全国315个城市，用python爬取肯德基老爷爷的店面信息

我觉得我生活在这世上二十多年里，去过最多的餐厅就是肯德基小时候逢生日必去，现在长大了，肯德基成了我的日常零食下班后从门前路过饿了便会进去点分黄金鸡块或者小吃拼盘早上路过，会买杯咖啡。主要快捷美味且饱腹，而且到处都是总是会路过，现在只要一饿，心心念念便是肯德基的味道

环境介绍

python 3.6

pycharm

requests

csv

爬虫的一般思路

1、确定爬取的url路径，headers参数

2、发送请求 -- requests 模拟浏览器发送请求，获取响应数据

3、解析数据

4、保存数据

步骤

1、确定爬取的url路径，headers参数

先爬取北京的数据

base_url = 'http://www.kfc.com.cn/kfccda/ashx/getstorelist.ashx?op=keyword'
headers = {'user-agent': 'mozilla/5.0 (windows nt 6.1; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/79.0.3945.117 safari/537.36'}
data = {
    'cname': '',
    'pid': '',
    'keyword': '北京',
    'pageindex': '1',
    'pagesize': '10',
}

2、发送请求 -- requests 模拟浏览器发送请求，获取响应数据

response = requests.post(url=base_url, headers=headers, data=data)
json_data = response.json()
# pprint.pprint(json_data)

3、解析数据

data_list = json_data['table1']
# pprint.pprint(data_list)
# 构建循环，解析数据字段
for ls in data_list:
    storename = ls['storename'] + '餐厅'  # 餐厅名称
    cityname = ls['cityname']  # 餐厅城市
    addressdetail = ls['addressdetail']  # 餐厅地址
    pro = ls['pro']  # 餐厅详情
    # print(storename, cityname, addressdetail, pro)

4、保存数据

 
 print('正在爬取：', storename)
    with open('data.csv', 'a', newline='') as csvfile:  # newline=''  指定一行一行写入
        csvwriter = csv.writer(csvfile, delimiter=',')  # delimiter=','  csv数据的分隔符
        csvwriter.writerow([storename, cityname, addressdetail, pro])  # 序列化数据，写入csv

5、全国315个城市的数据

获取拉勾网315个城市的数据

# coding:utf-8
import requests
import csv
import time
import random

ip = [{'http': '1.199.31.213:9999'}, {'http': '182.46.197.33:9999'}, {'http': '58.18.133.101:56210'},
      {'http': '175.44.108.123:9999'}, {'http': '123.52.97.90:9999'}, {'http': '182.92.233.137:8118'},
      {'http': '223.242.225.42:9999'}, {'http': '113.194.28.84:9999'}, {'http': '113.194.30.115:9999'},
      {'http': '113.195.19.41:9999'}, {'http': '144.123.69.123:9999'}, {'http': '27.192.168.202:9000'},
      {'http': '163.204.244.179:9999'}, {'http': '112.84.53.197:9999'}, {'http': '117.69.13.69:9999'},
      {'http': '1.197.203.214:9999'}, {'http': '125.108.111.22:9000'}, {'http': '171.35.169.69:9999'},
      {'http': '171.15.173.234:9999'}, {'http': '171.13.103.52:9999'}, {'http': '183.166.97.201:9999'},
      {'http': '60.2.44.182:44990'}, {'http': '58.253.158.21:9999'}, {'http': '47.94.89.87:3128'},
      {'http': '60.13.42.235:9999'}, {'http': '60.216.101.46:32868'}, {'http': '117.90.137.91:9000'},
      {'http': '123.169.164.163:9999'}, {'http': '123.169.162.230:9999'}, {'http': '125.108.119.189:9000'},
      {'http': '163.204.246.68:9999'}, {'http': '223.100.166.3:36945'}, {'http': '113.195.18.134:9999'},
      {'http': '163.204.245.50:9999'}, {'http': '125.108.79.50:9000'}, {'http': '163.125.220.205:8118'},
      {'http': '1.198.73.246:9999'}, {'http': '175.44.109.51:9999'}, {'http': '121.232.194.47:9000'},
      {'http': '113.194.30.27:9999'}, {'http': '129.28.183.30:8118'}, {'http': '123.169.165.73:9999'},
      {'http': '120.83.99.190:9999'}, {'http': '175.42.128.48:9999'}, {'http': '123.101.212.223:9999'},
      {'http': '60.190.250.120:8080'}, {'http': '125.94.44.129:1080'}, {'http': '118.112.195.91:9999'},
      {'http': '110.243.5.163:9999'}, {'http': '118.89.91.108:8888'}, {'http': '125.122.199.13:9000'},
      {'http': '171.11.28.248:9999'}, {'http': '211.152.33.24:39406'}, {'http': '59.62.35.130:9000'},
      {'http': '123.163.96.124:9999'}]


