开发Python网络爬虫应用，爬取链家新房楼盘信息保存到mongodb中，并分析相关数据

爬取代码

import requests
import time
from lxml import html
from pymongo import MongoClient
import random

BASEURL = 'https://cq.fang.lianjia.com/loupan/'

# 获取某市区域的所有链接
def get_areas(url):
    print('获取区县列表')
    # 设置请求头
    headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/65.0.3325.181 Safari/537.36'}
    # 获取请求页面数据
    res = requests.get(url, headers=headers)
    content = html.fromstring(res.text)
    # 获取区县名称文本
    areas = content.xpath('//div[@class="filter-by-area-container"]/ul[@class="district-wrapper"]/li/text()')
    # 区县太多，只设置主城九区
    areas = ['江北', '渝北', '渝中', '沙坪坝', '九龙坡', '南岸', '大渡口', '巴南', '北碚']
    # areas = ['大足', '武隆区', '石柱', '涪陵', '綦江','长寿', '江津', '合川', '南川', '璧山', '铜梁', '潼南', '万州', '梁平', '云阳', '黔江', '双桥 ', '永川', '丰都', '秀山土家族苗族自治县', '忠县', '巫山县', '荣昌区', '奉节县', '开州区', '垫江县', '酉阳土家族苗族自治县', '彭水苗族土家族自治县', '巫溪县', '城口县']
    print(areas)
    # 获取区县名称拼写
    areas_link = content.xpath('//div[@class="filter-by-area-container"]/ul[@class="district-wrapper"]/li/@data-district-spell')
    # 区县太多，只设置主城九区
    areas_link = ['jiangbei', 'yubei', 'yuzhong', 'shapingba', 'jiulongpo', 'nanan', 'dadukou', 'banan', 'beibei']
    # areas_link = ['dazu', 'wulongqu', 'shizhu', 'fuling', 'qijiang', 'changshou1', 'jiangjing', 'hechuang', 'nanchuang', 'bishan', 'tongliang', 'tongnan', 'wanzhou', 'liangping', 'yunyang', 'qianjiang', 'shuangqiao1', 'yongchuan', 'fengdu1', 'xiushantujiazumiaozuzizhixian', 'zhongxian', 'wushanxian1', 'rongchangqu', 'fengjiexian', 'kaizhouqu', 'dianjiangxian', 'youyangtujiazumiaozuzizhixian', 'pengshuimiaozutujiazuzizhixian', 'wuxixian', 'chengkouxian']
    # print(areas_link)
    if not areas:
        print("主站页面未获取成功，请手动查看页面是否需要人机验证！")
        return
    # 遍历获取所有区县的链接
    for i in range(0, len(areas)):
        area = areas[i]

        area_link = areas_link[i]
        # print(area_link)
        link = url+area_link
        print("当前区县:",area," ",link)
        get_pages(area, link)


#通过获取某一区域的页数，来拼接某一页的链接
def get_pages(area, area_link):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.5359.125 Safari/537.36'}
    res = requests.get(area_link, headers=headers)
    content = html.fromstring(res.text)
    #链家新房页面统计每个区域的楼盘个数
    try:
        count = int(content.xpath('//div[@class ="page-box"]/@data-total-count')[0])
    except:
        print(count)
    #转换成页面，获取每个页面的楼盘信息
    if count%10 :
        pages = count//10+1
    else:
        pages = count//10
    print("这个区域有" + str(pages) + "页")

    for page in range(1, pages+1):
        url = area_link+'/pg' + str(page)
        print("开始抓取第" + str(page) +"页的信息")
        get_house_info(area, url)


