feat: 添加日志解析和404 错误统计功能
- 新增日志解析函数 parse_log_line,用于解析 Apache 日志 - 添加过滤 404 错误的函数 filter_404 - 实现从 HDFS 读取日志、解析、过滤和统计 404 错误的完整流程- 打印 404 错误记录的数量
This commit is contained in:
parent
beb743f10d
commit
e556d97aca
54
2-2.py
Normal file
54
2-2.py
Normal file
@ -0,0 +1,54 @@
|
||||
import re
|
||||
from pyspark import SparkContext
|
||||
|
||||
# 初始化 SparkContext
|
||||
sc = SparkContext.getOrCreate()
|
||||
|
||||
# 正则表达式匹配日志格式
|
||||
LOG_PATTERN = re.compile(
|
||||
r'^(\S+) (\S+) (\S+) \[([\w:/]+\s[+-]\d{4})\] "(\S+) (\S+)\s*(\S*)\s?" (\d{3}) (\S+)'
|
||||
)
|
||||
|
||||
# 日志解析函数
|
||||
def parse_log_line(line):
|
||||
match = LOG_PATTERN.match(line)
|
||||
if not match:
|
||||
return None
|
||||
|
||||
content_size_str = match.group(9)
|
||||
content_size = int(content_size_str) if content_size_str.isdigit() else 0
|
||||
|
||||
return {
|
||||
'ip': match.group(1),
|
||||
'user_identity': match.group(2),
|
||||
'user_id': match.group(3),
|
||||
'timestamp': match.group(4),
|
||||
'method': match.group(5),
|
||||
'endpoint': match.group(6),
|
||||
'protocol': match.group(7),
|
||||
'status_code': int(match.group(8)),
|
||||
'content_size': content_size
|
||||
}
|
||||
|
||||
if __name__ == "__main__":
|
||||
# 读取日志文件
|
||||
logFile = "hdfs://master:9000/user/root/apache.access.log.PROJECT"
|
||||
raw_logs = sc.textFile(logFile)
|
||||
|
||||
# 解析日志并过滤掉解析失败的记录
|
||||
access_logs = raw_logs.map(parse_log_line).filter(lambda x: x is not None).cache()
|
||||
|
||||
# 创建只包含 404 错误日志的 RDD
|
||||
error_404_logs = access_logs.filter(lambda log: log['status_code'] == 404).cache()
|
||||
|
||||
# 获取最多 40 个不同的 endpoint
|
||||
unique_404_endpoints = error_404_logs.map(lambda log: log['endpoint']).distinct()
|
||||
top_40_endpoints = unique_404_endpoints.take(40)
|
||||
|
||||
# 输出结果
|
||||
print("最多 40 个不同的 404 错误端点:")
|
||||
for i, ep in enumerate(top_40_endpoints):
|
||||
print("{}: {}".format(i + 1, ep))
|
||||
|
||||
# 停止 SparkContext
|
||||
sc.stop()
|
Loading…
Reference in New Issue
Block a user