深圳房产信息爬取

最新推荐文章于 2021-07-12 15:10:52 发布

mo8808

最新推荐文章于 2021-07-12 15:10:52 发布

阅读量394

点赞数

CC 4.0 BY-SA版权

文章标签：爬虫

本文链接：https://blog.youkuaiyun.com/mo8808/article/details/101616713

from selenium import webdriver
import time

driver = webdriver.Firefox(executable_path = r'C:\Users\mok9697m\Desktop\geckodriver.exe')
#把上述地址改成你电脑中geckodriver.exe程序的地址
for i in range(0,3):
    link = "https://zh.airbnb.com/s/Shenzhen--China/homes?items_offset=" + str(i *18)
    driver.get(link)
    time.sleep(5)
    rent_list = driver.find_elements_by_css_selector('div._gig1e7')

    for eachhouse in rent_list:
        try:
            comment = eachhouse.find_element_by_css_selector('div._qhtkbey').text
        except:
            comment = 0
        price = eachhouse.find_element_by_css_selector('div._1ovgt1s0>div._1ixtnfc>span:nth-child(2)')
        price = price.text.replace("每晚", "").replace("价格", "").replace("\n", "")
     
        details = eachhouse.find_element_by_css_selector('span._fk7kh10')
        details = details.text
        house_type = details.split(" · ")[0]
        bed_number = details.split(" · ")[1]
       
        print (comment,price,house_type,bed_number)
    time.sleep(5)
 #price = eachhouse.find_element_by_css_selector('div._1yarz4r')
       # price = price.text.replace("每晚", "").replace("价格", "").replace("\n", "")
        #name = eachhouse.find_element_by_css_selector('div._vbshb6')
       # name = name.text
        #details = eachhouse.find_element_by_css_selector('span._14ksqu3j')
        #details = details.text
       # house_type = details.split(" · ")[0]
       # bed_number = details.split(" · ")[1]
        #print (comment, price, name, house_type, bed_number)