PHP编程：php实现爬取和分析知乎用户数据

/**
 * 通过用户名抓取个人中心页面并存储
 * 
 * @param $username str :用户名 flag
 * @return boolean   :成功与否标志
 */
public function spiderUser($username)
{
  $cookie = "xxxx" ;
  $url_info = 'http://www.zhihu.com/people/' . $username; //此处cui-xiao-zhuai代表用户ID,可以直接看url获取本人id
  $ch = curl_init($url_info); //初始化会话
  curl_setopt($ch,CURLOPT_HEADER,0);
  curl_setopt($ch,CURLOPT_COOKIE,$cookie); //设置哀求COOKIE
  curl_setopt($ch,CURLOPT_USERAGENT,$_SERVER['HTTP_USER_AGENT']);
  curl_setopt($ch,CURLOPT_RETURNTRANSFER,1); //将curl_exec()获取的信息以文件流的形式返回,而不是直接输出.
  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;
 }

// 获取用户头像
preg_match('/<img.+src="?([^s]+.(jpg|gif|bmp|bnp|png))"?.+>/i',$match_img);
$img_url = $match_img[1];
// 匹配用户名：
// <span class="name">崔小拽</span>
preg_match('/<span.+class="?name"?>([x{4e00}-x{9fa5}]+).+span>/u',$match_name);
$user_name = $match_name[1];
// 匹配用户简介
// class bio span 中文
preg_match('/<span.+class="?bio"?.+&;([x{4e00}-x{9fa5}]+).+span>/u',$match_title);
$user_title = $match_title[1];
// 匹配性别
//<input type="radio" name="gender" value="1" checked="checked" class="male"/> 男??
// gender value1 ;结束 中文
preg_match('/<input.+name="?gender"?.+value="?1"?.+([x{4e00}-x{9fa5}]+).+;/u',$match_sex);
$user_sex = $match_sex[1];
// 匹配地区
//<span class="location item" title="北京">
preg_match('/<span.+class="?location.+"?.+"([x{4e00}-x{9fa5}]+)">/u',$match_city);
$user_city = $match_city[1];
// 匹配工作
//<span class="employment item" title="人见人骂的公司">人见人骂的公司</span>
preg_match('/<span.+class="?employment.+"?.+"([x{4e00}-x{9fa5}]+)">/u',$match_employment);
$user_employ = $match_employment[1];
// 匹配职位
// <span class="position item" title="程序猿"><a href="/topic/19590046" title="程序猿" class="topic-link" data-token="19590046" data-topicid="13253">程序猿</a></span>
preg_match('/<span.+class="?position.+"?.+"([x{4e00}-x{9fa5}]+).+">/u',$match_position);
$user_position = $match_position[1];
// 匹配学历
// <span class="education item" title="研究僧">研究僧</span>
preg_match('/<span.+class="?education.+"?.+"([x{4e00}-x{9fa5}]+)">/u',$match_education);
$user_education = $match_education[1];
// 工作情况
// <span class="education-extra item" title='挨踢'>挨踢</span>
preg_match('/<span.+class="?education-extra.+"?.+>([x{4e00}-
x{9fa5}]+)</u',$match_education_extra);
$user_education_extra = $match_education_extra[1];
// 匹配关注话题数量
// class="zg-link-litblue"><strong>41 个话题</strong></a>
preg_match('/class="?zg-link-litblue"?><strong>(d+)s.+strong>/i',$match_topic);
$user_topic = $match_topic[1];
// 关注人数
// <span class="zg-gray-normal">关注了
preg_match_all('/<strong>(d+)<.+<label>/i',$match_care);
$user_care = $match_care[1][0];
$user_be_careed = $match_care[1][1];
// 历史浏览量
// <span class="zg-gray-normal">个人主页被 <strong>17</strong> 人浏览</span>
preg_match('/class="?zg-gray-normal"?.+>(d+)<.+span>/i',$match_browse);
$user_browse = $match_browse[1];

# 官方的最优批量插入
INSERT INTO yourtable VALUES (1,2),(5,5),...;

#!/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 &  

// 获取用户头像
preg_match('/<img.+src="?([^s]+.(jpg|gif|bmp|bnp|png))"?.+>/i',$match_browse);
$user_browse = $match_browse[1];