web-analyze/2-1.py

48 lines
1.4 KiB
Python
Raw Permalink Normal View History

import re
from pyspark import SparkContext
sc = SparkContext.getOrCreate()
logFile = "hdfs://master:9000/user/root/apache.access.log.PROJECT"
raw_logs = sc.textFile(logFile)
# 日志模式
LOG_PATTERN = re.compile(r'^(\S+) (\S+) (\S+) \[([\w:/]+\s[+-]\d{4})\] "(\S+) (\S+)\s*(\S*)\s?" (\d{3}) (\S+)')
# 解析日志
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
}
# 过滤出包含 404 响应代码的日志
def filter_404(log):
return log['status_code'] == 404
# 解析并过滤日志
parsed_logs = raw_logs.map(parse_log_line).filter(lambda x: x is not None)
# 过滤出 404 错误记录并缓存
error_404_logs = parsed_logs.filter(filter_404).cache()
# 统计 404 错误数量
count_404 = error_404_logs.count()
# 打印结果(使用 .format 替代 f-string
print("日志中共有 {} 条 404 响应代码记录。".format(count_404))
sc.stop()