php 抓取自如友家首页的区域和地铁数据

步骤

1. 使用composer安装 php抓取扩展包

   composer require jaeger/querylist

2. 分析自如首页html结构
   

   • 经过分析发现区域和地铁数据在类名.clearfix.filterList下面，所以代码可以这么些：

<?php
require_once 'vendor/autoload.php';
$url = 'http://www.ziroom.com/z/nl/z3.html';
$ql = \QL\QueryList::get($url);
//地区
$data = $ql->find('.clearfix.filterList:eq(0)>li .tag a')->texts();
$area_son = [];
$area_parent = [];
$area_p_key = '';
foreach ($data as $k => $v) {
    if ($v == '全部'){
        $area_parent[] = $data[$k-1];
    }
}
foreach ($data as $v) {
    if (in_array($v,$area_parent)){
        $area_p_key = $v;
    }
    if ($v != '全部' && !in_array($v,$area_parent)){
        $area_son[$area_p_key][] = $v;
    }
}
//地铁
$data = $ql->find('.clearfix.filterList:eq(1)>li .tag a')->texts();
$subway_son = [];
$subway_parent = [];
$subway_p_key = '';
foreach ($data as $k => $v) {
    if ($v == '全部'){
        $subway_parent[] = $data[$k-1];
    }
}
foreach ($data as $v) {
    if (in_array($v,$subway_parent)){
        $subway_p_key = $v;
    }
    if ($v != '全部' && !in_array($v,$subway_parent)){
        $subway_son[$subway_p_key][] = $v;
    }
}
var_dump($area_parent);
var_dump($subway_parent);
//        p($area_son);
//        p($subway_son);

• 得到如下结果

array (size=13)
  0 => string '东城' (length=6)
  1 => string '西城' (length=6)
  2 => string '朝阳' (length=6)
  3 => string '海淀' (length=6)
  4 => string '丰台' (length=6)
  5 => string '石景山' (length=9)
  6 => string '通州' (length=6)
  7 => string '昌平' (length=6)
  8 => string '大兴' (length=6)
  9 => string '顺义' (length=6)
  10 => string '房山' (length=6)
  11 => string '门头沟' (length=9)
  12 => string '亦庄开发区' (length=15)
H:\wamp\www\projects\test\test.php:51:
array (size=21)
  0 => string '1号线' (length=7)
  1 => string '2号线' (length=7)
  2 => string '4号线' (length=7)
  3 => string '5号线' (length=7)
  4 => string '6号线' (length=7)
  5 => string '7号线' (length=7)
  6 => string '8号线' (length=7)
  7 => string '9号线' (length=7)
  8 => string '10号线' (length=8)
  9 => string '13号线' (length=8)
  10 => string '14号线' (length=8)
  11 => string '15号线' (length=8)
  12 => string '西郊线' (length=9)
  13 => string 'S1号线' (length=8)
  14 => string '燕房线' (length=9)
  15 => string '16号线' (length=8)
  16 => string '八通线' (length=9)
  17 => string '昌平线' (length=9)
  18 => string '亦庄线' (length=9)
  19 => string '房山线' (length=9)
  20 => string '机场线' (length=9)
Array
(
    [东城] => Array
        (
            [0] => 安定门
            [1] => 安贞
            [2] => 崇文门
            [3] => 朝阳门内
            [4] => 东花市
            [5] => 地安门
            [6] => 灯市口
            [7] => 东四
            [8] => 东单
            [9] => 东直门
            [10] => 广渠门
            [11] => 和平里
            [12] => 交道口
            [13] => 金宝街
            [14] => 建国门内
            [15] => 天坛
            [16] => 西罗园
            [17] => 永定门
            [18] => 左安门
            [19] => 北新桥
            [20] => 雍和宫
        )

    [西城] => Array
        (
            [0] => 白纸坊
            [1] => 长椿街
            [2] => 车公庄
            [3] => 德胜门
            [4] => 阜成门
            [5] => 广安门
            [6] => 官园
[15号线] => Array
        (
            [0] => 俸伯
            [1] => 顺义
            [2] => 石门
            [3] => 南法信
            [4] => 后沙峪
            [5] => 花梨坎
            [6] => 国展
            [7] => 孙河
            [8] => 马泉营
            [9] => 崔各庄
            [10] => 望京东
            [11] => 望京
            [12] => 望京西
            [13] => 关庄
            [14] => 大屯路东
            [15] => 安立路
            [16] => 奥林匹克公园
            [17] => 北沙滩
            [18] => 六道口
            [19] => 清华东路西口
        )

    [西郊线] => Array
        (
            [0] => 巴沟
            [1] => 万安
            [2] => 茶棚
            [3] => 颐和园西门
        )

    [S1号线] => Array
        (
            [0] => 苹果园