def get_page(keyword):
    global base_url
    base_url = 'http://www.kfc.com.cn/kfccda/ashx/getstorelist.ashx?op=keyword'
    global headers
    headers = {
        'user-agent': 'mozilla/5.0 (windows nt 6.1; win64; x64) applewebkit/537.36 (khtml, like gecko) chrome/79.0.3945.117 safari/537.36'}
    data = {
        'cname': '',
        'pid': '',
        'keyword': keyword,
        'pageindex': '1',
        'pagesize': '10',
    }
    try:
        response = requests.post(url=base_url, headers=headers, data=data)
        json_data = response.json()
        page = json_data['table'][0]['rowcount']

        if page % 10 > 0:
            page_num = page // 10 + 1
        else:
            page_num = page // 10

        return page_num
    except exception as e:
        print(e)




def send_request(keyword):
    page_num = get_page(keyword)

    try:
        for page in range(1, page_num + 1):
            print('============正在获取第{}页信息=========='.format(page))
            data = {
                'cname': '',
                'pid': '',
                'keyword': keyword,
                'pageindex': str(page),
                'pagesize': '10',
            }

            response = requests.post(url=base_url, headers=headers, data=data, proxies=random.choice(ip),timeout=3)

            json_data = response.json()
            # pprint.pprint(json_data)
            time.sleep(0.4)

            # 3、解析数据
            data_list = json_data['table1']
            # pprint.pprint(data_list)

            # 构建循环，解析数据字段
            for ls in data_list:
                storename = ls['storename'] + '餐厅'  # 餐厅名称
                cityname = ls['cityname']  # 餐厅城市
                addressdetail = ls['addressdetail']  # 餐厅地址
                pro = ls['pro']  # 餐厅详情
                # print(storename, cityname, addressdetail, pro)

                # 4、保存数据
                print('正在爬取：', storename)
                with open('data5.csv', 'a', newline='') as csvfile:  # newline=''  指定一行一行写入
                    csvwriter = csv.writer(csvfile, delimiter=',')  # delimiter=','  csv数据的分隔符
                    csvwriter.writerow([storename, cityname, addressdetail, pro])  # 序列化数据，写入csv
            time.sleep(0.2)
    except exception as e:
        print(e)


