centos7+TP5.1+selenium+chrome抓取搜狗微信推文_thinkphp 使用 selenium-优快云博客

本文介绍如何在CentOS环境下使用TP5.1框架、Selenium和Chrome进行搜狗微信推文的自动化抓取。从Composer依赖包的引入、谷歌浏览器及chromedriver的安装，到具体的PHP代码实现，详细展示了整个抓取流程。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

centos7+TP5.1+selenium+chrome抓取搜狗微信推文

一、Composer 引入

"require": {
    "php-webdriver/webdriver": "1.8.0",
    "jaeger/querylist": "^4.1"
}

二、安装谷歌浏览器yum install google-chrome

三、安装chromedriver
所有版本的下载地址：https://sites.google.com/a/chromium.org/chromedriver/downloads

wget https://chromedriver.storage.googleapis.com/2.39/chromedriver_linux64.zip

unzip chromedriver_linux64.zip

四、代码操作

<?php

namespace app\index\controller;


use Facebook\WebDriver\Remote\DesiredCapabilities;
use Facebook\WebDriver\Remote\RemoteWebDriver;
use Facebook\WebDriver\WebDriverBy;
use QL\QueryList;


class Test{
    protected $host ;
    protected  $driver  ;
    public function __construct() {
        $this->host  =  'http://localhost:9515' ;
        $res = $this->query_process('chromedriver.exe');

        if(!$res){
            //启动chromedriver.exe
            print_r("启动chromedriver.exe");
            $out1 = "";
            $a=exec  ("C:\Users\Dongmei\Desktop\selenium\chromedriver.exe",$out1);
            print_r($out1);

            echo '<br/>';

            print_r($a);
        }

        $this->driver =  RemoteWebDriver::create( $this->host, DesiredCapabilities:: chrome());
    }

 public function index() {

      $this->driver->get("https://weixin.sogou.com/");
     $element =  $this->driver->findElement(
         WebDriverBy::cssSelector('.query')
     );
     $element->clear(); //清空
     $element->sendKeys("一门式政务");
     //点击搜索
      $this->driver->findElement(WebDriverBy::cssSelector('.swz'))->click();
      sleep(1);
     $html =  $this->driver->getPageSource();

     $html = str_replace("<!--headTrap<body></body><head></head><html></html>-->", "", $html);  //去除微信干扰元素!!!否则乱码
     $rules=[
         'html'=>array('.txt-box', 'html'),
     ];
     $data = QueryList::html($html)->rules($rules)->query()->getData();

     $res= $data->all();

     $doc=\phpQuery::newDocumentHTML($res['html']);
     $as = pq($doc)->find('a');
     $hrefs=[];
     foreach ($as as $a) {
         $href= pq($a)->attr('href');
         $host = parse_url($href);
         if(!isset($host['host'])){
             $hrefs[] = "https://weixin.sogou.com".$href;
         }
     }
     foreach ($hrefs as $v) {
         $this->getHtmlByUrl($v);
         die;
     }

     $this->driver->close();
    
 }

  protected function getHtmlByUrl($url){
      $this->driver->get($url);
      echo '<span style="color:#ad3c27">延迟2S...</span>';
      sleep('2');
      echo '<span style="color:#3bad43">..开始抓取————</span>';
      $html =  $this->driver->getPageSource();
      $html = str_replace("<!--headTrap<body></body><head></head><html></html>-->", "", $html);  //去除微信干扰元素!!!否则乱码
      $rules = array(   //设置QueryList的解析规则
          'content' => array('#js_content', 'html'),  //文章内容
          'title' => array('#activity-name', 'text'),  //文章标题
          'author'=> array('.rich_media_meta_text:eq(1)','text'),  //作者
          'account_name' => array('#js_profile_qrcode .profile_nickname','text'),  //公众号
          'account_en_name' => array('#js_profile_qrcode .profile_meta:eq(0) .profile_meta_value','text'),  //公众号英文标识
      );
     $data = QueryList::html($html)->rules($rules)->query()->getData();
     return $data;
  }