python爬虫入门实战---------一周天气预报爬取_每天一个爬虫练习，爬取天气数据，适合新手...

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://www.tianqihoubao.com/lishi/huichang/month/201101.html')print('正在抓取2月份数据')

data_2_month= get_data('http://www.tianqihoubao.com/lishi/huichang/month/201102.html')print('正在抓取3月份数据')

data_3_month= get_data('http://www.tianqihoubao.com/lishi/huichang/month/201103.html')print('正在抓取4月份数据')

data_4_month= get_data('http://www.tianqihoubao.com/lishi/huichang/month/201104.html')print('正在抓取5月份数据')

data_5_month= get_data('http://www.tianqihoubao.com/lishi/huichang/month/201105.html')print('正在抓取6月份数据')

data_6_month= get_data('http://www.tianqihoubao.com/lishi/huichang/month/201106.html')print('正在抓取7月份数据')

data_7_month= get_data('http://www.tianqihoubao.com/lishi/huichang/month/201107.html')print('正在抓取8月份数据')

data_8_month= get_data('http://www.tianqihoubao.com/lishi/huichang/month/201108.html')print('正在抓取9月份数据')

data_9_month= get_data('http://www.tianqihoubao.com/lishi/huichang/month/201109.html')print('正在抓取10月份数据')

data_10_month= get_data('http://www.tianqihoubao.com/lishi/huichang/month/201110.html')print('正在抓取11月份数据')

data_11_month= get_data('http://www.tianqihoubao.com/lishi/huichang/month/201111.html')print('正在抓取12月份数据')

data_12_month= get_data('http://www.tianqihoubao.com/lishi/huichang/month/201112.html')print('数据抓取成功！正在整合该年数据，请稍后......')

time.sleep(3)

data= pd.concat([data_1_month, data_2_month, data_3_month, data_4_month, data_5_month, data_6_month, data_7_month, data_8_month, data_9_month, data_10_month, data_11_month, data_12_month]).reset_index(drop=True)print(data)print('数据整合完毕!')#数据爬取结果会保存在此代码同一径下