我想实现通过淘宝号查询淘宝买家信誉的功能，就像131458.com的一样。
我的思路是通过curl采集这个网站的数据。但是却被防了，返回给我的是无用的信息。
代码如下：
$parm=$data['parm']."&_=".time()."326"; //参数 $ch= curl_init(); $uri="http://www.131458.com/handler/TaobaoInfo.ashx?"; curl_setopt($ch, CURLOPT_URL, $uri.$parm); curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); curl_setopt($ch, CURLOPT_HEADER, 0); curl_setopt($ch, CURLOPT_REFERER, "http://www.131458.com/"); //curl_setopt($ch, CURLOPT_HTTPHEADER, array('X-FORWARDED-FOR:125.67.52.246', 'CLIENT-IP:125.67.52.246')); curl_setopt($ch, CURLOPT_USERAGENT, "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/35.0.1916.153 Safari/537.36 SE 2.X MetaSr 1.0"); / $return = curl_exec($ch); curl_close($ch); echo $return; 请问还要添加什么，才能模拟浏览器访问，采集到正常数据。
回复讨论(解决方案)
抓包看看呢？一般都是header里面需要啥，就都传过去
首先，你的方法不对，则是chrome F12下跟踪的结果，CURL命令如下：
curl "http://www.131458.com/handler/TaobaoInfo.ashx?tbNickInfoJson=hades&token=736905fff9ee639a4b5f46b53526434b_0b32d3aec47ad29fef2d7ddb67831933&_=1447405734036" -H "Cookie: ASP.NET_SessionId=4ki3s2yhj2555bzxlbvdqhju; Hm_lvt_ccc93bebd5e7bdc84975186073891702=1447405635; Hm_lpvt_ccc93bebd5e7bdc84975186073891702=1447405635; bdshare_firstime=1447405634805" -H "Accept-Encoding: gzip, deflate, sdch" -H "Accept-Language: zh-CN,zh;q=0.8" -H "User-Agent: Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/46.0.2490.86 Safari/537.36" -H "Accept: application/json, text/javascript, */*; q=0.01" -H "Referer: http://www.131458.com/" -H "X-Requested-With: XMLHttpRequest" -H "Connection: keep-alive" --compressed
一次不好完成的curl.
截图:
escape($tb_nick_name));$url = 'http://www.131458.com/handler/load.aspx/Load';// 初始化$curl = curl_init($url);$header = array();$header[] = 'Content-Type: application/json; charset=UTF-8';$header[] = 'User-Agent: Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36';curl_setopt($curl, CURLOPT_HTTPHEADER, $header);curl_setopt($curl, CURLOPT_HEADER, 0);curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);curl_setopt($curl, CURLOPT_POST, 1);curl_setopt($curl, CURLOPT_POSTFIELDS, json_encode($post));curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_file);curl_setopt($curl, CURLOPT_FOLLOWLOCATION, 1);$response = curl_exec($curl);curl_close($curl);$d = json_decode($response)->d;$_token = md5($d . 'vvl81');$url = 'http://www.131458.com/handler/TaobaoInfo.ashx?nickCode=' . escape($tb_nick_name) . '&token=' . $_token . '_' . $d . '&_=' . time() . rand(100, 999);$curl = curl_init($url);$header = array();$header[] = 'Content-Type: application/json; charset=UTF-8';$header[] = 'User-Agent: Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36';curl_setopt($curl, CURLOPT_HTTPHEADER, $header);curl_setopt($curl, CURLOPT_HEADER, 0);curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);curl_setopt($curl, CURLOPT_COOKIEFILE, $cookie_file);$contents = curl_exec($curl);curl_close($curl);/* * $preg = "/]*?>.*?<\/script>/si"; * $newstr = preg_replace($preg,"",$contents); */echo htmlspecialchars($contents);function escape($string){ $n = $bn = $tn = 0; $output = ''; $special = "-_.+@/*0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"; while ($n < strlen($string)) { $ascii = ord($string[$n]); if ($ascii == 9 || $ascii == 10 || (32 <= $ascii && $ascii <= 126)) { $tn = 1; $n ++; } elseif (194 <= $ascii && $ascii <= 223) { $tn = 2; $n += 2; } elseif (224 <= $ascii && $ascii <= 239) { $tn = 3; $n += 3; } elseif (240 <= $ascii && $ascii <= 247) { $tn = 4; $n += 4; } elseif (248 <= $ascii && $ascii <= 251) { $tn = 5; $n += 5; } elseif ($ascii == 252 || $ascii == 253) { $tn = 6; $n += 6; } else { $n ++; } $singleStr = substr($string, $bn, $tn); $charVal = bin2hex(iconv('utf-8', 'ucs-2', $singleStr)); if (base_convert($charVal, 16, 10) > 0xff) { if (! preg_match("/win/i", PHP_OS)) $charVal = substr($charVal, 2, 2) . substr($charVal, 0, 2); $output .= '%u' . $charVal; } else { if (false !== strpos($special, $singleStr)) $output .= $singleStr; else $output .= "%" . dechex(ord($string[$bn])); } $bn = $n; } return $output;}
一次不好完成的curl.