if __name__ == '__main__':
    # https://www.lagou.com/lbs/getallcitysearchlabels.json
    all_cities = ['安阳', '安庆', '鞍山', '澳门特别行政区', '安顺', '阿勒泰', '安康', '阿克苏', '阿坝藏族羌族自治州', '阿拉善盟', '北京', '保定', '蚌埠', '滨州',
                  '包头', '宝鸡', '北海', '亳州', '百色', '毕节', '巴中', '本溪', '巴音郭楞', '巴彦淖尔', '博尔塔拉', '保山', '白城', '白山', '成都', '长沙',
                  '重庆', '长春', '常州', '沧州', '赤峰', '郴州', '潮州', '常德', '朝阳', '池州', '滁州', '承德', '昌吉', '楚雄', '崇左', '东莞', '大连',
                  '德州', '德阳', '大庆', '东营', '大同', '达州', '大理', '德宏', '丹东', '定西', '儋州', '迪庆', '鄂州', '恩施', '鄂尔多斯', '佛山',
                  '福州', '阜阳', '抚州', '抚顺', '阜新', '防城港', '广州', '贵阳', '桂林', '赣州', '广元', '贵港', '广安', '固原', '甘孜藏族自治州', '杭州',
                  '合肥', '惠州', '哈尔滨', '海口', '呼和浩特', '邯郸', '衡阳', '湖州', '淮安', '海外', '菏泽', '衡水', '河源', '怀化', '黄冈', '黄石',
                  '黄山', '淮北', '淮南', '葫芦岛', '呼伦贝尔', '汉中', '红河', '贺州', '河池', '鹤壁', '鹤岗', '海东', '哈密', '济南', '金华', '嘉兴',
                  '济宁', '江门', '晋中', '吉林', '九江', '揭阳', '焦作', '荆州', '锦州', '荆门', '吉安', '景德镇', '晋城', '佳木斯', '酒泉', '济源',
                  '昆明', '开封', '克拉玛依', '喀什', '兰州', '临沂', '廊坊', '洛阳', '柳州', '六安', '聊城', '连云港', '吕梁', '泸州', '拉萨', '丽水',
                  '乐山', '龙岩', '临汾', '漯河', '六盘水', '凉山彝族自治州', '丽江', '娄底', '莱芜', '辽源', '陇南', '临夏', '来宾', '绵阳', '茂名', '马鞍山',
                  '梅州', '牡丹江', '眉山', '南京', '宁波', '南昌', '南宁', '南通', '南阳', '南充', '宁德', '南平', '内江', '莆田', '濮阳', '萍乡',
                  '平顶山', '盘锦', '攀枝花', '平凉', '普洱', '青岛', '泉州', '清远', '秦皇岛', '曲靖', '衢州', '齐齐哈尔', '黔西南', '黔南', '钦州', '黔东南',
                  '庆阳', '七台河', '日照', '深圳', '上海', '苏州', '沈阳', '石家庄', '绍兴', '汕头', '宿迁', '商丘', '三亚', '上饶', '宿州', '邵阳',
                  '十堰', '遂宁', '韶关', '三门峡', '汕尾', '随州', '三沙', '三明', '绥化', '石嘴山', '四平', '朔州', '商洛', '*', '天津', '太原',
                  '唐山', '台州', '泰安', '泰州', '天水', '通辽', '铜陵', '*', '铜仁', '铜川', '铁岭', '塔城', '天门', '通化', '武汉', '无锡', '温州',
                  '潍坊', '乌鲁木齐', '芜湖', '威海', '梧州', '渭南', '吴忠', '乌兰察布', '文山', '乌海', '西安', '厦门', '徐州', '新乡', '西宁', '咸阳',
                  '许昌', '邢台', '孝感', '襄阳', '香港特别行政区', '湘潭', '信阳', '忻州', '咸宁', '宣城', '西双版纳', '湘西土家族苗族自治州', '新余', '兴安盟',
                  '烟台', '扬州', '银川', '盐城', '宜春', '岳阳', '宜昌', '阳江', '玉溪', '玉林', '益阳', '运城', '宜宾', '榆林', '云浮', '营口', '永州',
                  '延安', '鹰潭', '伊犁', '延边', '阳泉', '雅安', '郑州', '珠海', '中山', '株洲', '淄博', '遵义', '湛江', '肇庆', '镇江', '张家口', '周口',
                  '驻马店', '漳州', '枣庄', '长治', '昭通', '舟山', '资阳', '张掖', '自贡', '中卫', '张家界']
    for city in all_cities:
        send_request(city)