抓取空气质量指数AQI_PM2.5历史数据，可视化展示

抓取空气质量指数AQI_PM2.5历史数据，可视化展示：

url=‘http://www.tianqihoubao.com/aqi/hangzhou-201810.html’杭州的空气质量数据，可以在主页抓取全国的pm2.5数据展示

import time,requests,re
import pandas as pd
from lxml import etree
#https://blog.csdn.net/u013337691/article/details/51894453

url='http://www.tianqihoubao.com/aqi/hangzhou.html'
headers = {'user-agent': "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_2) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.95 Safari/537.36", }

response = requests.get(url, headers=headers)
html = response.text
response = etree.HTML(html)

url_list = response.xpath('//div[@class="box p"]//a/@href')
for url in url_list:
    url='http://www.tianqihoubao.com'+url

    #print(url)
    #url='http://www.tianqihoubao.com/aqi/hangzhou-201810.html'

    data = pd.read_html(url, header=0, encoding='gbk')[0]
    print(data)
    time.sleep(1)
    data.to_csv("pm2.5.csv",mode='a', header=False)

数据分析：

import pandas as pd
from matplotlib import  pyplot as plt
file_path = "pm2.5.csv"
#杭州市2013.10-2018.11的PM2.5随时间的变化情况:

df = pd.read_csv(file_path,names=['data_time','quality','AQI','ranking','PM2.5','Pm10','So2','No2','Co','O3'])
#print(df)

df["timeStamp"] = pd.to_datetime(df["data_time"]) #把时间字符串转为索引

df.set_index('timeStamp',inplace=True)  #
#print(df.head())

#进行降采样：
df=df.resample('M').mean()

#绘图：
plt.figure(figsize=(20, 8), dpi=80)
data=df['PM2.5']
# print(data.index)
# print(data.values)

_x=data.index
_y=data.values
_x = [i.strftime("%Y%m%d") for i in _x]
plt.plot(range(len(_x)), _y)
plt.xticks(range(len(_x)), _x, rotation=45)
plt.show()