df = df.append(pd.read_html(url), ignore_index=True)
df.to_csv(‘NAB11.csv’,header=[‘RK’,’NAME’,’TEAM’,’SALARY’], index=False)
import pandas as pd
df = pd.DataFrame()
url_list = [‘http://www.espn.com/nba/salaries//seasontype/4′]
for i in range(2, 13):
url = ‘http://www.espn.com/nba/salaries//page/%s/seasontype/4′ % i
url_list.append(url)
遍历网页中的table读取网页表格数据
for url in url_list:
df = df.append(pd.read_html(url), ignore_index=True)
列表解析：遍历dataframe第3列，以子字符串$开头
df = df[[x.startswith(‘$’) for x in df[3]]]
df.to_csv(‘NAB11.csv’,header=[‘RK’,’NAME’,’TEAM’,’SALARY’], index=False)
import pandas as pd
aa =’./data/TB2018.xlsx’
df = pd.DataFrame(pd.read_excel(aa))
df1= df[[‘买家会员名’,’买家实际支付金额’]]
print(df1)
bb =’./data/000001.csv’
df = pd.read_csv(bb,encoding = ‘gbk’)
df1= df[[‘date’,’open’,’high’,’close’,’low’]]
df1.columns = [‘日期’,’开盘价’,’最高价’,’闭市价’,’最低价’]
print(df1)
print(‘———获取文本数据———–‘)
cc =’./data/fl4_name.txt’
df = pd.read_csv(cc,encoding=’gbk’)
print(df)
pd.set_option(‘display.max_columns’,500)
pd.set_option(‘display.width’,1000)
pd.set_option(‘display.unicode.ambiguous_as_wide’, True)
pd.set_option(‘display.unicode.east_asian_width’, True)
print(df.head(10))
Original: https://blog.csdn.net/s13596191285/article/details/125514254
Author: 荣华富贵8
Title: 程序员都无法理解的代码
原创文章受到原创版权保护。转载请注明出处：https://www.johngo689.com/675740/
转载文章受原作者版权保护。转载请注明原作者出处！