEOUT, $timeout);
curl_setopt ($ch, CURLOPT_FOLLOWLOCATION, 1);
$contents = trim(curl_exec($ch));
curl_close($ch);
return $contents;
}
//获得标题和url
$string =
getwebcontent('http://www.***.com/learn/zhunbeihuaiyun/jijibeiyun/2');
//正则匹配<li>获取标题和地址
preg_match_all ("/<li><a href=\"\/learn\/article\/(.*)\">(.*)<\/a>/",$string, $out, PREG_SET_ORDER);
foreach($out as $key => $value){
$article['title'][] = $out[$key][2];
$article['link'][] = "http://www.***.com/learn/article/".$out[$key][1];
}
//根据url获取文章内容
foreach($article['link'] as $key=>$value){
$content_html = getwebcontent($article['link'][$key]);
preg_match("/<div id=pagenum_0(.*)>[\s|\S]*?<\/div>/",$content_html,$matches);
$article[content][$key] = $matches[0];
}
//不转码还真不能保存成文件
foreach($article[title] as $key=>$value){
$article[title][$key] = iconv('utf-8', 'gbk', $value);//转码
}
//存入文件
$num = count($article['title']);
for($i=0; $i<$num; $i++){
file_put_contents("{$article[title][$i]}.txt", $article['content'][$i]);
}
?>
