我如何从Mediwiki获取数据
|
嗨，我正在使用以下api从mediawiki获取数据。当我复制此URL并将其粘贴到浏览器中时，将出现xml响应。
http://en.wikipedia.org/w/api.php?action=query&prop=revisions&titles=API|Main_Page&rvprop=timestamp|user|comment|content
但是当我尝试使用curl时，会出现错误“脚本应使用带有联系信息的信息丰富的User-Agent字符串，否则它们可能被IP阻止，恕不另行通知。”
我为此使用以下代码。有人可以追踪我的错误吗？
$url=\'http://en.wikipedia.org/w/api.php?action=query&prop=revisions&titles=API|Main_Page&rvprop=timestamp|user|comment|content\';
$curl = curl_init();
curl_setopt($curl, CURLOPT_URL, $url);
curl_setopt($curl, CURLOPT_RETURNTRANSFER, 1);
//curl_setopt($curl, CURLOPT_TIMEOUT, 1);
$objResponse = curl_exec($curl);
curl_close($curl);
echo $objResponse;die;
没有找到相关结果
已邀请:
2 个回复
翰冒绢县
<?php function getwiki($url=\"\", $referer=\"\", $userAgent=\"\") { if($url==\"\"||$referer==\"\"||$userAgent==\"\") { return false;}; $headers[] = \'Accept: image/gif, image/x-bitmap, image/jpeg, image/pjpeg\'; $headers[] = \'Connection: Keep-Alive\'; $headers[] = \'Content-type: application/x-www-form-urlencoded;charset=UTF-8\'; $user_agent = $userAgent; $process = curl_init($url); curl_setopt($process, CURLOPT_HTTPHEADER, $headers); curl_setopt($process, CURLOPT_HEADER, 0); curl_setopt($process, CURLOPT_USERAGENT, $user_agent); curl_setopt($process, CURLOPT_REFERER, $referer); curl_setopt($process, CURLOPT_TIMEOUT, 30); curl_setopt($process, CURLOPT_RETURNTRANSFER, 1); curl_setopt($process, CURLOPT_FOLLOWLOCATION, 1); $return = curl_exec($process); curl_close($process); return $return; } //edited to include Adam Backstrom\'s sound advice echo getwiki(\'http://en.wikipedia.org/w/api.php?action=query&prop=revisions&titles=API|Main_Page&rvprop=timestamp|user|comment|content\', \'http://en.wikipedia.org/\', \'Mozilla/5.0 (compatible; YourCoolBot/1.0; +http://yoursite.com/botinfo)\'); ?>佩疵瓦