PHP 文章采集代碼主要是應用了正則表達式。
//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;
}
//獲得標題和url
$string =
getwebcontent('http://www.***.com/learn/zhunbeihuaiyun/jijibeiyun/2');
//正則匹配<li>獲取標題和地址
preg_match_all ("/<li><a href=\"\/learn\/article\/(.*)\">(.*)<\/a>/",$string, $out, PREG_SET_ORDER);
foreach($out as $key => $value){
$article['title'][] = $out[$key][2];
$article['link'][] = "http://www.***.com/learn/article/".$out[$key][1];
}
//根據url獲取文章內容
foreach($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] = $matches[0];
}
//不轉碼還真不能保存成文件
foreach($article[title] as $key=>$value){
$article[title][$key] = iconv('utf-8', 'gbk', $value);//轉碼
}
//存入文件
$num = count($article['title']);
for($i=0; $i<$num; $i++){
file_put_contents("{$article[title][$i]}.txt", $article['content'][$i]);
}
?>
