8. xpath - 58房源信息爬取

image.png
image.png
image.png
image.png

# 需求：爬取58二手房中房源信息
import requests
from lxml import etree
if __name__=="__main__":
    headers = {
        'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) '
                      'AppleWebKit/537.36 (KHTML, like Gecko) '
                      'Chrome/96.0.4664.45 Safari/537.36'
    }
    # 爬取到页面源码数据
    url = 'https://bj.58.com/ershoufang/'
    page_text = requests.get(url=url,headers=headers).text

    # 数据解析
    tree = etree.HTML(page_text)
    # 存储的就是li标签对象
    li_list = tree.xpath('//url[@class="house-list-wrap"]/li')
    fp = open('58.txt','w',encoding='utf-8')
    for li in li_list:
        # 局部解析
        title = li.xpath('./div[2]/h2/a/text()')[0]
        print(title)
        fp.write(title+'\n')