一段很简单的爬虫程序,爬取的网站为http://www.tianqihoubao.com,可以自己修改爬取城市以及爬取的月份,这里爬取的是1到7月的数据
from bs4 import BeautifulSoup
import requests
import pymysql
import warnings
# import pinyin
# from pinyin import PinYin
from pypinyin import pinyin, lazy_pinyin
import pypinyin
warnings.filterwarnings("ignore")
conn = pymysql.connect(host='localhost', user='root', passwd='root', db='test2', port=3306, charset='utf8')
cursor = conn.cursor()
def get_temperature(url,city):
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36'} # 设置头文件信息
response = requests.get(url, headers=headers).content # 提交requests get 请求
soup = BeautifulSoup(response, "lx