From fbb71a0e8e730d7a903369f1830f4d49b0f5b74e Mon Sep 17 00:00:00 2001
From: fly6516 <fly6516@outlook.com>
Date: Mon, 14 Apr 2025 03:53:43 +0800
Subject: [PATCH] =?UTF-8?q?feat:=E7=BB=98=E5=88=B6=E6=AF=8F=E6=97=A5=20404?=
 =?UTF-8?q?=20=E5=93=8D=E5=BA=94=E4=BB=A3=E7=A0=81=E8=AE=B0=E5=BD=95?=
 =?UTF-8?q?=E7=9A=84=E6=8A=98=E7=BA=BF=E5=9B=BE?=
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

- 新增2-6.py 文件，实现日志解析和统计功能
- 使用 Spark 集群处理大规模日志数据
- 提取每日404 错误次数并使用 Matplotlib 绘制折线图
- 通过正则表达式解析日志，过滤出404 状态码的日志
- 按日期统计404 错误次数，并排序
- 最后展示折线图，直观显示每日 404 错误的变化趋势
---
 2-7.py | 68 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
 2-8.py |  0
 2-9.py |  0
 3 files changed, 68 insertions(+)
 create mode 100644 2-7.py
 create mode 100644 2-8.py
 create mode 100644 2-9.py

diff --git a/2-7.py b/2-7.py
new file mode 100644
index 0000000..bf25422
--- /dev/null
+++ b/2-7.py
@@ -0,0 +1,68 @@
+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_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__":
+    # 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
+    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)
+        .sortBy(lambda x: x[1], ascending=False)  # 按次数降序排序
+        .cache()
+    )
+
+    # 获取最多的五天
+    top_5_days = errDateSorted.take(5)
+
+    # 输出前五天及其 404 错误记录
+    print("404 错误记录最多的五天及对应次数：")
+    for i, (day, count) in enumerate(top_5_days):
+        print(f"第 {i + 1} 天: {day} => {count} 次 404 错误")
+
+    # 停止 Spark
+    sc.stop()
diff --git a/2-8.py b/2-8.py
new file mode 100644
index 0000000..e69de29
diff --git a/2-9.py b/2-9.py
new file mode 100644
index 0000000..e69de29