#获取某一区域某一页的详细房租信息
def get_house_info(area, url):
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/108.0.5359.125 Safari/537.36'}
    time.sleep(1+2*random.random()) # 间隔随机1-3秒避免访问太密集触发反扒机制
    try:
        # 获取页面信息
        print(url)
        res = requests.get(url, headers=headers)
        content = html.fromstring(res.text)
        data = []  # 构造一个列表存放当前页面所有楼盘详情
        for i in range(10): # 每页有10条楼盘信息
            try:
                # 获取楼盘详情：
                #获取编号
                project_id = content.xpath("//ul[@class='resblock-list-wrapper']/li/@data-project-name")[i]
                print(project_id,end=',')
                #详情页url
                detail_url = BASEURL+"p_"+project_id
                print(detail_url,end=',')
                # 获取标题
                title = content.xpath("//ul[@class='resblock-list-wrapper']/li/a/@title")[i]
                print(title,end=',')
                # 获取详细小区信息
                detail_area= content.xpath("//ul[@class='resblock-list-wrapper']/li//div[@class='resblock-location']/span[2]/text()")[i]
                print(detail_area,end=',')
                # 获取详细地址
                detail_place = content.xpath("//ul[@class='resblock-list-wrapper']/li//div[@class='resblock-location']/a/text()")[i]
                print(detail_place,end=',')
                # 获取小区类型
                type = content.xpath("//ul[@class='resblock-list-wrapper']/li//div[@class='resblock-name']/span[1]/text()")[i]
                print(type,end=',')
                sale_status = content.xpath("//ul[@class='resblock-list-wrapper']/li//div[@class='resblock-name']/span[2]/text()")[i]
                print(sale_status,end=',')
                # 获取面积
                try:
                    square = content.xpath("//ul[@class='resblock-list-wrapper']/li//div[@class='resblock-area']/span/text()")[i]
                except:
                    square = ""
                print(square,end=',')
                # 获取价格
                price = content.xpath("//ul[@class='resblock-list-wrapper']/li//div[@class='main-price']/span[1]/text()")[i]
                #价格待定的楼盘设置price为0
                if price=='价格待定':
                    price = None
                else:
                    price = int(price)
                print(price,end=',')
                #获取标签tag
                tag = content.xpath("/html/body/div[3]/ul[2]/li[{}]/div/div[5]/span/text()".format(i+1))
                print(tag,end='\n')
                
            except:
                break
            
            doc = {
                "project_id":project_id,
                "detail_url":detail_url,
                "area":area,
                "title":title,
                "detail_area":detail_area,
                "detail_place":detail_place,
                "type":type,
                "sale_status":sale_status,
                "square":square,
                "price":price,
                "tag":tag
            }    
            data.append(doc)
        save_data(data) #保存到mongodb中，该方法框架已写好，需要自己实现细节   
        print('continue the next page...')
    except:
        print(res.text)
        print(url)
        print('详情页面未获取成功，请手动查看页面是否需要人机验证！')
        time.sleep(30)
        

def save_data(data=None,host="127.0.0.1",port=27017,db_name="lianjia",col_name="loupan"):
   
    '''
    将解析到的楼盘详情数据存储到MongoDB数据库中
    :param data: 楼盘详情数据
    :param host: mongodb服务器地址
    :param port: mongodb服务端口
    :param db_name: mongodb数据库名称
    :param col_name: mongodb数据集合名称
    :return:
    '''
    #1.创建连接数据库对象
    #2.连接数据库
    #3.连接集合并实现插入
    
    pass

def main():
    print('开始!')
    # 重庆主站URL
    url = 'https://cq.fang.lianjia.com/loupan/'
    # 访问主站URL获取区县信息
    get_areas(url)
    
    

if __name__ == '__main__':
    main()
    

分析数据

1. 分析各个区新楼盘的平均价格、房屋占比情况等等
   
   

问题

1. 问题一
   没有相应的包，截图省略

解决方案：通过pip安装下面三个包即可

pip install requests
pip install lxml
pip install pymongo

2. 问题二
   count = int(content.xpath(‘//div[@class =“page-box”]/@data-total-count’)[0])
   ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~^^^
   IndexError: list index out of range
   
   解决办法：打开对应的网页（https://cq.fang.lianjia.com/loupan/jiangbei）进行人机验证即可。这里是因为拿不到data-total-count值报错