如何使用Python腳本為站群創(chuàng)建蜘蛛統(tǒng)計(jì)和分析頁面？

import sys import pandas as pd  logfile = sys.argv[1] if len(sys.argv) > 1 else "Access.log"  # 讀取日志文件 with open(logfile) as f:     log_lines = f.readlines()  # 解析日志數(shù)據(jù) log_data = [] for line in log_lines:     parts = line.split()     if len(parts) > 10:         log_data.append({             "ip": parts[0],             "date": parts[3][1:],             "request": parts[5][1:],             "status": parts[8],             "agent": " ".join(parts[11:])         })  df = pd.DataFrame(log_data)  # 定義常用搜索引擎蜘蛛U(xiǎn)ser-Agent spider_agents = ["googlebot", "bingbot", "baiduspider", "yandexbot", "sogou"]  # 篩選蜘蛛訪問記錄 spider_df = df[df["agent"].str.contains("|".join(spider_agents))]  # 按蜘蛛類型和日期匯總統(tǒng)計(jì) spider_summary = spider_df.groupby(spider_df["agent"].str.extract("(" + "|".join(spider_agents) + ")", expand=False)).size().reset_index(name="count")  print(spider_summary)

python3 spider_analyzer.py access.log