import requests from bs4 import BeautifulSoup import pandas as pd import matplotlib.pyplot as plt # 抓取深圳的天气情况 url = "http://www.weather.com.cn/weather/101280601.shtml" response = requests.get(url) response.encoding = 'UTF-8' # print(response) soup = BeautifulSoup(response.text, 'html.parser') # print(soup) # 解析网页，获取日期、最高温度和最低温度 dates = [item.get_text() for item in soup.select('.t li h1')] dates = [item.get_text() for item in soup.select('.t li h1')] high_temps = [int(item.get_text().replace('℃', '')) for item in soup.select('.t li .tem span')] low_temps = [int(item.get_text().replace('℃', '')) for item in soup.select('.t li .tem i')] # 将数据保存到 DataFrame 中 df = pd.DataFrame({ 'date': dates, 'high_temp': high_temps, 'low_temp': low_temps }) # 将 DataFrame 保存到 CSV 文件中 df.to_csv('shenzhen_weather.csv', index=False) # 从 CSV 文件中读取 DataFrame df = pd.read_csv('shenzhen_weather.csv') # 绘制最高温度和最低温度的折线图 plt.rcParams['font.sans-serif'] = ['Arial Unicode MS'] plt.plot(df['date'], df['high_temp'], label='High Temperature') plt.plot(df['date'], df['low_temp'], label='Low Temperature') plt.xlabel('Date') plt.ylabel('Temperature (℃)') plt.title('Shenzhen Weather') plt.legend() plt.show()

# 请你根据你所在地区的气温、天气，使用 Excel 工具绘制一张天气和气温变化图表 import requests, pandas, matplotlib.pyplot # 数据采集 def get_data(): url = 'https://api.openweathermap.org/data/2.5/weather?q=YOUR_CITY,uk&appid=YOUR_API_KEY' response = requests.get(url) if response.status_code == 200: data = response.json() return data else: print('访问异常,异常状态码:' + requests.status_codes) return None # 数据挖掘 def save_data(data): if get_data(): df = pandas.DataFrame(data['weather'][0]) df['main'] = data['maiin'] df['dt_txt'] = data['dt_txt'] df['data'] = pandas.to_datetime(df['dt_txt']) grouped = df.groupby('data')['temp'].mean() return grouped else: print('数据存储失败,请检查数据采集') return None # 数据可视化 def show_data(grouped): matplotlib.pyplot.plot(grouped.index, grouped.values) matplotlib.pyplot.xlabel('Date') matplotlib.pyplot.ylabel('Average Temperature') matplotlib.pyplot.show()

一顿借鉴组装，实现了，抓取网页天气情况，保存到CSV中，读取CSV到df，图标展示双折线图显示最低与最高温度 import requests from bs4 import BeautifulSoup import csv import pandas as pd import matplotlib.pyplot as plt url = 'https://www.tianqi.com/shenyang/30/' def getHTMLtext(url): """请求获得网页内容""" headers = {"User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36"} try: r = requests.get(url, timeout = 30, headers = headers) r.raise_for_status() r.encoding = r.apparent_encoding print("成功访问") return r.text except: print("访问错误") return" " def get_content(html): """处理得到有用信息保存数据文件""" final = [] bs = BeautifulSoup(html, "html.parser") body = bs.body ul = body.find('ul', {'class': 'weaul'}) li = ul.find_all('li') i = 0 for day in li: if i < 30 and i > 0: temp = [] date = day.find(attrs={'class':'fl'}).string temp.append(date) inf = day.find_all(attrs={'class':'weaul_z'}) temp.append(inf[0].string) tem = inf[1].find_all('span') tem_low = tem[0].string tem_high = tem[1].string temp.append(tem_low) temp.append(tem_high) final.append(temp) i = i + 1 return final if __name__ == '__main__': html_text = getHTMLtext(url) data = get_content(html_text) header =[['日期','天气','最低温度','最高温度']] with open('weather.csv', 'w', newline='') as f: writer = csv.writer(f) writer.writerows(header) writer.writerows(data) df = pd.read_csv("weather.csv", encoding='gbk') x = df["日期"] y1 = df["最低温度"] y2 = df["最高温度"] # 中文乱码 plt.rcParams['font.sans-serif']=['SimHei'] plt.rcParams['axes.unicode_minus']=False # 绘制折线图 plt.plot(x, y1) plt.plot(x, y2) plt.title("本市近30天温度情况") plt.show()

