爬虫小练习

爬取全国天气

仅供学习，请勿滥用

import pandas as pd ,numpy as np 
import matplotlib.pyplot as plt 
import lxml.etree as tree
import requests,time as T
#**以山东德州为例**
headers = {
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) '
                        'Chrome/51.0.2704.63 Safari/537.36'
            }
url =np.array([[fr"https://lishi.tianqi.com/dezhou/20{year}{month}.html" 
       for month in ['01','02','03','04','05','06','07','08','09','10','11','12']]
      for year in ['01','02','03','04','05','06','07','08','09','10','11','12',，'13','14','15',"16",'17','18','19','20']]).flatten()
air_name = ['平均高温', '平均低温', '极端高温', '极端低温', '平均空气质量指数', '空气最好', '空气最差']
weather_data = []
for url_ in url:
    T.sleep(0.5)
    response = requests.get(url_,headers=headers)
    text = response.text
    print(response)
    html = tree.HTML(text)
    time_ = url_.split(sep = r'/')[-1][:-5]
    data = html.xpath(r'//div[@class="tian_twoa"]/text()')
#     data_name =  html.xpath(r'//div[@class="tian_twob"]/text()')
    res = data.append(time_)
    weather_data.extend([res])