Python实战实现爬取天气数据并完成可视化分析详解

import random
import time
from spider.data_storage import DataStorage
from spider.html_downloader import HtmlDownloader
from spider.html_parser import HtmlParser
class SpiderMain:
    def __init__(self):
        self.html_downloader=HtmlDownloader()
        self.html_parser=HtmlParser()
        self.data_storage=DataStorage()
    def start(self):
        \"\"\"
        爬虫启动方法
        将获取的url使用下载器进行下载
        将html进行解析
        数据存取
        :return:
        \"\"\"
        for i in range(1,13):  # 采用循环的方式进行依次爬取
            time.sleep(random.randint(0, 10))  # 随机睡眠0到40s防止ip被封
            url=\"XXXX\"
            if i<10:
               url =url+\"20210\"+str(i)+\".html\"  # 拼接url
            else:
                url=url+\"2021\"+str(i)+\".html\"
            html=self.html_downloader.download(url)
            resultWeather=self.html_parser.parser(html)
            if i==1:
             t = [\"日期\", \"最高气温\", \"最低气温\", \"天气\", \"风向\"]
             resultWeather.insert(0,t)
            self.data_storage.storage(resultWeather)
if __name__==\"__main__\":
    main=SpiderMain()
    main.start()

import requests as requests
class HtmlDownloader:
    def download(self,url):
        \"\"\"
        根据给定的url下载网页
        :param url:
        :return: 下载好的文本
        \"\"\"
        headers = {\"User-Agent\":
                       \"Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:101.0) Gecko/20100101 Firefox/101.0\"}
        result = requests.get(url,headers=headers)
        return result.content.decode(\'utf-8\')

from bs4 import BeautifulSoup
class HtmlParser:
    def parser(self,html):
        \"\"\"
        解析给定的html
        :param html:
        :return: area set
        \"\"\"
        weather = []
        bs = BeautifulSoup(html, \"html.parser\")
        body = bs.body  # 获取html中的body部分
        div = body.find(\'div\', {\'class:\', \'tian_three\'})  # 获取class为tian_three的

        ul = div.find(\'ul\')  # 获取div中的

        li = ul.find_all(\'li\')  # 获取ul中的所有

        for l in li:
            tempWeather = []
            div1 = l.find_all(\"div\")  # 获取当前li中的所有div
            for i in div1:
                tempStr = i.string.replace(\"℃\", \"\")  # 将℃进行替换
                tempStr = tempStr.replace(\" \", \"\")  # 替换空格
                tempWeather.append(tempStr)
            weather.append(tempWeather)
        return weather

import pandas as pd
class DataStorage:
    def storage(self,weather):
        \"\"\"
        数据存储
        :param weather list
        :return:
        \"\"\"
        data = pd.DataFrame(columns=weather[0], data=weather[1:])  # 格式化数据
        data.to_csv(\"C:\\\\Users\\\\86183\\\\Desktop\\\\成都.csv\", index=False, sep=\",\",mode=\"a\")  # 保存到csv文件当中

