爬虫——爬取7天天气状况

最新推荐文章于 2024-08-23 13:57:37 发布

正在学习c

最新推荐文章于 2024-08-23 13:57:37 发布

阅读量456

点赞数

本文链接：https://blog.csdn.net/qq_43345339/article/details/108291515

版权

import requests
from lxml import etree

# 网页地址
    # http://www.weather.com.cn/weather1d/103163100.shtml
    # http://www.weather.com.cn/weather1d/101010100.shtml
    #http://www.weather.com.cn/weather1d/101030100.shtml
    #http://www.weather.com.cn/weather1d/101120101.shtml
    #http://www.weather.com.cn/weather1d/101120201.shtml
    #http://www.weather.com.cn/weather1d/101020100.shtml
    #http://www.weather.com.cn/weather1d/101260101.shtml
url = "http://www.weather.com.cn/weather/101120701.shtml"
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/84.0.4147.135 Safari/537.36'
}

# 准备请求头

response = requests.get(url,headers = headers)

# 获得html文件
html = etree.HTML(response.text)
# print(html)
day_list = html.xpath('//ul[@class="t clearfix"]/li/h1/text()')
wea_list = html.xpath('//ul[@class="t clearfix"]/li/p[@class="wea"]/text()')
tem_list1 = html.xpath('//ul[@class="t clearfix"]/li/p[@class="tem"]/span/text()')
tem_list2 = html.xpath('//ul[@class="t clearfix"]/li/p[@class="tem"]/i/text()')
tem_list = []
for i in range(len(tem_list1)):
    tem_list.append(tem_list1[i]+'/'+tem_list2[i])
list = []

# 显示出来爬取的数据
for i in range(len(tem_list1)):
    str1 = (day_list[i]+':'+wea_list[i]+tem_list[i]).encode("ISO-8859-1").decode('utf-8')
    with open('wea.txt','a',encoding='utf-8') as f:
        f.write(str1)
        f.write('\n')