From 4747d647c766834151d51f7df1d4a88d05c42be8 Mon Sep 17 00:00:00 2001
From: fly6516 <fly6516@outlook.com>
Date: Mon, 14 Apr 2025 03:46:02 +0800
Subject: [PATCH] =?UTF-8?q?refactor(2-3.py):=20=E9=87=8D=E6=9E=84=E6=97=A5?=
 =?UTF-8?q?=E5=BF=97=E5=88=86=E6=9E=90=E4=BB=A3=E7=A0=81=E5=B9=B6=E6=8F=90?=
 =?UTF-8?q?=E5=8F=96=20404=20=E9=94=99=E8=AF=AF=E6=9C=80=E5=A4=9A=E7=9A=84?=
 =?UTF-8?q?=E7=AB=AF=E7=82=B9?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- 重命名变量和函数以提高代码可读性
- 修改日志解析逻辑，优化错误处理
- 提取状态码为 404 的日志并计算触发错误最多的端点
- 输出前 20个触发 404 错误最多的端点
---
 2-3.py | 24 ++++++++++++------------
 2-4.py | 58 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 70 insertions(+), 12 deletions(-)
 create mode 100644 2-4.py

diff --git a/2-3.py b/2-3.py
index 686ade0..b2d61a1 100644
--- a/2-3.py
+++ b/2-3.py
@@ -4,12 +4,12 @@ from pyspark import SparkContext
 # 初始化 SparkContext
 sc = SparkContext.getOrCreate()
 
-# 日志正则表达式
+# 日志匹配的正则表达式
 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
+# 解析日志的函数
 def parse_log_line(line):
     match = LOG_PATTERN.match(line)
     if not match:
@@ -35,24 +35,24 @@ if __name__ == "__main__":
     logFile = "hdfs://master:9000/user/root/apache.access.log.PROJECT"
     raw_logs = sc.textFile(logFile)
 
-    # 解析日志
+    # 解析并过滤有效日志
     access_logs = raw_logs.map(parse_log_line).filter(lambda x: x is not None).cache()
 
-    # 获取 404 错误日志
+    # 提取状态码为 404 的日志
     error_404_logs = access_logs.filter(lambda log: log['status_code'] == 404).cache()
 
-    # 获取前 25 个产生 404 错误最多的主机
-    top_25_404_hosts = (
+    # 计算触发 404 错误最多的端点
+    top_20_404_endpoints = (
         error_404_logs
-        .map(lambda log: (log['ip'], 1))
+        .map(lambda log: (log['endpoint'], 1))
         .reduceByKey(lambda a, b: a + b)
-        .takeOrdered(25, key=lambda x: -x[1])
+        .takeOrdered(20, key=lambda x: -x[1])
     )
 
-    # 打印结果
-    print("前 25 个产生 404 错误最多的主机：")
-    for i, (host, count) in enumerate(top_25_404_hosts):
-        print("{}: {} 次 404 错误".format(i + 1, host, count))
+    # 输出结果
+    print("前 20 个触发 404 错误最多的端点：")
+    for i, (endpoint, count) in enumerate(top_20_404_endpoints):
+        print("{}: {} => {} 次 404 错误".format(i + 1, endpoint, count))
 
     # 停止 Spark
     sc.stop()
diff --git a/2-4.py b/2-4.py
new file mode 100644
index 0000000..686ade0
--- /dev/null
+++ b/2-4.py
@@ -0,0 +1,58 @@
+import re
+from pyspark import SparkContext
+
+# 初始化 SparkContext
+sc = SparkContext.getOrCreate()
+
+# 日志正则表达式
+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__":
+    # 加载日志文件
+    logFile = "hdfs://master:9000/user/root/apache.access.log.PROJECT"
+    raw_logs = sc.textFile(logFile)
+
+    # 解析日志
+    access_logs = raw_logs.map(parse_log_line).filter(lambda x: x is not None).cache()
+
+    # 获取 404 错误日志
+    error_404_logs = access_logs.filter(lambda log: log['status_code'] == 404).cache()
+
+    # 获取前 25 个产生 404 错误最多的主机
+    top_25_404_hosts = (
+        error_404_logs
+        .map(lambda log: (log['ip'], 1))
+        .reduceByKey(lambda a, b: a + b)
+        .takeOrdered(25, key=lambda x: -x[1])
+    )
+
+    # 打印结果
+    print("前 25 个产生 404 错误最多的主机：")
+    for i, (host, count) in enumerate(top_25_404_hosts):
+        print("{}: {} 次 404 错误".format(i + 1, host, count))
+
+    # 停止 Spark
+    sc.stop()