import pandas as pd
import matplotlib as mpl
import numpy as np
import matplotlib.pyplot as plt
plt.rcParams[\"font.sans-serif\"] = [\"SimHei\"]  # 设置字体
plt.rcParams[\"axes.unicode_minus\"] = False  # 该语句解决图像中的“-”负号的乱码问题
def broken_line_chart(x, y1, y2):  # 折线图绘制函数
    plt.figure(dpi=500, figsize=(10, 5))
    plt.title(\"泸州-成都每日平均气温折线图\")
    plt.plot(x, y1, color=\'cyan\', label=\'泸州\')
    plt.plot(x, y2, color=\'yellow\', label=\'成都\')
    # 获取图的坐标信息
    coordinates = plt.gca()
    # 设置x轴每个刻度的间隔天数
    xLocator = mpl.ticker.MultipleLocator(30)
    coordinates.xaxis.set_major_locator(xLocator)
    # 将日期旋转30°
    plt.xticks(rotation=30)
    plt.xticks(fontsize=8)
    plt.ylabel(\"温度(℃)\")
    plt.xlabel(\"日期\")
    plt.legend()
    plt.savefig(\"平均气温走势折线图.png\")  # 平均气温折线图
    plt.show()
    plt.close()
data_luZhou = pd.read_csv(\'C:\\\\Users\\\\86183\\\\Desktop\\\\泸州.csv\')
data_chengdu = pd.read_csv(\'C:\\\\Users\\\\86183\\\\Desktop\\\\成都.csv\')
# 将列的名称转为列表类型方便添加
columS = data_luZhou.columns.tolist()
columY = data_chengdu.columns.tolist()
# 将数据转换为列表
data_luZhou=np.array(data_luZhou).tolist()
data_chengdu=np.array(data_chengdu).tolist()
# 在最开始的位置上添加列的名字
data_luZhou.insert(0, columS)
data_chengdu.insert(0, columY)
# 添加平均气温列
data_luZhou[0].append(\"平均气温\")
data_chengdu[0].append(\"平均气温\")
weather_dict_luZhou = {}
weather_dict_chengdu = {}
for i in range(1, len(data_luZhou)):
    # 去除日期中的星期
    data_luZhou[i][0] = data_luZhou[i][0][0:10]
    data_chengdu[i][0] = data_chengdu[i][0][0:10]
    # 获取平均气温
    average_luZhou = int((int(data_luZhou[i][1]) + int(data_luZhou[i][2])) / 2)
    average_chengdu = int((int(data_chengdu[i][1]) + int(data_chengdu[i][2])) / 2)
    # 将平均气温添加进入列表中
    data_luZhou[i].append(average_luZhou)
    data_chengdu[i].append(average_chengdu)
# 将新的数据存入新的csv中
new_data_luZhou = pd.DataFrame(columns=data_luZhou[0], data=data_luZhou[1:])
new_data_chengdu = pd.DataFrame(columns=data_chengdu[0], data=data_chengdu[1:])
new_data_luZhou.to_csv(\"D:/PythonProject/spider/泸州.csv\", index=False, sep=\",\")
new_data_chengdu.to_csv(\"D:/PythonProject/spider/成都.csv\", index=False, sep=\",\")
# 折线图的绘制
y1 = np.array(new_data_luZhou.get(\"平均气温\")).tolist()
y2 = np.array(new_data_chengdu.get(\"平均气温\")).tolist()
x = np.array(new_data_luZhou.get(\"日期\")).tolist()
broken_line_chart(x, y1, y2)
# 进行每个月的平均气温求解
new_data_luZhou[\"日期\"] = pd.to_datetime(new_data_luZhou[\"日期\"])
new_data_chengdu[\"日期\"] = pd.to_datetime(new_data_chengdu[\"日期\"])
new_data_luZhou.set_index(\"日期\", inplace=True)
new_data_chengdu.set_index(\"日期\", inplace=True)
# 按月进行平均气温的求取
month_l = new_data_luZhou.resample(\'m\').mean()
month_l = np.array(month_l).tolist()
month_c = new_data_chengdu.resample(\'m\').mean()
month_c = np.array(month_c).tolist()
length = len(month_c)
month_average_l = []
month_average_c = []
for i in range(length):
    month_average_l.append(month_l[i][2])
    month_average_c.append(month_c[i][2])
month_list = [str(i) + \"月\" for i in range(1, 13)]
plt.figure(dpi=500, figsize=(10, 5))
plt.title(\"泸州-成都每月平均折线气温图\")
plt.plot(month_list, month_average_l, color=\"cyan\",label=\"泸州\", marker=\'o\')
plt.plot(month_list, month_average_c, color=\"blue\",label=\'成都\', marker=\'v\')
for a, b in zip(month_list, month_average_l):
