尝试抓取的页面,结果:
换其他链接不会出现这样的问题,请问如何解决这个问题??
有没有能够正常抓取到 http://www.chwfsc.com/ 这个网站内容的范例??
闭关修行中......
mb_http_output('utf-8');$url="http://www.chwfsc.com/";$ch=curl_init();curl_setopt($ch,CURLOPT_URL,$url);curl_setopt($ch,CURLOPT_HEADER,0);curl_setopt($ch,CURLOPT_NOBODY, true);curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);curl_setopt($ch,CURLOPT_ENCODING,'utf8');curl_setopt($ch,CURLOPT_POST,1);curl_setopt($ch,CURLOPT_USERAGENT,'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.47 Safari/536.11');$html=curl_exec($ch);curl_close($ch);var_dump($html);可以了,亲测可用
封装个curl试试
function task() { $url = "url"; $headers = randIp(); $curl = curl_init(); curl_setopt($curl, CURLOPT_URL, $url); curl_setopt($curl, CURLOPT_BINARYTRANSFER, true); curl_setopt($curl, CURLOPT_HTTPHEADER, $headers); curl_setopt($curl, CURLOPT_FOLLOWLOCATION, 1); curl_setopt($curl, CURLOPT_SSL_VERIFYPEER, false); curl_setopt($curl, CURLOPT_SSL_VERIFYHOST, 2); curl_setopt($curl, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows NT 6.1; WOW64; rv:12.0) Gecko/20100101 Firefox/12.0"); //模拟浏览器类型 curl_setopt($curl, CURLOPT_TIMEOUT, 300); // 设置超时限制防止死循环 curl_setopt($curl, CURLOPT_HEADER, 0); // 显示返回的Header区域内容 curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1); // 获取的信息以文件流的形式返回 $tmpInfo = curl_exec($curl); if (curl_errno($curl)) { print "Error: " . curl_error($curl); } else { curl_close($curl); } } //此函数提供了国内的IP地址 function randIP(){ $ip_long = array( array('607649792', '608174079'), //36.56.0.0-36.63.255.255 array('1038614528', '1039007743'), //61.232.0.0-61.237.255.255 array('1783627776', '1784676351'), //106.80.0.0-106.95.255.255 array('2035023872', '2035154943'), //121.76.0.0-121.77.255.255 array('2078801920', '2079064063'), //123.232.0.0-123.235.255.255 array('-1950089216', '-1948778497'), //139.196.0.0-139.215.255.255 array('-1425539072', '-1425014785'), //171.8.0.0-171.15.255.255 array('-1236271104', '-1235419137'), //182.80.0.0-182.92.255.255 array('-770113536', '-768606209'), //210.25.0.0-210.47.255.255 array('-569376768', '-564133889'), //222.16.0.0-222.95.255.255 ); $rand_key = mt_rand(0, 9); $ip= long2ip(mt_rand($ip_long[$rand_key][0], $ip_long[$rand_key][1])); $headers['CLIENT-IP'] = $ip; $headers['X-FORWARDED-FOR'] = $ip; $headerArr = array(); foreach( $headers as $n => $v ) { $headerArr[] = $n .':' . $v; } return $headerArr; }
mb_http_output('utf-8');
$url="http://www.chwfsc.com/";
$ch=curl_init();
curl_setopt($ch,CURLOPT_URL,$url);
curl_setopt($ch,CURLOPT_HEADER,0);
curl_setopt($ch,CURLOPT_NOBODY, true);
curl_setopt($ch,CURLOPT_RETURNTRANSFER,1);
curl_setopt($ch,CURLOPT_ENCODING,'utf8');
curl_setopt($ch,CURLOPT_POST,1);
curl_setopt($ch,CURLOPT_USERAGENT,'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.47 Safari/536.11');
$html=curl_exec($ch);
curl_close($ch);
var_dump($html);
可以了,亲测可用
封装个curl试试