62 lines
1.7 KiB
Python
62 lines
1.7 KiB
Python
import re
|
||
from pyspark import SparkContext
|
||
|
||
sc = SparkContext.getOrCreate()
|
||
|
||
LOG_PATTERN = re.compile(
|
||
r'^(\S+) (\S+) (\S+) \[([\w:/]+\s[+-]\d{4})\] "(\S+) (\S+)\s*(\S*)\s?" (\d{3}) (\S+)'
|
||
)
|
||
|
||
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
|
||
}
|
||
|
||
def extract_day(log):
|
||
# 时间格式为：10/Oct/2000:13:55:36 -0700
|
||
full_date = log['timestamp']
|
||
day = full_date.split('/')[0] # 只提取日
|
||
return day
|
||
|
||
if __name__ == "__main__":
|
||
logFile = "hdfs://master:9000/user/root/apache.access.log.PROJECT"
|
||
raw_logs = sc.textFile(logFile)
|
||
|
||
access_logs = raw_logs.map(parse_log_line).filter(lambda x: x is not None).cache()
|
||
|
||
# 过滤 404 状态码的日志
|
||
error_404_logs = access_logs.filter(lambda log: log['status_code'] == 404).cache()
|
||
|
||
# 每日 404 次数统计
|
||
errDateSorted = (
|
||
error_404_logs
|
||
.map(lambda log: (extract_day(log), 1))
|
||
.reduceByKey(lambda a, b: a + b)
|
||
.sortByKey(True)
|
||
.cache()
|
||
)
|
||
|
||
# 收集结果
|
||
daily_404_stats = errDateSorted.collect()
|
||
|
||
print("每天 404 错误记录数量：")
|
||
for day, count in daily_404_stats:
|
||
print("Day {}: {} 次 404 错误".format(day, count))
|
||
|
||
sc.stop()
|