importrequestsfrom bs4 importBeautifulSoupimportpandas as pdimporttimedefget_data(url):
resp=requests.get(url)
html= resp.content.decode('gbk')
soup= BeautifulSoup(html, 'html.parser')
tr_list= soup.find_all('tr')
dates, conditions, tempmin, tempmax=[], [], [], []for data in tr_list[1:]:
sub_data=data.text.split()
dates.append(sub_data[0])
conditions.append(''.join(sub_data[1:3]))
tempmax.append(sub_data[3])
tempmin.append(sub_data[5])
_data=pd.DataFrame()
_data["日期"] =dates
_data['天气状况'] =conditions
_data['最高气温'] =tempmax
_data['最低气温'] =tempminreturn_data#data_1_month = get_data('此处为任一月份数据的网址') 使用时只需修改此处,具体示例如下
print('正在抓取1月份数据')
data_1_month= get_data('http:/