[Python3 crawler] 17_ Crawling weather information

Statement of needs

Go to the website http://lishi.tianqi.com/kunming/201802.html to see the weather information of Kunming in February 2018, and then store the data in the database.

implementation code

#-*-coding:utf-8 -*-
import urllib.request
import random
import pymysql
from bs4 import BeautifulSoup

user_agent = [
    'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/54.0.2840.87 Safari/537.36',  
        'Mozilla/5.0 (X11; U; Linux x86_64; zh-CN; rv:1.9.2.10) Gecko/20100922 Ubuntu/10.10 (maverick) Firefox/3.6.10',  
        'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11',  
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/30.0.1599.101 Safari/537.36',  
        'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.71 Safari/537.1 LBBROWSER',  
        'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; .NET4.0E; QQBrowser/7.0.3698.400)', 
]

headers = {'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',  
'Accept-Encoding': 'gzip, deflate, sdch',  
'Accept-Language': 'zh-CN,zh;q=0.8',  
'User-Agent': user_agent[random.randint(0,5)]}



print ( " Connect to mysql server " )
db = pymysql.connect("192.168.6.128","root","root","test_db",charset="utf8")
print("******连接成功********")

cursor = db.cursor()

cursor.execute("DROP TABLE IF EXISTS TB")

sql = """CREATE TABLE TB(DT_DATE VARCHAR(10),
    HIGH_TEMP VARCHAR(40),LOW_TEMP VARCHAR(40),WEATHER VARCHAR(40),WIND VARCHAR(40),WIND_TAIL VARCHAR(10))"""
cursor.execute(sql)

url = "http://lishi.tianqi.com/kunming/201802.html"

index = urllib.request.urlopen(url).read()
print(index)
#print(index)
index_soup = BeautifulSoup(index)

i = 1
 # class_="" here is to filter the title bar of calss="t1" 
uls = index_soup.find( " div " ,class_= " tqtongji2 " ).find_all( " ul " ,class_= "" ) #Get all ul as a list

for ul in uls:
    style = ul.get( ' style ' ) #traverse all li single items 
    lis = ul.find_all( ' li ' ) # get the labels under each li as a list 
    li = [x for x in lis]
    V_DT_DATE = li[0].text.strip()

    V_HIGH_TEMP = li[1].text.strip()
    V_LOW_TEMP = li[2].text.strip()
    V_WEATHER = li[3].text.strip()
    V_WIND = li[4].text.strip()
    #print(V_WIND)
    V_WIND_TAIL = li[5].text.strip()
    inser_tb = ("INSERT INTO TB " "VALUES(%s,%s,%s,%s,%s,%s)")
    data = (V_DT_DATE,V_HIGH_TEMP,V_LOW_TEMP,V_WEATHER,V_WIND,V_WIND_TAIL)
    cursor.execute(inser_tb,data)
    db.commit()
print ( " Data has been crawled and stored in Mysql " )
db.close()