安居客无锡二手房数据获取

最新推荐文章于 2024-11-26 23:55:59 发布

小明ღ

最新推荐文章于 2024-11-26 23:55:59 发布

阅读量719

点赞数 1

本文链接：https://blog.youkuaiyun.com/weixin_43210595/article/details/115350019

版权

本文展示了如何使用selenium模拟浏览器抓取安居客无锡二手房信息，同时提供了两种方法：一是requests配合BeautifulSoup解析，二是lxml直接解析XPath。通过对比，深入理解不同工具在网页抓取中的应用。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

安居客无锡二手房

网址： https://wuxi.anjuke.com/sale/

用selenium模拟浏览器抓取

# 用selenium模拟浏览器抓取
# selenium版本3.141.0
# firefox版本86.0
# geckodriver0.29.0
# geckodriver下载地址：https://github.com/mozilla/geckodriver/releases
from selenium import webdriver
import time
import pandas as pd
driver = webdriver.Firefox(executable_path = r'D:\geckodriver.exe') #geckodriver.exe的存放位置
link = "https://wuxi.anjuke.com/sale/"
driver.get(link)
df = pd.DataFrame(columns=('title', 'name', 'price', 'price_area', 'no_room', 'area', 'orientations', 'floor', 'year', 'address', 'tags'))
a = 0
for x in range(50):
    print('正在爬取第%s页'%(x+1))
    house_list = driver.find_elements_by_css_selector('div.property')
    for i in range(len(house_list)):
        title = house_list[i].find_elements_by_css_selector('h3.property-content-title-name')[0].text
        name = house_list[i].find_elements_by_css_selector('p.property-content-info-comm-name')[0].text
        price = house_list[i].find_elements_by_css_selector('span.property-price-total-num')[0].text
        price_area = house_list[i].find_elements_by_css_selector('p.property-price-average')[0].text
        no_rooms = house_list[i].find_elements_by_xpath('//div[@class="property"]/a/div[2]/div[1]/section/div[1]/p[1]/span')
        no_room = no_rooms[6*i].text+no_rooms[6*i+1].text+no_rooms[6*i+2].text+no_rooms[6*i+3].text+no_rooms[6*i+4].text+no_rooms[6*i+5].text
        infos = house_list[i].find_elements_by_xpath('//div[@class="property-content-info"]/p[@class="property-content-info-text"]')
        area = infos[4*i].text
        orientations = infos[4*i+1].text
        floor = infos[4*i+2].text
        try:
            year = infos[4*i+3].text
        except:
            year = ''
        address = house_list[i].find_elements_by_css_selector('p.property-content-info-comm-address')[0].text[:2]
        tag_list = house_list[i].find_elements_by_xpath('//div[@class="property"]['+str(i)+'+1]//div[@class="property-content-info"]/span')
        tags = [i.text for i in tag_list]
        row = {'title':title, 'name':name, 'price':price, 'price_area':price_area, 'no_room':no_room, 'area':area, 'orientations':orientations, 'floor':floor, 'year':year, 'address':address, 'tags':tags}
        df.loc[a]= row #将数据存储至df第a+1行
        a += 1
    time.sleep(5) #间隔5秒再爬取下一个页面
    next_page = driver.find_elements_by_css_selector('a.next')[0] #点击下一页
    next_page.click()
print('爬取完毕，一共爬取%s条数据'%(a))

