Python开发之处理常见的txt、excel、csv文档

前言：主要是python处理数据常见的txt、excel、csv文件数据！

---

（一）txt文件处理

1.读取小文件

代码：

def read_small_txt():
    """读取小文件"""
    file_name = "data.txt"
    with open(file_name, "r", encoding="utf-8") as f:
        print(f.read())

2.按行读取大文件

代码：

def read_large_txt():
    """按行读取大文件"""
    file_name = "data.txt"
    file = open(file_name, "r", encoding="utf-8")
    for line in file:
        line = line.rstrip("\n")
        if isinstance(line, str) and line != "":
            print(line) #这里读取的数据可以进行字典或者元组或者list的转换，根据具体的文本形式
    file.close()

3.写文件

代码：

def write_txt():
    """写文件"""
    with open("data2.txt", 'w',encoding="utf-8") as f:
        f.write('Hello, python!')

4.追加写文件

多用于爬虫的时候或者从服务器获取很多的数据的时候，获取一行数据，保存一条数据。
代码：

def write_zhujia_txt():
    """追加写文件"""
    with open("data2.txt", "a+", encoding="utf-8") as f:
        f.write("我是追加的内容.........." + "\n")

5.具有一定格式的txt转换成excel文件

比如：

可以发现事每三行是一个类别。所以是可以转换成excel的
代码：

import pandas as pd

def txt_to_df(file_name):

    file = open(file_name, "r", encoding = "utf-8")
    df = pd.DataFrame() # 保存结果
    tmp_dict = dict()  # 当前行
    index = 0 # 计数, 3行一条记录
    for line in file:
        line = line.rstrip("\n")
        if isinstance(line, str) and line != "":
            tmp_dict["编号"] = 2018
            if index == 0:
                tmp_dict["项目名称"] = line
                index += 1
            elif index == 1:
                tmp_dict["合作单位"] = line
                index += 1
            elif index == 2:
                tmp_dict["主要完成人"] = line
                df = df.append(tmp_dict, ignore_index = True)
                index = 0
    return df


if __name__ == '__main__':

    df = txt_to_df("安徽省人民政府关于2015年度安徽省科学技术奖励的决定.txt")
    print(df)
    file_path = pd.ExcelWriter('安徽省人民政府关于2015年度安徽省科学技术奖励的决定.xlsx')
    df.to_excel(file_path, encoding='utf-8', index=False)
    file_path.save()
    pass

（二）excel文件处理

本次介绍主要使用pandas来处理文件，如果你对pandas不太熟悉，可以看看我的另外一个博客《Python开发之Pandas的简单使用（一）》
《Python开发之Pandas的简单使用（二）》
这里推荐一个人的博客《使用pandas读取excel》
data.xlsx的内容格式：

1.读取excel的单列数据，返回list

代码：

import pandas as pd

def read01_excel_data():
    """
    https://blog.csdn.net/weixin_38546295/article/details/83537558
    返回单列的list，用元组接收
    :return: 元组
    """
    file_path = "data.xlsx"
    df = pd.read_excel(file_path, sheet_name=0)
    title1_list = df['title1'].tolist()
    title2_list = df['title2'].tolist()
    title3_list = df['title3'].tolist()
    return title1_list, title2_list, title3_list

2.读取excel文件，返回list 元组数据

def read02_excel_data():
    """
    :return: [(),(),()]
    """
    file_path = "data.xlsx"
    df = pd.read_excel(file_path, sheet_name=0)
    title1_list = df['title1'].tolist()
    title2_list = df['title2'].tolist()
    title3_list = df['title3'].tolist()
    data_list = []
    for i,j,k in zip(title1_list,title2_list,title3_list):
        data_tup = (i,j,k)
        data_list.append(data_tup)

    return data_list

3.读取excel文件，返回list 字典数据

def read03_excel_data():
    """
    :return: [{},{},{}]
    """
    file_path = "data.xlsx"
    df = pd.read_excel(file_path, sheet_name=0)
    title1_list = df['title1'].tolist()
    title2_list = df['title2'].tolist()
    title3_list = df['title3'].tolist()
    data_list = []
    for i,j,k in zip(title1_list,title2_list,title3_list):
        data_dict = {"title1":i,"title2":j,"title3":k}
        data_list.append(data_dict)
    return data_list

4.list保存成excel文件（一）

def save_excel():
    data_df = pd.DataFrame()
    data_dict = {}
    for i in range(100):
        data_dict["标题1"] = "我是内容{}".format(i)
        data_df = data_df.append(data_dict, ignore_index=True)
    with pd.ExcelWriter("data2.xlsx") as w:
        data_df.to_excel(w, encoding="utf-8", index=False, sheet_name="sheet01")

5.list保存成excel文件（二）

def save2_excel():
    title = {'标题1': [], '标题2': []}
    for i in range(100):
        title['标题1'].append("我是标题1的{}".format(i))
        title['标题2'].append("我是标题2的{}".format(i))
    data_df = pd.DataFrame.from_dict(title)
    with pd.ExcelWriter("data3.xlsx") as w:
        data_df.to_excel(w, encoding="utf-8", index=False, sheet_name="sheet01")

（三）csv文件处理

csv文件内容形式：

1.csv文件的读取

代码：

import pandas as pd

def read_csv_data():
    df = pd.read_csv("data.csv")
    df = df["num1"].tolist()
    print(df)

2.list转存成csv文件

import pandas as pd

list = [[1, 2, 3], [4, 5, 6], [7, 9, 9]]
name = ['a', 'b', 'c']
test = pd.DataFrame(columns=name, data=list)  # 数据有三列，a,b,c
print(test)
test.to_csv('data.csv', encoding='utf-8')

---

再见！