【愚公系列】《Python网络爬虫从入门到精通》037-文件的存取

file = open(filename, mode='r', buffering=-1)

import requests     # 导入网络请求模块
from bs4 import BeautifulSoup  # html解析库

url = 'http://quotes.toscrape.com/tag/inspirational/'   # 定义请求地址
headers = {'User-Agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36'}
response = requests.get(url,headers)   # 发送网络请求
if response.status_code==200:   # 如果请求成功
    #创建一个BeautifulSoup对象，获取页面正文
    soup = BeautifulSoup(response.text, features="lxml")
    text_all = soup.find_all('span',class_='text')   # 获取所有显示励志名句的span标签
    txt_file = open('data.txt','w',encoding='utf-8') # 创建open对象
    for i,value in enumerate(text_all):              # 循环遍历爬取内容
        txt_file.write(str(i)+value.text+'\n')       # 写入每条爬取的励志名句并在结尾换行
    txt_file.close()                                 # 关闭文件操作

with open('message.txt', 'r', encoding='utf-8') as f:
    content = f.read(9)  # 读取前9个字符
print(content)  # 输出：Python的强

with open('message.txt', 'r', encoding='utf-8') as f:
    f.seek(11)  # 跳过前11个字节（汉字占2字节）
    part = f.read(8)  # 读取后续8字符
print(part)  # 输出：大到你无法

print("\n","="*20,"Python经典应用","="*20,"\n")
with open('message.txt','r') as file:   # 打开保存Python经典应用信息的文件
    number = 0   # 记录行号
    while True:
        number += 1
        line = file.readline()
        if line =='':
            break    # 跳出循环
        print(number,line,end= "\n")  # 输出一行内容
print("\n","="*20,"over","="*20,"\n")

print("\n","="*20,"Python经典应用","="*20,"\n")
with open('message.txt','r') as file:      # 打开保存Python经典应用信息的文件
    message = file.readlines()              # 读取全部信息
    print(message)                           # 输出信息
    print("\n","="*25,"over","="*25,"\n")

with open('big_data.txt') as f:
    for line in f:  # 内存友好的逐行读取
        process(line)

import csv

# TXT转CSV
with open('data.txt', 'r') as txt_file, open('data.csv', 'w') as csv_file:
    writer = csv.writer(csv_file)
    for line in txt_file:
        writer.writerow([line.strip()])

df.to_csv(
    path_or_buf=None,   # 文件路径/缓冲区对象
    sep=',',            # 分隔符（默认逗号）
    na_rep='',          # 缺失值占位符
    float_format=None,  # 浮点数格式（如"%.2f"）
    columns=None,       # 指定存储列
    header=True,        # 是否包含列名
    index=True,         # 是否保留行索引
    mode='w',           # 写入模式（'w'覆盖/'a'追加）
    encoding=None,      # 文件编码（推荐'utf-8-sig'）
    line_terminator='\n'# 换行符
)

import pandas as pd

data = {'A': [1,2,3], 'B': [4,5,6], 'C': [7,8,9]}
df = pd.DataFrame(data)

# 基础存储
df.to_csv('basic.csv')  

# 进阶设置（无索引/指定列/自定义分隔符）
df.to_csv('advance.csv', 
          index=False, 
          columns=['A','C'], 
          sep='|',
          float_format="%.1f")

df.to_excel(
    excel_writer,        # 文件路径/ExcelWriter对象
    sheet_name='Sheet1', # 工作表名称
    na_rep='',           # 缺失值占位符
    float_format=None,   # 浮点数格式化
    columns=None,        # 指定存储列
    header=True,         # 保留列名
    index=True,          # 保留行索引
    startrow=0,          # 起始行（从0开始）
    startcol=0,          # 起始列（从0开始）
    engine=None          # 写入引擎（'openpyxl'/'xlsxwriter'）
)

import pandas as pd

data = {
    '编号': ['mr001','mr002','mr003','mr004'],
    '体育': [34.5,33,35,39],
    '语文': [110,110,105,108],
    '数学': [108,110,105,101],
    '英语': [99,110,101,112]
}
df = pd.DataFrame(data)

# 基础存储
df.to_excel('basic.xlsx')  

# 进阶设置（指定位置/去除索引）
df.to_excel('advance.xlsx', 
           sheet_name='成绩表',
           index=False,
           startrow=1,
           startcol=1)

# CSV保留两位小数
df.to_csv('data.csv', float_format="%.2f")

# Excel科学计数法显示
df.to_excel('data.xlsx', float_format="%.2E")

# CSV文件解决中文乱码
df.to_csv('中文数据.csv', encoding='utf-8-sig')

# Excel文件指定编码
with pd.ExcelWriter('中文数据.xlsx', engine='openpyxl') as writer:
    df.to_excel(writer, encoding='utf-8')

with pd.ExcelWriter('multi_sheet.xlsx') as writer:
    df1.to_excel(writer, sheet_name='Sheet1')
    df2.to_excel(writer, sheet_name='Sheet2')