使用PHP抓取微博数据实现demo及原理解析

       'User-Agent: spider'

// 通过这段代码你可以直接获取到微博的(HTML)网页
    public function curlGetWbData()
    {
        // 设置脚本超时时间
        set_time_limit(60);
        // 拉取微博地址
        $getWbUrl = "https://weibo.com/p/1005056447467552/home?profile_ftype=1&is_all=1#_0";
        // 设置curl 请求头
        $header = [
            'User-Agent: spider'
        ];
        $ch = curl_init();                                              // 初始化curl
        curl_setopt($ch, CURLOPT_URL, $getWbUrl);
        curl_setopt($ch, CURLOPT_RETURNTRANSFER, 1);
        curl_setopt($ch, CURLOPT_SSL_VERIFYPEER, false);    // 禁止 cURL 验证对等证书
        curl_setopt($ch, CURLOPT_SSL_VERIFYHOST, false);
        curl_setopt($ch, CURLOPT_FOLLOWLOCATION, 1);
        curl_setopt($ch, CURLOPT_HTTPHEADER, $header);            // 设置请求头
        $wbContent = curl_exec($ch);
        curl_close($ch);
        // 到这里我们就拿到了微博的网页
        return $wbContent;
    }

div[class='WB_cardwrap WB_feed_type S_bg2 WB_feed_like ']

// 这个方法是
public static function actionAddWbData(string $wbContent, string $userID)
{
    $htmlDeal = new HtmlDomParser();    // 处理DOM的对象
    $htmlDeal->load($wbContent);        // 装载文本
    // 微博VIP和普通用户的class名不一致
    $wbHtml['normal'] = $htmlDeal->find("div[class='WB_cardwrap WB_feed_type S_bg2 WB_feed_like ']");
    $wbHtml['vip']    = $htmlDeal->find("div[class='WB_cardwrap WB_feed_type S_bg2 WB_feed_vipcover WB_feed_like ']");
    $wbNum = [];
    foreach ($wbHtml as $item => $key) {
        if (count($key) <= 0) {
            continue;
        }
        $wbNum[$userID][$item] = self::dealWbContent($key, $userID);
    }
    Yii::info("抓取微博日志记录" . '----' . json_encode($wbNum));
    return $wbNum;
}