//包含PHP Simple html Dom 类库文件
include_once('./simplehtmldom/simple_html_dom.php');
//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.babytree.com/learn/zhunbeihuaiyun/jijibeiyun/2');
//正则匹配
获取标题和地址
preg_match_all ("/
(.*)/",
$string, $out, PREG_SET_ORDER);
foreach($out as $key => $value){
$article['title'][] = $out[$key][2];
$article['link'][] = "http://www.babytree.com/learn/article/".$out[$key][1];
}
//根据url获取文章内容
foreach($article['link'] as $key=>$value){
$html = file_get_html($value);
$div = $html->find('div[id=pagenum_0]');
$article[content][] = $div[0]->innertext;
}
//标题转码---真正用的时候不用这步--因为咱本来就要用utf8的
//不转码还真不能保存成文件
foreach($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; $i
file_put_contents("{$article[title][$i]}.txt", $article['content'][$i]);
}
/*本来想12点之前发的。。但小看一下都3点半了。。。 就算昨天的吧
本来获取文章内容时用正则是最好的，速度也是最快的，
奈何正则是好，但正则表达式是真难！于是乎小查了一下，
网上也有很多人也在用PHP Simple Dom 虽然效率慢了点，但效果还是不错的
从包含类库文件到写入txt文件 大概是7/8就秒 还有带于进一步优化，特别是那获取文章内容时的正则，那个太恶心了
大家可以小研究一下*/
?> Statement：The content of this article is voluntarily contributed by netizens, and the copyright belongs to the original author. This site does not assume corresponding legal responsibility. If you find any content suspected of plagiarism or infringement, please contact admin@php.cn
