Question

php curl获取不到淘宝页面。

代码：

<?php
$curl = curl_init();
curl_setopt($curl,CURLOPT_URL,$_GET['url']);
curl_setopt($curl,CURLOPT_RETURNTRANSFER,true);
curl_setopt($curl,CURLOPT_USERAGENT,"Mozilla/4.0 (compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)");
$output = curl_exec($curl);
curl_close($curl);
print_r($output);

Answer 1

　　正确的抓取方法如下（仅供参考肢清）：
　　/**
　　* 根据地址抓取淘宝页面html代码
　　* @param type $url 地址
　　* @return boolean
　　*/
　　public function getTaoBaoHtml($url) {
　　if (empty($url)) {
　　return false;
　　}
　　$ch = curl_init();
　　// 设置 url
　　curl_setopt($ch, CURLOPT_URL, $url);
　　// 设置浏览尘饥芦器的特定header
　　curl_setopt($ch, CURLOPT_HTTPHEADER, array(
　　"User-Agent: {Mozilla/5.0 (Windows NT 6.1; WOW64; rv:26.0) Gecko/20100101 Firefox/26.0}",
　　"Accept: {text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8}",
　　"派带Accept-Language: {zh-cn,zh;q=0.8,en-us;q=0.5,en;q=0.3}",
　　"Cookie:{cq=ccp%3D1; cna=a7suCzOmSTECAXgg9iCf4AtX; t=671b2069c7e8ac444da66d664a397a5f; tracknick=%5Cu4F0D%5Cu6653%5Cu8F8901; _tb_token_=nDiU1vCuzFd0; cookie2=c54709ffbe04a5ccb80283c34d6b00fa; pnm_cku822=128WsMPac%2FFS4KgNn%2BYfhzduo4U2NC0zh9cAS4%3D%7CWUCLjKhqr873bOIFQcMecSw%3D%7CWMEKRlV%2B3D9a6XWaidNWNQOSWXwaXugvQHzhxALh%7CX0YLbX78NUR2b2DHoxnIqZENQqR35TBZbfQ5vooI0b6GHZA3U1kr%7CXkdILogCr878ZK9I%2B%2FE3QjAD3lFJJaAZRA%3D%3D%7CXUeMwMR2s%2BTUQk8IPP5TNgWfUjQwonccMCxihTa0fRYgtjgfa4j6%7CXMYK7F8liOvH3hMUpzXkiaU%2FJw%3D%3D}",
　　));
　　// 页面内容我们并不需要
　　curl_setopt($ch, CURLOPT_NOBODY, 0);
　　// 只需返回HTTP header
　　curl_setopt($ch, CURLOPT_HEADER, 0);
　　// 返回结果，而不是输出它
　　//curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
　　curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
　　ob_start();
　　curl_exec($ch);
　　$html = ob_get_contents();
　　ob_end_clean();
　　curl_close($ch);
　　return $html;
　　}

Answer 2

$curl = curl_init();
curl_setopt($curl,CURLOPT_URL,$_GET['url']);
curl_setopt($curl,CURLOPT_RETURNTRANSFER,true);
curl_setopt($curl,CURLOPT_USERAGENT,"Mozilla/4.0
(compatible; MSIE 6.0; Windows NT 5.1; SV1; .NET CLR 1.1.4322; .NET CLR 2.0.50727)");
$output = curl_exec($curl);
curl_close($curl);
print_r($output);