php网络爬虫，实现采集功能

//获取天气预报网站的网页内容
$html = file_get_contents("http://www.weather.com.cn/weather1d/101210101.shtml");
//正则表达式
$reg = ‘#hour3data.+?\[".+?,.+?,(?<tianqi>.+?),(?<wendu>.+?),#‘;
//如果匹配成功，就输出温度相关的信息
if(preg_match($reg, $html, $mat)){
    echo "今天".$mat[‘tianqi‘].",温度".$mat[‘wendu‘];
}

$url = "http://r.pengyou.com/fcg-bin/cgi_get_portrait.fcg?uins=1579715173";
$html = file_get_contents($url);
$reg = ‘#.+?\["(.+?)",.+?,.+?,.+?,.+?,.+?,"(.+?)"#‘;
if(preg_match($reg, $html, $mat)){
    //由于防盗链，无法直接使用腾讯的头像链接，所以要先下载到本地
    file_put_contents("1.jpg",file_get_contents($mat[1]));
    echo "<img src=‘./1.jpg‘ />".$mat[2];
}

$ip = "14.215.177.38";
$html = file_get_contents("http://ip.chinaz.com/".$ip);
$regex = ‘#<p class="WhwtdWrap bor-b1s col-gray03">[\s\S]+?<span class="Whwtdhalf w50-0">(.+?)</span>[\s\S]+?</p>#‘;
if(preg_match($regex, $html, $mat)){
    echo $mat[1];
}

$html = file_get_contents("http://book.qidian.com/info/1004608738");
$regex = ‘#<li data-rid="\d+?"><a href="(.+?)"[\s\S]+?>(.+?)</a>[\s\S]+?</li>#‘;
if(preg_match_all($regex, $html, $mats)){
    foreach($mats[1] as $k => $v){
        $html1 = file_get_contents("http:".$v);
        $regex1 = ‘#<div class="read-content j_readContent">([\s\S]+?)</div>#‘;
        //匹配内容
        if(preg_match($regex1, $html1, $mat)){
            $mat[1] = preg_replace(‘#<.+?>|\s+?#‘, "",$mat[1]);
            $content = "\r\n".$mats[2][$k]."\r\n".$mat[1];
            file_put_contents("1.txt", $content, FILE_APPEND);
        } else {
            echo "内容没有匹配成功";
        }
        echo $mats[2][$k]."\n";
    }
}