使用Python统计网站访问流量

pip install Flask

from flask import Flask, request
 
app = Flask(__name__)
 
@app.route('/')
def home():
    return "欢迎访问我们的网站！"
 
if __name__ == '__main__':
    app.run(debug=True)

import logging
from datetime import datetime
from flask import Flask, request
 
app = Flask(__name__)
 
# 设置日志格式
logging.basicConfig(filename='access.log', level=logging.INFO, format='%(asctime)s - %(message)s')
 
@app.before_request
def log_request_info():
    # 记录请求的时间、IP地址、请求的方法和路径
    now = datetime.now().strftime("%Y-%m-%d %H:%M:%S")
    ip = request.remote_addr
    method = request.method
    path = request.path
    logging.info(f'{now} - {ip} - {method} - {path}')
 
@app.route('/')
def home():
    return "欢迎访问我们的网站！"
 
if __name__ == '__main__':
    app.run(debug=True)

from collections import Counter
import re
 
# 读取日志文件
with open('access.log', 'r') as file:
    logs = file.readlines()
 
# 提取日期并计数
dates = [re.match(r'(\d{4}-\d{2}-\d{2})', log).group(1) for log in logs]
date_counts = Counter(dates)
 
# 打印结果
for date, count in date_counts.items():
    print(f"{date}: {count} 次访问")

pip install Flask

from flask import Flask, request
import logging
from datetime import datetime
 
# 创建Flask应用
app = Flask(__name__)
 
# 配置日志
logging.basicConfig(filename='access.log', level=logging.INFO, format='%(asctime)s - %(message)s')
 
@app.route('/')
def home():
    log_request(request)
    return "欢迎访问我们的网站！"
 
@app.route('/about')
def about():
    log_request(request)
    return "关于我们"
 
@app.route('/contact')
def contact():
    log_request(request)
    return "联系我们"
 
def log_request(req):
    # 获取请求信息
    remote_addr = req.remote_addr
    path = req.path
    timestamp = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
    
    # 记录日志
    logging.info(f"访问者IP: {remote_addr}, 请求路径: {path}, 时间: {timestamp}")
 
if __name__ == '__main__':
    app.run(debug=True)

python app.py

from flask import Flask, request
 
app = Flask(__name__)
 
@app.before_request
def before_request():
    # 记录请求的时间戳
    request.start_time = time.time()
 
@app.after_request
def after_request(response):
    # 获取请求时间
    duration = time.time() - request.start_time
    # 记录访问日志
    log_entry = f"{request.remote_addr} - {request.method} {request.url} - {response.status_code} - {duration:.2f}s"
    print(log_entry)  # 这里可以选择将日志写入文件或数据库
    return response
 
@app.route('/')
def home():
    return "Hello, World!"
 
if __name__ == '__main__':
    app.run(debug=True)

import re
 
def parse_log_file(file_path):
    pattern = r'(\d+\.\d+\.\d+\.\d+) - (\w+) (\S+) - (\d+) - (\d+\.\d+)s'
    with open(file_path, 'r') as file:
        for line in file:
            match = re.match(pattern, line)
            if match:
                ip, method, url, status_code, duration = match.groups()
                yield {
                    'ip': ip,
                    'method': method,
                    'url': url,
                    'status_code': int(status_code),
                    'duration': float(duration)
                }
 
# 示例：统计每个URL的访问次数
from collections import Counter
 
log_entries = list(parse_log_file('access.log'))
url_counter = Counter(entry['url'] for entry in log_entries)
 
for url, count in url_counter.most_common(10):
    print(f"URL: {url}, 访问次数: {count}")

import matplotlib.pyplot as plt
 
# 假设我们已经有了按URL分组的访问次数
urls, counts = zip(*url_counter.most_common(10))
 
plt.figure(figsize=(10, 5))
plt.bar(urls, counts)
plt.xlabel('URL')
plt.ylabel('访问次数')
plt.title('Top 10 最常访问的URL')
plt.xticks(rotation=45)
plt.tight_layout()
plt.show()