//Collect 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;
}
//Get the title and url
$string =
getwebcontent('http://www.***.com/learn/zhunbeihuaiyun/jijibeiyun/2');
//Regular matching <Li> Gets the title and address
preg_match_all ("/<li><a href="/learn/article/(.*)">(.*)</a>/",$string, $out, PREG_SET_ORDER);
foreach($out as $key => $value){
$article['title'][] = $out[$key][2];
$article['link'][] = "http://www.***.com/learn/article/".$out[$key][1];
}
//Get the article content based on the url
foreach($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] = $matches[0];
}
//It really can't be saved to a file without transcoding
foreach($article[title] as $key=>$value){
$article[title][$key] = iconv('utf-8', 'gbk', $value);//transcoding
}
//In the file
$num = count($article['title']);
for($i=0; $i<$num; $i++){
file_put_contents("{$article[title][$i]}.txt", $article['content'][$i]);
}
?>