抄作业改了下：） import requests from bs4 import BeautifulSoup import csv import pandas as pd import matplotlib.pyplot as plt url = 'https://www.tianqi.com/shenyang/30/' def getHTMLtext(url): headers = { "User-Agent": "Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36" } try: r = requests.get(url, timeout=30, headers=headers) r.raise_for_status() r.encoding = r.apparent_encoding print("成功访问") return r.text except Exception as e: print(f"访问错误, 错误原因:{e}") return -1 def get_content(html): final = [] body = BeautifulSoup(html, "html.parser").body ul = body.find('ul', {'class': 'weaul'}) li = ul.find_all('li') i = 0 for day in li: if i < 30 and i > 0: temp = [] date = day.find(attrs={'class': 'fl'}).string temp.append(date) inf = day.find_all(attrs={'class': 'weaul_z'}) temp.append(inf[0].string) tem = inf[1].find_all('span') tem_low = tem[0].string tem_high = tem[1].string temp.append(tem_low) temp.append(tem_high) final.append(temp) i = i + 1 return final if __name__ == '__main__': html_text = getHTMLtext(url) data = get_content(html_text) header = ['日期', '天气', '最低温度', '最高温度'] with open('weather.csv', 'w',newline='', encoding='utf-8') as f: writer = csv.writer(f) writer.writerow(header) writer.writerows(data) df = pd.read_csv("weather.csv",encoding="utf-8") x = df["日期"] y1 = df["最低温度"] y2 = df["最高温度"] plt.figure(figsize=(10, 6)) plt.rcParams['font.sans-serif'] = ['SimHei'] plt.rcParams['axes.unicode_minus'] = False plt.plot(x, y1) plt.plot(x, y2) plt.title("本市近30天温度情况") plt.xticks(rotation=45) plt.show()

# %% 包导入和全局设置 import pandas as pd import requests from bs4 import BeautifulSoup from matplotlib import pyplot as plt # 解决中文问题 plt.rcParams['font.sans-serif'] = ['SimHei'] # 解决负号显示问题 plt.rcParams['axes.unicode_minus'] = False # %% 数据爬取 def get_data(): """请求访问网页""" url = 'https://www.tianqi.com/ningbo/10/' headers = { 'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36 Edg/115.0.1901.183'} resp = requests.get(url, headers=headers) """读取并返回网页内容""" html = resp.content.decode('utf-8') soup = BeautifulSoup(html, 'html.parser') """查找网页中需要的天气数据""" ul = soup.body.find('ul', {'class': 'weaul'}) li_list = ul.find_all("li") dates, conditions, temp = [], [], [] for data in li_list: sub_data = data.text.split() print(sub_data) dates.append(sub_data[0]) conditions.append(sub_data[2]) temp.append(sub_data[3]) df = pd.DataFrame() df['日期'] = dates df['天气状况'] = conditions df['温度'] = temp return df weather = get_data() weather.to_csv("宁波天气（10天）.csv", index=False, encoding='utf-8', ) # %% 数据处理 data = pd.read_csv("宁波天气（10天）.csv") temps = data['温度'].str.split('~', expand=True) data['最低温度'] = temps[0] data['最高温度'] = temps[1].map(lambda x: int(x.replace('℃', ''))) print(data) # %% 数据可视化 dates = data['日期'] lows = data['最低温度'] highs = data['最高温度'] # 根据数据绘制图形 fig = plt.figure(dpi=128, figsize=(10, 6)) plt.plot(dates, lows, c='red', alpha=0.5) plt.plot(dates, highs, c='green', alpha=0.5) plt.title('宁波天气（10天）', fontsize=24) plt.xlabel('日期', fontsize=12) fig.autofmt_xdate() # 绘制斜的日期标签，以防重叠 plt.ylabel('温度', fontsize=12) plt.tick_params(axis='both', which='major', labelsize=10) plt.xticks(dates[::20]) plt.show()