截图:
escape($tb_nick_name));$url = 'http://www.131458.com/handler/load.aspx/Load';// 初始化$curl = curl_init($url);$header = array();$header[] = 'Content-Type: application/json; charset=UTF-8';$header[] = 'User-Agent: Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36';curl_setopt($curl, CURLOPT_HTTPHEADER, $header);curl_setopt($curl, CURLOPT_HEADER, 0);curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);curl_setopt($curl, CURLOPT_POST, 1);curl_setopt($curl, CURLOPT_POSTFIELDS, json_encode($post));curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_file);curl_setopt($curl, CURLOPT_FOLLOWLOCATION, 1);$response = curl_exec($curl);curl_close($curl);$d = json_decode($response)->d;$_token = md5($d . 'vvl81');$url = 'http://www.131458.com/handler/TaobaoInfo.ashx?nickCode=' . escape($tb_nick_name) . '&token=' . $_token . '_' . $d . '&_=' . time() . rand(100, 999);$curl = curl_init($url);$header = array();$header[] = 'Content-Type: application/json; charset=UTF-8';$header[] = 'User-Agent: Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36';curl_setopt($curl, CURLOPT_HTTPHEADER, $header);curl_setopt($curl, CURLOPT_HEADER, 0);curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);curl_setopt($curl, CURLOPT_COOKIEFILE, $cookie_file);$contents = curl_exec($curl);curl_close($curl);/* * $preg = "/]*?>.*?<\/script>/si"; * $newstr = preg_replace($preg,"",$contents); */echo htmlspecialchars($contents);function escape($string){ $n = $bn = $tn = 0; $output = ''; $special = "-_.+@/*0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"; while ($n < strlen($string)) { $ascii = ord($string[$n]); if ($ascii == 9 || $ascii == 10 || (32 <= $ascii && $ascii <= 126)) { $tn = 1; $n ++; } elseif (194 <= $ascii && $ascii <= 223) { $tn = 2; $n += 2; } elseif (224 <= $ascii && $ascii <= 239) { $tn = 3; $n += 3; } elseif (240 <= $ascii && $ascii <= 247) { $tn = 4; $n += 4; } elseif (248 <= $ascii && $ascii <= 251) { $tn = 5; $n += 5; } elseif ($ascii == 252 || $ascii == 253) { $tn = 6; $n += 6; } else { $n ++; } $singleStr = substr($string, $bn, $tn); $charVal = bin2hex(iconv('utf-8', 'ucs-2', $singleStr)); if (base_convert($charVal, 16, 10) > 0xff) { if (! preg_match("/win/i", PHP_OS)) $charVal = substr($charVal, 2, 2) . substr($charVal, 0, 2); $output .= '%u' . $charVal; } else { if (false !== strpos($special, $singleStr)) $output .= $singleStr; else $output .= "%" . dechex(ord($string[$bn])); } $bn = $n; } return $output;}
非常感谢你。
我现在有一个问题，就是获取了d之后，会调用一个$.TO函数，返回的结果你是怎么分析出来，是一个md5(d."vvl81")的，我只看到了定义了C="vvl",然后他手动添加了"8"，最后一个"1"是怎么知道的。
主要是网站现在已经改了，在后面加个"1"再md5已经和网站的数据不一样了。
一次不好完成的curl.
