爬虫实战（安居客二手房和租房信息爬取）

不说废话，直接上代码！

import requests
import csv
import parsel  # 解析数据
# 安居客二手房信息
# 网页源代码解析
# json数据解析
for page in range(1,51):
    print(f"正在爬取第-----{page}------页数据信息！")
    url=f'https://anjuke.com/sale/p{page}/'
    header = {
        'cookie': 'sessid=E8557945-A48A-DECA-D8A1-102112E95525; aQQ_ajkguid=6005B887-989E-9E1E-EB74-C01BBCE2362D; twe=2; ajk-appVersion=; fzq_h=3cdd8dc4ff49c08b22268609df890299_1670208027764_406af778a32a4516a91f70fef3d1409d_986905475; id58=CrIclWONWihf8mLgZefRAg==; ctid=231; lps=https%3A%2F%2Fyx.zu.anjuke.com%2F%7Chttps%3A%2F%2Fyuxi.anjuke.com%2F; cmctid=2040; wmda_uuid=48c23ab83834bd513b73a85f47e86a23; wmda_new_uuid=1; wmda_session_id_6289197098934=1670208078386-18df4190-2941-5746; wmda_visited_projects=%3B6289197098934; obtain_by=1; xxzl_cid=df78ca61c6fa40b680bd980d2ff3bd01; xxzl_deviceid=out+sEolHB8HXmPxXFzGJuGNceTZiUsWOVAr25QoCxZqXuiGQDtGyv3aQwmOHRGV',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36',
        'referer': 'https://yx.zu.anjuke.com/fangyuan/'
    }

    response = requests.get(url=url,headers=header)
    html_data = response.text
    # print(response)
    selectors = parsel.Selector(html_data)
    lis = selectors.css('.property-content')
    for li in lis:
        标题 = li.css('.property-content-title-name::text').get()
        户型 = li.css('.property-content-info:nth-child(1) .property-content-info-text:nth-child(1) span::text').getall()
        面积 = li.css('.property-content-info:nth-child(1) .property-content-info-text:nth-child(2)::text').getall()
        朝向 = li.css('.property-content-info:nth-child(1) .property-content-info-text:nth-child(3)::text').get()
        楼层 = li.css('.property-content-info:nth-child(1) .property-content-info-text:nth-child(4)::text').get()
        建造时间 = li.css('.property-content-info:nth-child(1) .property-content-info-text:nth-child(5)::text').get()
        小区名称 = li.css('.property-content-info:nth-child(2) .property-content-info-comm-name::text').getall()
        小区地址 = li.css('.property-content-info:nth-child(2) .property-content-info-comm-address span::text').getall()
        总价 = li.css('.property-price .property-price-total .property-price-total-num::text').getall()
        单价 = li.css('.property-price .property-price-average::text').getall()
        print(标题)
        with open('./txt/玉溪安居客二手房.csv',mode='a+',encoding='utf-8-sig',newline='') as f:
            csv_text = csv.writer(f)
            csv_text.writerow((标题,户型,面积,朝向,楼层,建造时间,小区名称,小区地址,总价,单价))
print("爬取完成！")

这是爬取下来的格式，当然里面的标点符号我替换掉了

 

 租房信息：

import requests
import csv
import parsel  # 解析数据
# 安居客租房信息
# 网页源代码解析
# json数据解析
for page in range(1,34):
    print(f"正在爬取第-----{page}------页数据信息！")
    url=f'https://yx.zu.anjuke.com/fangyuan/p{page}/'
    header = {
        'cookie': 'sessid=E8557945-A48A-DECA-D8A1-102112E95525; aQQ_ajkguid=6005B887-989E-9E1E-EB74-C01BBCE2362D; twe=2; ajk-appVersion=; fzq_h=3cdd8dc4ff49c08b22268609df890299_1670208027764_406af778a32a4516a91f70fef3d1409d_986905475; id58=CrIclWONWihf8mLgZefRAg==; ctid=231; lps=https%3A%2F%2Fyx.zu.anjuke.com%2F%7Chttps%3A%2F%2Fyuxi.anjuke.com%2F; cmctid=2040; wmda_uuid=48c23ab83834bd513b73a85f47e86a23; wmda_new_uuid=1; wmda_session_id_6289197098934=1670208078386-18df4190-2941-5746; wmda_visited_projects=%3B6289197098934; obtain_by=1; xxzl_cid=df78ca61c6fa40b680bd980d2ff3bd01; xxzl_deviceid=out+sEolHB8HXmPxXFzGJuGNceTZiUsWOVAr25QoCxZqXuiGQDtGyv3aQwmOHRGV',
        'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.0.0 Safari/537.36',
        'referer': 'https://yx.zu.anjuke.com/fangyuan/'
    }
    response = requests.get(url=url,headers=header)
    html_data = response.text
        # print(response)
    selectors = parsel.Selector(html_data)
    lis = selectors.css('.zu-itemmod')
    for li in lis:
        标题 = li.css('.zu-info .strongbox::text').get()
        户型 = li.css('.zu-info .strongbox::text').getall()[1]+'室'+li.css('.strongbox::text').getall()[2]+'厅'
        面积 = li.css('.zu-info .strongbox::text').getall()[3]+'㎡'
        价格 = li.css('.zu-side .strongbox::text').getall()
        出租类型 = li.css('.zu-info .cls-1::text').getall()
        朝向 = li.css('.zu-info .cls-2::text').getall()
        电梯 = li.css('.zu-info .cls-3::text').getall()
        位置 = li.css('.zu-info .details-item::text').getall()[8]
        小区 = li.css('.zu-info a::text').getall()
        楼层 = li.css('.zu-info p::text').getall()[4]
        联系人 = li.css('.zu-info p::text').getall()[5]
        print(位置)
        with open('./txt/玉溪安居客租房.csv',mode='a+',encoding='utf-8-sig',newline='') as f:
            csv_text = csv.writer(f)
            csv_text.writerow((标题,户型,面积,价格,出租类型,朝向,电梯,位置,小区,楼层,联系人))
print("爬取完成！")

这是爬取后修改为.xlsx格式的

 

 懂得都懂。现在爬取数据，后续更新对于数据的处理的内容文章！