"""爬取数据""" import pandas as pd import requests from bs4 import BeautifulSoup from matplotlib import pyplot as plt # 解决中文问题 plt.rcParams['font.sans-serif'] = ['SimHei'] # 解决负号显示问题 plt.rcParams['axes.unicode_minus'] = False def get_data(): """请求访问网页""" url = 'https://www.tianqi.com/hangzhou/10/' headers = { 'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/110.0.0.0 Safari/537.36'} resp = requests.get(url, headers=headers) """读取并返回网页内容""" html = resp.content.decode('utf-8') soup = BeautifulSoup(html, 'html.parser') """查找网页中需要的天气数据""" ul = soup.body.find('ul', {'class': 'weaul'}) li_list = ul.find_all("li") dates, conditions, temp = [], [], [] for data in li_list: sub_data = data.text.split() print(sub_data) dates.append(sub_data[0]) conditions.append(sub_data[2]) temp.append(sub_data[3]) df = pd.DataFrame() df['日期'] = dates df['天气状况'] = conditions df['温度'] = temp return df weather = get_data() weather.to_csv('杭州天气预报(10天).csv', index=False, encoding='utf-8') """数据可视化""" data = pd.read_csv('杭州天气预报(10天).csv') data['最低温度'] = data['温度'].str.split('~', expand=True)[0] data['最高温度'] = data['温度'].str.split('~', expand=True)[1] data['最高温度'] = data['最高温度'].map(lambda x: int(x.replace('℃', ''))) print(data) dates = data['日期'] lows = data['最低温度'] highs = data['最高温度'] # 根据数据绘制图形 fig = plt.figure(dpi=128, figsize=(10, 6)) plt.plot(dates, lows, c='red', alpha=0.5) plt.plot(dates, highs, c='green', alpha=0.5) plt.title('杭州天气预报(10天)', fontsize=24) plt.xlabel('日期', fontsize=12) fig.autofmt_xdate() # 绘制斜的日期标签，以防重叠 plt.ylabel('温度', fontsize=12) plt.tick_params(axis='both', which='major', labelsize=10) plt.xticks(dates[::20]) plt.show()

from openpyxl import Workbook from openpyxl.chart import ( ScatterChart, Reference, Series, LineChart, ) wb = Workbook() # grab the active worksheet ws = wb.active # 写入标题行 title = ["日期", "天气", "最高温度", "最低温度", "风级"] ws.append(title) # 写入数据 data = [ ['19日（今天）', '晴', 11, -1, '<3级'], ['20日（明天）', '多云', 7, 0, '3-4级'], ['21日（后天）', '阴转小雨', 10, 1, '4-5级转3-4级'], ['22日（周日）', '小雨转阴', 8, 4, '4-5级转<3级'], ['23日（周一）', '多云', 9, -2, '<3级转3-4级'], ['24日（周二）', '多云', 1, -6, '3-4级转<3级'], ['25日（周三）', '多云', 4, -5, '<3级'] ] for i in data: ws.append(i) # 画图 # chart = ScatterChart() # chart.title = "未来7天气温" # chart.style = 13 # chart.x_axis.title = '日期' # chart.y_axis.title = '温度' # xvalues = Reference(ws, min_col=1, min_row=2, max_row=8) # for i in range(3, 5): # values = Reference(ws, min_col=i, min_row=1, max_row=8) # series = Series(values, xvalues, title_from_data=True) # chart.series.append(series) # 画图 chart = LineChart() # 折线图 # x 坐标的数据，通常用一列数据作为,这里选择第一列 x_data=Reference(ws, min_col=1,min_row=2, max_col=1,max_row=ws.max_row ) # 数据收集，选择第3，4列作为数据画图 data=Reference(ws, min_col=3, min_row=1, max_col=4, max_row=ws.max_row,) # --------------------------------------------------- chart.add_data(data,from_rows=False,titles_from_data=True) # from_rows：如果是True表示将一行的数据作为一个条线，如果是False表示按列画 # titles_from_data：如果是True，表示每一组（根据from_rows确定是每一行还是每一列）数据的第一个作为title # -------------------------------------------------------------------------------- chart.set_categories(x_data) # 设置横坐标 chart.y_axis.title = '温度' # 设置y轴的名字 chart.x_axis.title = '日期' # 设置x轴的名字 chart.title='天气情况' ws.add_chart(chart, "A11") # Save the file wb.save("sample.xlsx")