截图:
escape($tb_nick_name));$url = 'http://www.131458.com/handler/load.aspx/Load';// 初始化$curl = curl_init($url);$header = array();$header[] = 'Content-Type: application/json; charset=UTF-8';$header[] = 'User-Agent: Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36';curl_setopt($curl, CURLOPT_HTTPHEADER, $header);curl_setopt($curl, CURLOPT_HEADER, 0);curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);curl_setopt($curl, CURLOPT_POST, 1);curl_setopt($curl, CURLOPT_POSTFIELDS, json_encode($post));curl_setopt($curl, CURLOPT_COOKIEJAR, $cookie_file);curl_setopt($curl, CURLOPT_FOLLOWLOCATION, 1);$response = curl_exec($curl);curl_close($curl);$d = json_decode($response)->d;$_token = md5($d . 'vvl81');$url = 'http://www.131458.com/handler/TaobaoInfo.ashx?nickCode=' . escape($tb_nick_name) . '&token=' . $_token . '_' . $d . '&_=' . time() . rand(100, 999);$curl = curl_init($url);$header = array();$header[] = 'Content-Type: application/json; charset=UTF-8';$header[] = 'User-Agent: Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/42.0.2311.90 Safari/537.36';curl_setopt($curl, CURLOPT_HTTPHEADER, $header);curl_setopt($curl, CURLOPT_HEADER, 0);curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);curl_setopt($curl, CURLOPT_COOKIEFILE, $cookie_file);$contents = curl_exec($curl);curl_close($curl);/* * $preg = "/]*?>.*?<\/script>/si"; * $newstr = preg_replace($preg,"",$contents); */echo htmlspecialchars($contents);function escape($string){ $n = $bn = $tn = 0; $output = ''; $special = "-_.+@/*0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"; while ($n < strlen($string)) { $ascii = ord($string[$n]); if ($ascii == 9 || $ascii == 10 || (32 <= $ascii && $ascii <= 126)) { $tn = 1; $n ++; } elseif (194 <= $ascii && $ascii <= 223) { $tn = 2; $n += 2; } elseif (224 <= $ascii && $ascii <= 239) { $tn = 3; $n += 3; } elseif (240 <= $ascii && $ascii <= 247) { $tn = 4; $n += 4; } elseif (248 <= $ascii && $ascii <= 251) { $tn = 5; $n += 5; } elseif ($ascii == 252 || $ascii == 253) { $tn = 6; $n += 6; } else { $n ++; } $singleStr = substr($string, $bn, $tn); $charVal = bin2hex(iconv('utf-8', 'ucs-2', $singleStr)); if (base_convert($charVal, 16, 10) > 0xff) { if (! preg_match("/win/i", PHP_OS)) $charVal = substr($charVal, 2, 2) . substr($charVal, 0, 2); $output .= '%u' . $charVal; } else { if (false !== strpos($special, $singleStr)) $output .= $singleStr; else $output .= "%" . dechex(ord($string[$bn])); } $bn = $n; } return $output;}
非常感谢你。
我现在有一个问题，就是获取了d之后，会调用一个$.TO函数，返回的结果你是怎么分析出来，是一个md5(d."vvl81")的，我只看到了定义了C="vvl",然后他手动添加了"8"，最后一个"1"是怎么知道的。
主要是网站现在已经改了，在后面加个"1"再md5已经和网站的数据不一样了。
你可以在console里alert($.To);
return e = 2147483648 & a, f = 2147483648 & b, c = 1073741824
你看下他引用的jquery文件,在最后加了个函数。
看到这几个数字就是MD5加密了,再把格式化下,可以看出加了个1了。
要是被改了估计被发现采集了吧
你看下这网站定义的歌函数,现在变成了
_token=$.To(data.d+c+ "822")+"_"+data.d
所以还是一样的,
md5($d . 'vvl8221');
这里的值每天都在变,你不要写固定了
_token=$.To(data.d+c+ "822")+"_"+data.d
谢谢大家，已经写好了。 特别感谢u012771039，现在结贴
