本文章來給各位同學介紹一下關于Php CURL模擬登陸論壇并采集數據實例,如果你對利用curl模擬登錄功能有興趣可進入參考。
libcurl同時也支持HTTPS認證、HTTP POST、HTTP PUT、 FTP 上傳(這個也能通過PHP的FTP擴展完成)、HTTP 基于表單的上傳、代理、cookies和用戶名+密碼的認證。
- <?php
- $discuz_url = 'http://www.49028c.com/';//論壇地址
- $login_url = $discuz_url .'login.php?action=login';//登錄頁地址
- $post_fields = array();
- //以下兩項不需要修改
- $post_fields['loginfield'] = 'username';
- $post_fields['loginsubmit'] = 'true';
- //用戶名和密碼,必須填寫
- $post_fields['username'] = 'tianxin';
- $post_fields['password'] = '111111';
- //安全提問
- $post_fields['questionid'] = 0;
- $post_fields['answer'] = '';
- //@todo驗證碼
- $post_fields['seccodeverify'] = '';
- //獲取表單FORMHASH
- $ch = curl_init($login_url);
- curl_setopt($ch, CURLOPT_HEADER, 0);
- curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
- $contents = curl_exec($ch);
- curl_close($ch);
- preg_match('/<input/s*type="hidden"/s*name="formhash"/s*value="(.*?)"/s*//>/i', $contents, $matches);
- if(!emptyempty($matches)) {
- $formhash = $matches[1];
- } else {
- die('Not found the forumhash.');
- }
- //POST數據,獲取COOKIE,cookie文件放在網站的temp目錄下
- $cookie_file = tempnam('./temp','cookie');
- $ch = curl_init($login_url);
- curl_setopt($ch, CURLOPT_HEADER, 0);
- curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
- curl_setopt($ch, CURLOPT_POST, 1);
- curl_setopt($ch, CURLOPT_POSTFIELDS, $post_fields);
- curl_setopt($ch, CURLOPT_COOKIEJAR, $cookie_file);
- curl_exec($ch);
- curl_close($ch);
- //取到了關鍵的cookie文件就可以帶著cookie文件去模擬發帖,fid為論壇的欄目ID
- $send_url = $discuz_url."post.php?action=newthread&fid=2";
- $ch = curl_init($send_url);
- curl_setopt($ch, CURLOPT_HEADER, 0);
- curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
- curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie_file);
- $contents = curl_exec($ch);
- curl_close($ch);
- //這里的hash碼和登陸窗口的hash碼的正則不太一樣,這里的hidden多了一個id屬性
- preg_match('/<input/s*type="hidden"/s*name="formhash"/s*id="formhash"/s*value="(.*?)"/s*//>/i', $contents, $matches);
- if(!emptyempty($matches)) {
- $formhash = $matches[1];
- } else {
- die('Not found the forumhash.');
- }
- $post_data = array();
- //帖子標題
- $post_data['subject'] = 'test2';
- //帖子內容
- $post_data['message'] = 'test2';
- $post_data['topicsubmit'] = "yes";
- $post_data['extra'] = '';
- //帖子標簽
- $post_data['tags'] = 'test';
- //帖子的hash碼,這個非常關鍵!假如缺少這個hash碼,discuz會警告你來路的頁面不正確
- $post_data['formhash']=$formhash;
- $ch = curl_init($send_url);
- curl_setopt($ch, CURLOPT_REFERER, $send_url); //偽裝REFERER
- curl_setopt($ch, CURLOPT_HEADER, 0);
- curl_setopt($ch, CURLOPT_RETURNTRANSFER, 0);
- curl_setopt($ch, CURLOPT_COOKIEFILE, $cookie_file);
- curl_setopt($ch, CURLOPT_POST, 1);
- curl_setopt($ch, CURLOPT_POSTFIELDS, $post_data);
- $contents = curl_exec($ch);
- curl_close($ch);
- //清理cookie文件
- unlink($cookie_file);
- ?>
以上所述就是本文的全部內容了,希望大家能夠喜歡。
新聞熱點
疑難解答