Python爬取7天天气

需要的包

• requests
• BeautifulSoup
• openpyxl

安装包

• 安装命令

pip install [包名]

代码演示

• 第一部分：爬取文件，写入excel表格

#爬虫获取天气

#导包
import datetime;
import  requests;
from bs4 import BeautifulSoup as bs;
from openpyxl import Workbook;
import re;

#获取网页：101181701为三门峡的代码
url='http://www.weather.com.cn/weather/101181701.shtml';
header={
    #从浏览器找的ua
    'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/101.0.0.0 Safari/537.36'
}

response=requests.get(url=url,headers=header);
#查看访问情况
print(response.status_code);

#设置文本格式
response.encoding=response.apparent_encoding;
html_doc=response.text;
#测试输出
#print(html_doc);

soup=bs(html_doc,'html.parser');

weather_data_list=soup.find_all('p',class_='tem');
#print(weather_data_list);

#获取今天最高温：最高温有时候会没有，用明天最高温代替
tagToday=soup.find('p',class_="tem")
try:
    temperatureHigh = tagToday.span.string
except   AttributeError  as  e:
    temperatureHigh =\
    tagToday.find_next('p',class_="tem").span.string

print(f"今天最高温度：{temperatureHigh}");

#创建7天日期列表
tem_list=[];
now = datetime.datetime.now();

#取数字正则表达式
reg_digital='\-?\d+\.?\d*'
today_high_temper=re.findall(reg_digital,temperatureHigh);
today_low_temper=re.findall(reg_digital,tagToday.i.string);
#添加今天温度
tem_list.append((now.strftime("%Y-%m-%d"),int(today_high_temper[0]),int(today_low_temper[0])));
print(tem_list);

#日期
date=now;

#添加后面七天的数据,得到七天的数据列表
for weather_data in weather_data_list[1:7]:
    #print(weather_data.i.string);
    date = date + datetime.timedelta(days=1)
    high_digital=re.findall(reg_digital,weather_data.span.string);
    low_digital=re.findall(reg_digital,weather_data.i.string);
    tem_list.append((date.strftime("%Y-%m-%d"),int(high_digital[0]),int(low_digital[0])));

print(tem_list);

#首标题和表头
wb=Workbook();
date_high_low=wb.active;
date_high_low.title=("7天日期统计分析");

date_high_low.append(["日期","最高温","最低温"]);
for row in tem_list:
    date_high_low.append(row);

wb.save("temper.xlsx");

• 第二部分：读取excel表格，画折线图

#图表可视化
#导包
from openpyxl import load_workbook
from openpyxl.chart import LineChart, Reference;

#加载文件
wb = load_workbook("temper.xlsx");
#加载sheet
ws=wb["7天日期统计分析"];

#日期
date_line=Reference(ws,min_col=1,min_row=2,max_row=8);

#高温低温数据
temper_data=Reference(ws,min_col=2,max_col=3,min_row=2,max_row=8);

chart=LineChart();
chart.title="7天气温统计分析";
chart.x_axis.title="日期";
chart.y_axis.title="温度";

chart.add_data(temper_data);

chart.set_categories(date_line);
chart.legend = None;
line_style = chart.series[0];
line_style.smooth = False;
ws.add_chart(chart, "D2");
wb.save("line.xlsx");

最终效果

• 效果演示图