python脚本处理常用 -持续更新

文件操作

input_path = ""
output_path = ""

with open(input_path, 'r') as infile:
    for line in infile:
        xxx

with open(input_path, 'r') as infile, with open(output_path, 'w') as outfile:
    for line in infile:
        xxx
        outfile.write(line)

字符串处理

line = "this is a string:line"

# 删除字符串前后的字符，默认空格，读取txt文件每行常用
line = line.strip()

# split分割字符串
# 用:分割字符串后得到一个list列表，可用index取内容
line = line.split(':')[1]

# replace替换
line = line.replace("line", "newline")
line = line.replace(line.split(':')[1], "newline")

# 正则表达式，安装re库
# ^是固定开头的，$是固定结尾的，.表示不定数量字符，*表示任意字符，.*不定量任意字符
pattern = r''
pattern = r'^this.*line$'

if re.match(pattern, ) != -1 :
    xxx

pandas库处理excel文件

import pandas as pd

input_path = "xxx.xlsx"
df = pd.read_excel(input_path, sheet_name = "Sheet2")
for index, row in df.iterrows():
    print(row)
    print(row[0], row[1])
    print(row["column1"], row["column2"])