file = open(filename, mode='r', encoding=None)

with open('example.txt', 'r', encoding='utf-8') as file:
    content = file.read()
# 文件會(huì)在with塊結(jié)束后自動(dòng)關(guān)閉

# 寫入文件
with open('data.txt', 'w', encoding='utf-8') as f:
    f.write('第一行內(nèi)容\n')
    f.write('第二行內(nèi)容\n')
    f.writelines(['第三行\(zhòng)n', '第四行\(zhòng)n'])

# 讀取文件
with open('data.txt', 'r', encoding='utf-8') as f:
    print(f.read())  # 讀取全部內(nèi)容
    f.seek(0)  # 重置文件指針到開頭
    print(f.readline())  # 讀取一行
    f.seek(0)
    print(f.readlines())  # 讀取所有行到列表

import csv

# 寫入CSV文件
data = [
    ['姓名', '年齡', '城市'],
    ['張三', 25, '北京'],
    ['李四', 30, '上海']
]

with open('people.csv', 'w', newline='', encoding='utf-8') as f:
    writer = csv.writer(f)
    writer.writerows(data)

# 讀取CSV文件
with open('people.csv', 'r', encoding='utf-8') as f:
    reader = csv.reader(f)
    for row in reader:
        print(row)

# 字典形式讀寫
with open('people_dict.csv', 'w', newline='', encoding='utf-8') as f:
    fieldnames = ['name', 'age', 'city']
    writer = csv.DictWriter(f, fieldnames=fieldnames)
    writer.writeheader()
    writer.writerow({'name': '王五', 'age': 28, 'city': '廣州'})

with open('people_dict.csv', 'r', encoding='utf-8') as f:
    reader = csv.DictReader(f)
    for row in reader:
        print(row['name'], row['age'])

import json

# Python對(duì)象轉(zhuǎn)JSON
data = {
    "name": "張三",
    "age": 25,
    "hobbies": ["讀書", "游泳"],
    "married": False
}

# 寫入JSON文件
with open('data.json', 'w', encoding='utf-8') as f:
    json.dump(data, f, ensure_ascii=False, indent=2)

# 讀取JSON文件
with open('data.json', 'r', encoding='utf-8') as f:
    loaded_data = json.load(f)
    print(loaded_data['name'])

from openpyxl import Workbook, load_workbook

# 創(chuàng)建Excel文件
wb = Workbook()
ws = wb.active
ws.title = "員工信息"

# 寫入數(shù)據(jù)
ws.append(['姓名', '部門', '工資'])
ws.append(['張三', '技術(shù)部', 15000])
ws.append(['李四', '市場部', 12000])

# 保存文件
wb.save('employees.xlsx')

# 讀取Excel文件
wb = load_workbook('employees.xlsx')
ws = wb.active

for row in ws.iter_rows(values_only=True):
    print(row)

import pandas as pd

# 從CSV創(chuàng)建DataFrame
df = pd.read_csv('people.csv')
print(df.head())

# 基本數(shù)據(jù)處理
print(df.describe())  # 統(tǒng)計(jì)描述
print(df.sort_values('年齡', ascending=False))  # 排序
print(df[df['年齡'] > 25])  # 條件篩選

# 數(shù)據(jù)清洗
df.dropna()  # 刪除空值
df.fillna(0)  # 填充空值
df['年齡'] = df['年齡'].astype(int)  # 類型轉(zhuǎn)換

# 保存處理結(jié)果
df.to_excel('processed_data.xlsx', index=False)

# 逐行處理大文本文件
with open('large_file.txt', 'r', encoding='utf-8') as f:
    for line in f:
        process_line(line)  # 自定義處理函數(shù)

# 分塊讀取大CSV文件
chunk_size = 10000
for chunk in pd.read_csv('large_data.csv', chunksize=chunk_size):
    process_chunk(chunk)

# 使用生成器處理數(shù)據(jù)
def read_large_file(file_path):
    with open(file_path, 'r', encoding='utf-8') as f:
        while True:
            data = f.read(1024)  # 每次讀取1KB
            if not data:
                break
            yield data

for chunk in read_large_file('very_large_file.txt'):
    process_chunk(chunk)

import os
from pathlib import Path

# 使用os模塊
print(os.listdir('.'))  # 列出當(dāng)前目錄文件
os.makedirs('new_dir', exist_ok=True)  # 創(chuàng)建目錄

# 使用更現(xiàn)代的pathlib
base_path = Path('.')
for file in base_path.glob('*.txt'):  # 查找所有txt文件
    print(file.name, file.stat().st_size)  # 文件名和大小

# 遞歸遍歷目錄
for root, dirs, files in os.walk('some_directory'):
    for file in files:
        print(os.path.join(root, file))

import zipfile
import gzip
import shutil

# ZIP文件處理
with zipfile.ZipFile('archive.zip', 'w') as zf:
    zf.write('file1.txt')
    zf.write('file2.txt')

with zipfile.ZipFile('archive.zip', 'r') as zf:
    zf.extractall('extracted_files')

# GZIP壓縮
with open('large_file.txt', 'rb') as f_in:
    with gzip.open('large_file.txt.gz', 'wb') as f_out:
        shutil.copyfileobj(f_in, f_out)

from io import StringIO, BytesIO

# 內(nèi)存文本文件
string_io = StringIO()
string_io.write('Hello ')
string_io.write('World!')
print(string_io.getvalue())  # Hello World!

# 內(nèi)存二進(jìn)制文件
bytes_io = BytesIO()
bytes_io.write(b'binary data')
print(bytes_io.getvalue())

import re
from collections import Counter

def analyze_logs(log_file):
    # 統(tǒng)計(jì)IP訪問次數(shù)
    ip_pattern = re.compile(r'\d{1,3}\.\d{1,3}\.\d{1,3}\.\d{1,3}')
    ip_counter = Counter()
    
    # 統(tǒng)計(jì)狀態(tài)碼
    status_pattern = re.compile(r'HTTP/1.\d" (\d{3})')
    status_counter = Counter()
    
    with open(log_file, 'r', encoding='utf-8') as f:
        for line in f:
            # 提取IP
            ip_match = ip_pattern.search(line)
            if ip_match:
                ip_counter[ip_match.group()] += 1
                
            # 提取狀態(tài)碼
            status_match = status_pattern.search(line)
            if status_match:
                status_counter[status_match.group(1)] += 1
    
    # 輸出結(jié)果
    print("Top 10 IPs:")
    for ip, count in ip_counter.most_common(10):
        print(f"{ip}: {count}次")
    
    print("\n狀態(tài)碼統(tǒng)計(jì):")
    for status, count in status_counter.most_common():
        print(f"{status}: {count}次")

# 使用示例
analyze_logs('web_server.log')