爬取每月天气变化并生成折线图

风船野

输入年月和城市，爬取该城市当月天气，并生成折线图
代码包括爬虫，可视化，和图形界面三大部分。
简易图形界面：

结果展示：


代码：

1. import requests
   
2. from matplotlib import pyplot as plt, font_manager
   
3. import bs4
   
4. from xpinyin import Pinyin
   
5. from tkinter import *
   
6. 
   
7. 
   
8. # 创建网址链接
   
9. def urls():
   
10.     global dates
    
11.     p = Pinyin()
    
12.     city = e1.get()
    
13.     city = p.get_pinyin(city)  # 汉字转为拼音
    
14.     city = city.replace("-", "")
    
15.     dates = variable1.get() + variable2.get()
    
16.     url = f"https://lishi.tianqi.com/{city}/{dates}.html".format(city=city, dates=dates)
    
17.     print(url)
    
18.     return url
    
19. 
    
20. 
    
21. # 爬取网页数据
    
22. def open_url(url):
    
23.     headers = {
    
24.         "accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8,"
    
25.                   "application/signed-exchange;v=b3;q=0.9",
    
26.         "sec - fetch - site": "same - origin",
    
27.         "accept - encoding": "gzip, deflate, br",
    
28.         "cache-control": "max-age=0",
    
29.         "accept-language": "zh-CN,zh;q=0.9",
    
30.         "referer": "https://www.tianqi.com/qiwen/city-xian-3/",
    
31.         "upgrade - insecure - requests": "1",
    
32.         "cokkie": "UM_distinctid=17a7045d2b737c-09469a16397897-6373264-149c48-17a7045d2b8b9a; "
    
33.                   "Hm_lvt_ab6a683aa97a52202eab5b3a9042a8d2=1625381262; "
    
34.                   "CNZZDATA1275796416=1699660372-1625376765-https%253A%252F%252Fwww.google.com.hk%252F%7C1625398369; "
    
35.                   "Hm_lpvt_ab6a683aa97a52202eab5b3a9042a8d2=1625402066",
    
36.         "user-agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) "
    
37.                       "Chrome/91.0.4472.124 Safari/537.36"}
    
38.     res = requests.get(url, headers=headers)
    
39.     return res
    
40. 
    
41. 
    
42. # 数据搜索
    
43. def find_s(res):
    
44.     temperature = []
    
45. 
    
46.     soup = bs4.BeautifulSoup(res.text, "html.parser")
    
47.     targets = soup.find("ul", class_="thrui")
    
48.     targets = targets.find_all("div", class_="th140")
    
49.     for each in targets:
    
50.         temperature.append(each.text)
    
51.     return temperature
    
52. 
    
53. 
    
54. # 数据分组处理
    
55. def handles_list(temperature):
    
56.     global temperature_max
    
57.     temperature_max, temperature_min = [], []
    
58.     for i in range(0, len(temperature), 4):
    
59.         temperature_max.append(temperature[i].replace("℃", ""))
    
60.         temperature_min.append(temperature[i + 1].replace("℃", ""))
    
61.     return temperature_max, temperature_min
    
62. 
    
63. 
    
64. # 制作折线图
    
65. def drawing(y_max, y_min):
    
66.     city = e1.get()
    
67.     data = dates[5]
    
68. 
    
69.     y_max = list(map(float, y_max))
    
70.     y_min = list(map(float, y_min))
    
71.     y_max = list(map(int, y_max))
    
72.     y_min = list(map(int, y_min))
    
73.     my_font = font_manager.FontProperties(fname="C:\Windows\Fonts\STKAITI.TTF")
    
74.     plt.figure(figsize=(20, 9), dpi=100)
    
75. 
    
76.     x = range(1, len(temperature_max) + 1)
    
77. 
    
78.     plt.plot(x, y_max, label="最高温度", color="red")
    
79.     plt.plot(x, y_min, label="最低温度", color="cyan")
    
80. 
    
81.     xl = [data + "月{}日".format(i) for i in x]
    
82.     plt.xticks(x, xl, fontproperties=my_font, rotation=40)
    
83.     plt.yticks(range(min(y_min + y_max), max(y_min + y_max) + 4, 2))
    
84.     plt.xlabel("时间", fontproperties=my_font)
    
85.     plt.ylabel("温度", fontproperties=my_font)
    
86.     plt.title("{city}{data}月份每日温度变化表".format(city=city, data=data), fontproperties=my_font)
    
87. 
    
88.     plt.legend(prop=my_font)
    
89.     plt.grid(alpha=0.8)
    
90.     plt.savefig("./{city}{data}月份每日温度变化表.png".format(city=city, data=data))
    
91.     plt.show()
    
92. 
    
93. 
    
94. def main():
    
95.     try:
    
96.         url = urls()
    
97.         res = open_url(url)
    
98.         temperature = find_s(res)
    
99.         y_max, y_min = handles_list(temperature)
    
100.         drawing(y_max, y_min)
     
101.     except AttributeError:
     
102.         lab5.grid(row=2, column=1, columnspan=4, rowspan=2, padx=10, pady=10)
     
103. 
     
104. 
     
105. # 图形界面
     
106. root = Tk()
     
107. f1 = Frame(root).grid()
     
108. lab1 = Label(f1, text="日期:").grid(row=0, column=0)
     
109. lab2 = Label(f1, text="城市:").grid(row=1, column=0)
     
110. 
     
111. variable1 = StringVar()
     
112. variable2 = StringVar()
     
113. variable1.set("2021")
     
114. variable2.set("01")
     
115. w = OptionMenu(f1, variable1, "2021", "2020", "2019", "2018", "2017", "2016", "2015", "2014", "2013"). \
     
116.     grid(row=0, column=1)
     
117. lab3 = Label(f1, text="年").grid(row=0, column=2)
     
118. w2 = OptionMenu(f1, variable2, "01", "02", "03", "04", "05", "06", "07", "08", "09", "10", "11", "12") \
     
119.     .grid(row=0, column=3)
     
120. lab4 = Label(f1, text="月").grid(row=0, column=4)
     
121. e1 = Entry(f1)
     
122. e1.grid(row=1, column=1, columnspan=4)
     
123. 
     
124. b1 = Button(f1, text="确定", width=10, command=main).grid(row=1, column=5, sticky=W, padx=10, pady=5)
     
125. lab5 = Label(f1, text="数据还没统计，等等再来吧！！！", foreground="red", font=("宋体", 10))
     
126. 
     
127. mainloop()
     

复制代码

希望各位大佬指正存在问题。感激不尽。