爬取天气信息

天气查询：http://www.tianqihoubao.com/

参考：https://blog.csdn.net/qq_38440882/article/details/82829865文章是保存到数据库，可以参考原文。

根据上面的内容，做了修改保存为DataFrame，保存为CSV，并且增加了温度上下限，可以参考下文。

from bs4 import BeautifulSoup
import requests
import pandas as pd
import warnings
from pypinyin import pinyin, lazy_pinyin
import pypinyin

warnings.filterwarnings("ignore")

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, "lxml")  # 用Beautifulsoup 进行解析

    conmid2 = soup.findAll('div', class_='wdetail')
    date_all=[]
    weather_all =[]
    temperature_up_all = []
    temperature_down_all = []
    wind_all = []
    for info in conmid2:
        tr_list = info.find_all('tr')[1:]  # 使用切片取到第三个tr标签
        for index, tr in enumerate(tr_list):  # enumerate可以返回元素的位置及内容
            td_list = tr.find_all('td')

            date = td_list[0].text.strip().replace("\n", "")  # 取每个标签的text信息，并使用replace()函数将换行符删除
            weather = td_list[1].text.strip().replace("\n", "").split("/")[0].strip()
            temperature_up = td_list[2].text.strip().replace("\n", "").split("/")[0].strip()
            temperature_down = td_list[2].text.strip().replace("\n", "").split("/")[1].strip()
            wind = td_list[3].text.strip().replace("\n", "").split("/")[0].strip()
            #print(city, date, weather, wind, temperature)
            date_all.append(date)
            weather_all.append(weather)
            temperature_up_all.append(temperature_up)
            temperature_down_all.append((temperature_down))
            wind_all.append(wind)
    return date_all, weather_all, temperature_up_all,temperature_down_all, wind_all


if __name__ == '__main__':

    citys1 = ["广州市"]
    data_all = pd.DataFrame()
    for city in citys1:
        city1 = ''.join(lazy_pinyin(city[:-1]))
        print(city1)
        urls = ['http://www.tianqihoubao.com/lishi/' + city1 + '/month/201809.html',
                'http://www.tianqihoubao.com/lishi/' + city1 + '/month/201810.html',
                'http://www.tianqihoubao.com/lishi/' + city1 + '/month/201811.html'
                ]
        for url in urls:
            date_all, weather_all, temperature_up_all, temperature_down_all, wind_all = get_temperature(url, city)
            data = pd.DataFrame({
                "date":date_all, "weather":weather_all, "temperature_up":temperature_up_all,"temperature_down":temperature_down_all,"wind":wind_all})
            data_all = pd.concat((data_all,data),axis=0)
            print(data_all.shape,data_all.columns)
    data_all.to_csv("weather_gz.csv", index= False)