PHP學(xué)習(xí)
/**
 * 通過用戶名抓取個人中心頁面并存儲
 * 
 * @param $username str :用戶名 flag
 * @return boolean   :成功與否標(biāo)志
 */
public function spiderUser($username)
{
  $cookie = "xxxx" ;
  $url_info = 'http://www.zhihu.com/people/' . $username; //此處cui-xiao-zhuai代表用戶ID,可以直接看url獲取本人id
  $ch = curl_init($url_info); //初始化會話
  curl_setopt($ch, CURLOPT_HEADER, 0);
  curl_setopt($ch, CURLOPT_COOKIE, $cookie); //設(shè)置哀求COOKIE
  curl_setopt($ch, CURLOPT_USERAGENT, $_SERVER['HTTP_USER_AGENT']);
  curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1); //將curl_exec()獲取的信息以文件流的形式返回,而不是直接輸出.
  curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
  $result = curl_exec($ch);
   file_put_contents('/home/work/zxdata_ch/php/zhihu_spider/file/'.$username.'.html',$result);
   return true;
 }

PHP學(xué)習(xí)
// 獲取用戶頭像
preg_match('/<img.+src=\"?([^\s]+\.(jpg|gif|bmp|bnp|png))\"?.+>/i', $str, $match_img);
$img_url = $match_img[1];
// 匹配用戶名：
// <span class="name">崔小拽</span>
preg_match('/<span.+class=\"?name\"?>([\x{4e00}-\x{9fa5}]+).+span>/u', $str, $match_name);
$user_name = $match_name[1];
// 匹配用戶簡介
// class bio span 中文
preg_match('/<span.+class=\"?bio\"?.+\>([\x{4e00}-\x{9fa5}]+).+span>/u', $str, $match_title);
$user_title = $match_title[1];
// 匹配性別
//<input type="radio" name="gender" value="1" checked="checked" class="male"/> 男??
// gender value1 ;結(jié)束 中文
preg_match('/<input.+name=\"?gender\"?.+value=\"?1\"?.+([\x{4e00}-\x{9fa5}]+).+\;/u', $str, $match_sex);
$user_sex = $match_sex[1];
// 匹配地區(qū)
//<span class="location item" title="北京">
preg_match('/<span.+class=\"?location.+\"?.+\"([\x{4e00}-\x{9fa5}]+)\">/u', $str, $match_city);
$user_city = $match_city[1];
// 匹配工作
//<span class="employment item" title="人見人罵的公司">人見人罵的公司</span>
preg_match('/<span.+class=\"?employment.+\"?.+\"([\x{4e00}-\x{9fa5}]+)\">/u', $str, $match_employment);
$user_employ = $match_employment[1];
// 匹配職位
// <span class="position item" title="程序猿"><a href="/topic/19590046" title="程序猿" class="topic-link" data-token="19590046" data-topicid="13253">程序猿</a></span>
preg_match('/<span.+class=\"?position.+\"?.+\"([\x{4e00}-\x{9fa5}]+).+\">/u', $str, $match_position);
$user_position = $match_position[1];
// 匹配學(xué)歷
// <span class="education item" title="研究僧">研究僧</span>
preg_match('/<span.+class=\"?education.+\"?.+\"([\x{4e00}-\x{9fa5}]+)\">/u', $str, $match_education);
$user_education = $match_education[1];
// 工作情況
// <span class="education-extra item" title='挨踢'>挨踢</span>
preg_match('/<span.+class=\"?education-extra.+\"?.+>([\x{4e00}-
\x{9fa5}]+)</u', $str, $match_education_extra);
$user_education_extra = $match_education_extra[1];
// 匹配關(guān)注話題數(shù)量
// class="zg-link-litblue"><strong>41 個話題</strong></a>
preg_match('/class=\"?zg-link-litblue\"?><strong>(\d+)\s.+strong>/i', $str, $match_topic);
$user_topic = $match_topic[1];
// 關(guān)注人數(shù)
// <span class="zg-gray-normal">關(guān)注了
preg_match_all('/<strong>(\d+)<.+<label>/i', $str, $match_care);
$user_care = $match_care[1][0];
$user_be_careed = $match_care[1][1];
// 歷史瀏覽量
// <span class="zg-gray-normal">個人主頁被 <strong>17</strong> 人瀏覽</span>
preg_match('/class=\"?zg-gray-normal\"?.+>(\d+)<.+span>/i', $str, $match_browse);
$user_browse = $match_browse[1];