    plt.text(a, b + 0.5, \'%.2f\' % b, horizontalalignment=\'center\', verticalalignment=\'bottom\', fontsize=6)
for a, b in zip(month_list, month_average_c):
    plt.text(a, b - 0.5, \'%.2f\' % b, horizontalalignment=\'center\', verticalalignment=\'bottom\', fontsize=6)
plt.legend()
plt.xlabel(\"月份\")
plt.ylabel(\"温度（℃）\")
plt.savefig(\"月平均气温折线图.png\")  # 月平均气温折线图
plt.show()
#
# 只获取两列的数据
data_l = pd.read_csv(\"泸州.csv\", usecols=[\'风向\', \'平均气温\'])
data_c = pd.read_csv(\"成都.csv\", usecols=[\'风向\', \'平均气温\'])
data_l = np.array(data_l).tolist()
data_c = np.array(data_c).tolist()
day_c = 0
day_l = 0
for i in range(len(data_l)):
    if len(data_l[i][0]) == 5:
        if int(data_l[i][0][3]) < 5 and 18 <= int(data_l[i][1]) <= 25:
            day_l += 1
    else:
        if int(data_l[i][0][2]) < 5 and 18 <= int(data_l[i][1]) <= 25:
            day_l += 1
    if len(data_c[i][0]) == 5:
        if int(data_c[i][0][3]) < 5 and 10 <= int(data_c[i][1]) <= 25:
            day_c += 1
    else:
        if int(data_c[i][0][2]) < 5 and 18 <= int(data_c[i][1]) <= 25:
            day_c += 1
plt.figure(dpi=500, figsize=(8, 4))
plt.title(\"泸州-成都平均气温在18-25且风力＜5级的天数\")
list_name = [\'泸州\', \'成都\']
list_days = [day_l, day_c]
plt.bar(list_name, list_days, width=0.5)
plt.text(0, day_l, \'%.0f\' % day_l, horizontalalignment=\'center\', verticalalignment=\'bottom\', fontsize=7)
plt.text(1, day_c, \'%.0f\' % day_c, horizontalalignment=\'center\', verticalalignment=\'bottom\', fontsize=7)
plt.xlabel(\"城市\")
plt.ylabel(\"天数(d)\")
plt.savefig(\"适宜居住柱形图.png\")
plt.show()
data_l=pd.read_csv(\"泸州.csv\")
data_c=pd.read_csv(\"成都.csv\")
# 将数据转换为列表
data_l=np.array(data_l).tolist()
data_c=np.array(data_c).tolist()
# 获取每种天气的天数，采用字典类型进行存储
for i in range(1,365):
    weather_l = data_l[i][3]
    weather_c = data_c[i][3]
    if weather_l in weather_dict_luZhou:
       weather_dict_luZhou[weather_l] = weather_dict_luZhou.get(weather_l) + 1
    else:
       weather_dict_luZhou[weather_l]=1
    if weather_c in weather_dict_chengdu:
        weather_dict_chengdu[weather_c]=weather_dict_chengdu.get(weather_c)+1
    else:
       weather_dict_chengdu[weather_c]=1
weather_list_luZhou = list(weather_dict_luZhou)
weather_list_chengdu = list(weather_dict_chengdu)
value_l = []
value_c = []
# 获取所有的天气种类
weather_list = sorted(set(weather_list_luZhou + weather_list_chengdu))
# 获取每种天气的天数，并将其对应的放入列表中，没有的则用0进行替代，方便条形图的绘制。
for i in weather_list:
    if i in weather_dict_luZhou:
        value_l.append(weather_dict_luZhou[i])
    else:
        value_l.append(0)
    if i in weather_dict_chengdu:
        value_c.append(weather_dict_chengdu[i])
    else:
        value_c.append(0)
# 绘制条形图进行对比
plt.figure(dpi=500, figsize=(10, 5))
plt.title(\"泸州-成都各种天气情况对比\")
x1 = list(range(len(weather_list)))
x = [i + 0.4 for i in x1]
plt.bar(x1, value_l, width=0.4, color=\'red\', label=\'泸州\')
plt.bar(x, value_c, width=0.4, color=\'orange\', label=\'成都\')
for a, b in zip(x1, value_l):
    plt.text(a, b + 0.4, \'%.0f\' % b, ha=\'center\', va=\'bottom\', fontsize=7)
for a, b in zip(x, value_c):
    plt.text(a, b + 0.4, \'%.0f\' % b, ha=\'center\', va=\'bottom\', fontsize=7)
plt.xticks(x1, weather_list)
plt.ylabel(\"天数\")
plt.xlabel(\"天气\")
plt.xticks(rotation=270)
plt.legend()
plt.savefig(\"泸州成都天气情况对比.png\")
plt.show()
plt.close()