使用requests抓取网页，用bs4解析网页

# 使用requests抓取网页，用bs4解析网页
import requests
from bs4 import BeautifulSoup
import pandas as pd
import time
from functools import reduce
headers = {'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36(KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36'}
df = pd.DataFrame(columns=('title', 'name', 'price', 'price_area', 'no_room', 'area', 'orientations', 'floor', 'year', 'address', 'tags', 'broker', 'rate', 'company'))
a = 0
for i in range(1,51):
    print('正在爬取第%s页'%(i))
    link = 'https://wuxi.anjuke.com/sale/p'+str(i) #由于网站初次访问需要验证码，运行程序前需要先手动打开一次网页输入验证码
    r = requests.get(link, headers = headers)
    soup = BeautifulSoup(r.text, 'lxml')
    house_list = soup.find_all('div', class_="property")
    for house in house_list:
        title = house.find('div', class_ ='property-content-title').h3.text.strip()
        price = house.find('span', class_ ='property-price-total-num').text.strip()
        price_area = house.find('p', class_='property-price-average').text.strip()
        no_room = house.find('div', class_='property-content-info').contents[0].text.strip()
        area = house.find('div', class_='property-content-info').contents[2].text.strip()
        orientations = house.find('div', class_='property-content-info').contents[4].text.strip()
        floor = house.find('div', class_='property-content-info').contents[6].text.strip()
        try:
            year = house.find('div', class_='property-content-info').contents[8].text.strip()
        except:
            year = ''
        name = house.find('p', class_='property-content-info-comm-name').text.strip()
        address = house.find('p', class_='property-content-info-comm-address').text.strip()[:2]
        tag_list = house.find_all('span', class_='property-content-info-tag')
        tags = [i.text for i in tag_list]
        broker = house.find('span', class_='property-extra-text').text
        broker_list = house.find_all('span', class_='property-extra-text')
        rate = broker_list[1].text.strip()[:3]
        try:
            company = broker_list[2].text.strip()
        except:
            company = ''
        row = {'title':title, 'name':name, 'price':price, 'price_area':price_area,
               'no_room':no_room, 'area':area, 'orientations':orientations,
               'floor':floor, 'year':year, 'address':address, 'tags':tags,
               'broker':broker, 'rate':rate, 'company':company}
        df.loc[a]= row
        a += 1
    time.sleep(5) 
print('爬取完毕，一共爬取%s条数据'%(a))

使用lxml解析网页（xpath）

# 使用lxml解析网页 （xpath）
import requests
from lxml import etree
import pandas as pd
import time
headers = {'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36(KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36'}
df = pd.DataFrame(columns=('title', 'name', 'price', 'price_area', 'no_room', 'area', 'orientations', 'floor', 'year', 'address', 'tags', 'broker', 'rate', 'company'))
a = 0
for x in range(50):
    print('正在爬取第%s页'%(x+1))
    time.sleep(5)
    link = "https://wuxi.anjuke.com/sale/p"+str(x+1)
    headers = {'User-Agent' : 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36(KHTML, like Gecko) Chrome/57.0.2987.98 Safari/537.36'} 
    r = requests.get(link, headers= headers)
    html = etree.HTML(r.text)
    title_list = html.xpath('//h3[@class="property-content-title-name"]/text()')
    name = html.xpath('//p[@class="property-content-info-comm-name"]/text()')
    price = html.xpath('//span[@class="property-price-total-num"]/text()')
    price_area = html.xpath('//p[@class="property-price-average"]/text()')
    no_rooms = html.xpath('//div[@class="property"]/a/div[2]/div[1]/section/div[1]/p[1]/span/text()')
    infos = html.xpath('//div[@class="property-content-info"]/p[@class="property-content-info-text"]/text()')
    info = [i.strip() for i in infos]
    address = html.xpath('//p[@class="property-content-info-comm-address"]/span[1]/text()')
    broker = html.xpath('//span[@class="property-extra-text"][1]/text()')
    rate = html.xpath('//span[@class="property-extra-text"][2]/text()')
    company = html.xpath('//span[@class="property-extra-text"][3]/text()')
    for i in range(len(title_list)):
        tags = html.xpath('//div[@class="property"]['+str(i)+'+1]//div[@class="property-content-info"]/span/text()')
        no_room = no_rooms[6*i]+no_rooms[6*i+1]+no_rooms[6*i+2]+no_rooms[6*i+3]+no_rooms[6*i+4]+no_rooms[6*i+5]
        row = {'title':title_list[i], 'name':name[i], 'price':price[i], 
               'price_area':price_area[i],'no_room':no_room, 'area':info[4*i],
               'orientations':info[4*i+1],'floor':info[4*i+2], 'year':info[4*i+3],
               'address':address[i], 'tags':tags, 'broker':broker[i],
               'rate':rate[i], 'company':company[i]}
        df.loc[a]=row
        a+=1