PHP學(xué)習(xí)
# 官方的最優(yōu)批量插入
INSERT INTO yourtable VALUES (1,2), (5,5), ...;

PHP學(xué)習(xí)
#!/bin/bash
# 干掉
ps aux |grep spider |awk '{print $2}'|xargs kill -9
sleep 5s
# 重新跑
nohup /home/cuixiaohuan/lamp/php5/bin/php /home/cuixiaohuan/php/zhihu_spider/spider_new.php &  

PHP學(xué)習(xí)
// 獲取用戶頭像
preg_match('/<img.+src=\"?([^\s]+\.(jpg|gif|bmp|bnp|png))\"?.+>/i', $str, $match_img);
$img_url = $match_img[1];
// 匹配用戶名：
// <span class="name">崔小拽</span>
preg_match('/<span.+class=\"?name\"?>([\x{4e00}-\x{9fa5}]+).+span>/u', $str, $match_name);
$user_name = $match_name[1];
// 匹配用戶簡介
// class bio span 中文
preg_match('/<span.+class=\"?bio\"?.+\>([\x{4e00}-\x{9fa5}]+).+span>/u', $str, $match_title);
$user_title = $match_title[1];
// 匹配性別
//<input type="radio" name="gender" value="1" checked="checked" class="male"/> 男??
// gender value1 ;結(jié)束 中文
preg_match('/<input.+name=\"?gender\"?.+value=\"?1\"?.+([\x{4e00}-\x{9fa5}]+).+\;/u', $str, $match_sex);
$user_sex = $match_sex[1];
// 匹配地區(qū)
//<span class="location item" title="北京">
preg_match('/<span.+class=\"?location.+\"?.+\"([\x{4e00}-\x{9fa5}]+)\">/u', $str, $match_city);
$user_city = $match_city[1];
// 匹配工作
//<span class="employment item" title="人見人罵的公司">人見人罵的公司</span>
preg_match('/<span.+class=\"?employment.+\"?.+\"([\x{4e00}-\x{9fa5}]+)\">/u', $str, $match_employment);
$user_employ = $match_employment[1];
// 匹配職位
// <span class="position item" title="程序猿"><a href="/topic/19590046" title="程序猿" class="topic-link" data-token="19590046" data-topicid="13253">程序猿</a></span>
preg_match('/<span.+class=\"?position.+\"?.+\"([\x{4e00}-\x{9fa5}]+).+\">/u', $str, $match_position);
$user_position = $match_position[1];
// 匹配學(xué)歷
// <span class="education item" title="研究僧">研究僧</span>
preg_match('/<span.+class=\"?education.+\"?.+\"([\x{4e00}-\x{9fa5}]+)\">/u', $str, $match_education);
$user_education = $match_education[1];
// 工作情況
// <span class="education-extra item" title='挨踢'>挨踢</span>
preg_match('/<span.+class=\"?education-extra.+\"?.+>([\x{4e00}-
\x{9fa5}]+)</u', $str, $match_education_extra);
$user_education_extra = $match_education_extra[1];
// 匹配關(guān)注話題數(shù)量
// class="zg-link-litblue"><strong>41 個話題</strong></a>
preg_match('/class=\"?zg-link-litblue\"?><strong>(\d+)\s.+strong>/i', $str, $match_topic);
$user_topic = $match_topic[1];
// 關(guān)注人數(shù)
// <span class="zg-gray-normal">關(guān)注了
preg_match_all('/<strong>(\d+)<.+<label>/i', $str, $match_care);
$user_care = $match_care[1][0];
$user_be_careed = $match_care[1][1];
// 歷史瀏覽量
// <span class="zg-gray-normal">個人主頁被 <strong>17</strong> 人瀏覽</span>
preg_match('/class=\"?zg-gray-normal\"?.+>(\d+)<.+span>/i', $str, $match_browse);
$user_browse = $match_browse[1];