#需求:爬取58二手房中的房源信息
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/88.0.4324.146 Safari/537.36'
}
#爬取到页面源码数据
url = 'https://sx.58.com/ershoufang/?PGTID=0d100000-0016-37fb-858e-a4cdf215c9b2&ClickID=2'
page_text= requests.get(url=url,headers=headers).text
#进行数据解析
tree=etree.HTML(page_text)#拿到的网页,而不是局部的数据
li_list=tree.xpath('//h3[@class="property-content-title-name"]/text()')
fp = open('./58.txt', 'w', encoding='utf-8')
for li in li_list:
# 局部解析
title = li
print(title)
fp.write(title + '\n')
xpath案例1——爬取58同城二手房的信息
最新推荐文章于 2023-09-24 16:02:01 发布