From d0d58e7d4bc49c59bed395503e21ec932a49ecaa Mon Sep 17 00:00:00 2001
From: fly6516 <fly6516@outlook.com>
Date: Mon, 14 Apr 2025 03:57:15 +0800
Subject: [PATCH] =?UTF-8?q?feat:=20=E6=B7=BB=E5=8A=A0=202-8.py=20=E6=96=87?=
 =?UTF-8?q?=E4=BB=B6=E5=B9=B6=E5=AE=9E=E7=8E=B0=E6=AF=8F=E5=B0=8F=E6=97=B6?=
 =?UTF-8?q?=20404=20=E9=94=99=E8=AF=AF=E7=BB=9F=E8=AE=A1?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- 新增 2-8.py 文件，实现从日志文件中解析和统计每小时的 404 错误数量
- 使用 Spark 进行日志处理和分析
- 添加日志解析函数和提取小时函数
- 实现从 HDFS 读取日志数据并进行过滤和聚合
- 最后输出每小时的 404 错误数量
---
 2-8.py | 66 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 66 insertions(+)

diff --git a/2-8.py b/2-8.py
index e69de29..b167bbf 100644
--- a/2-8.py
+++ b/2-8.py
@@ -0,0 +1,66 @@
+import re
+from pyspark import SparkContext
+
+# 初始化 SparkContext
+sc = SparkContext.getOrCreate()
+
+# 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+)'
+)
+
+# 解析日志的函数
+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
+    }
+
+def extract_hour(log):
+    # 时间格式为：10/Oct/2000:13:55:36 -0700
+    full_date = log['timestamp']
+    hour = full_date.split(':')[1]  # 提取小时
+    return hour
+
+if __name__ == "__main__":
+    # 加载日志文件
+    logFile = "hdfs://master:9000/user/root/apache.access.log.PROJECT"
+    raw_logs = sc.textFile(logFile)
+
+    # 解析并过滤有效日志
+    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
+    badRecords = access_logs.filter(lambda log: log['status_code'] == 404).cache()
+
+    # 每小时 404 错误次数统计
+    hourRecorded = (
+        badRecords
+        .map(lambda log: (extract_hour(log), 1))
+        .reduceByKey(lambda a, b: a + b)
+        .sortByKey()  # 按小时顺序排序
+        .cache()
+    )
+
+    # 获取结果并打印
+    result = hourRecorded.collect()
+    print("每小时的 404 错误数量：")
+    for hour, count in result:
+        print("小时 {}: {} 次 404 错误".format(hour, count))
+
+    # 停止 Spark
+    sc.stop()