import re

# 最簡單的例子：在字符串中查找 'hello'
text = "world hello python"
pattern = "hello"

# re.search() 掃描整個字符串，返回第一個匹配的Match對象
match = re.search(pattern, text)
if match:
    print(f"Found '{match.group()}' at position {match.start()} to {match.end()}")
# 輸出: Found 'hello' at position 6 to 11

import re

def validate_username(username):
    pattern = r'^[a-zA-Z]\w{3,15}$'
    # ^[a-zA-Z]   : 必須以字母開頭
    # \w{3,15}    : 后面跟3到15個單詞字符（總長度就是4-16）
    # $           : 必須以此結尾
    if re.fullmatch(pattern, username): # fullmatch確保整個字符串匹配模式
        return True
    else:
        return False

print(validate_username("Alice123"))    # True
print(validate_username("alice"))       # True (長度4)
print(validate_username("23alice"))     # False (數(shù)字開頭)
print(validate_username("a"))           # False (太短)
print(validate_username("alice!#"))     # False (包含非法字符)

text = "The price is 100 dollars"

print(re.match(r'\d+', text))    # None (開頭不是數(shù)字)
print(re.search(r'\d+', text))   # <re.Match object; span=(12, 15), match='100'>

text = "Apple: $1.99, Banana: $0.50, Orange: $2.00"

# 提取所有價格
prices = re.findall(r'\$\d+\.\d\d', text) # \.$ 轉義，匹配真正的美元符號
print(prices)  # ['$1.99', '$0.50', '$2.00']

# 使用finditer獲取更多信息（如位置）
for match in re.finditer(r'\$\d+\.\d\d', text):
    print(f"Found {match.group()} at {match.span()}")
# Found $1.99 at (7, 12)
# Found $0.50 at (23, 28)
# Found $2.00 at (38, 43)

text = "Today is 2023-10-27. The meeting is on 2023-11-01."

# 將日期格式從 YYYY-MM-DD 改為 DD/MM/YYYY
# 使用分組 \1, \2, \3 來引用前面匹配的內容
new_text = re.sub(r'(\d{4})-(\d{2})-(\d{2})', r'\3/\2/\1', text)
print(new_text) # Today is 27/10/2023. The meeting is on 01/11/2023.

# 使用函數(shù)進行更復雜的替換（將所有年份加1）
def add_one_year(match_obj):
    year = int(match_obj.group(1))
    month = match_obj.group(2)
    day = match_obj.group(3)
    return f"{day}/{month}/{year + 1}" # 返回要替換成的字符串

new_text_func = re.sub(r'(\d{4})-(\d{2})-(\d{2})', add_one_year, text)
print(new_text_func) # Today is 27/10/2024. The meeting is on 01/11/2024.

import re

# 未編譯模式，每次調用都要解釋一遍模式
result1 = re.findall(r'\d+', text1)
result2 = re.findall(r'\d+', text2)

# 編譯模式，只需解釋一次
pattern_obj = re.compile(r'\d+') # 返回一個Pattern對象
result1 = pattern_obj.findall(text1)
result2 = pattern_obj.findall(text2)

# 編譯后的對象擁有所有re模塊的方法：search, match, findall, sub等

text = "https://www.example.com http://blog.example.org"

# 只想捕獲域名，不需要協(xié)議這個分組
# 使用 (?:...) 表示非捕獲分組
domains = re.findall(r'(?:https?://)(\w+\.\w+\.\w+)', text)
print(domains) # ['www.example.com', 'blog.example.org']

# 對比捕獲分組，結果會包含協(xié)議
domains_with_protocol = re.findall(r'(https?://)(\w+\.\w+\.\w+)', text)
print(domains_with_protocol) # [('https://', 'www.example.com'), ('http://', 'blog.example.org')]

html_text = "<title>Python Regular Expressions</title> <div>Content</div>"

# 貪婪匹配：.* 會匹配到最后一個 > 之前的所有字符
greedy_match = re.search(r'<.*>', html_text)
print(greedy_match.group()) # <title>Python Regular Expressions</title> <div>Content</div>

# 非貪婪匹配：.*? 在遇到第一個 > 后就停止匹配
non_greedy_match = re.search(r'<.*?>', html_text)
print(non_greedy_match.group()) # <title>

# 提取后面跟著 " dollars" 的數(shù)字
text = "100 dollars, 200 euros, 300 dollars"
dollars = re.findall(r'\d+(?=\s*dollars)', text) # 只匹配數(shù)字，不匹配后面的“dollars”
print(dollars) # ['100', '300']

# 提取前面是 "$" 的數(shù)字
text = "The prices are $100, €200, and $300."
prices = re.findall(r'(?<=\$)\d+', text) # 只匹配數(shù)字，不匹配前面的“$”
print(prices) # ['100', '300']

# 匹配一個不在單詞中間的連字符（即單詞邊界處的連字符）
text = "multi-purpose and well-known, but not abc-123"
hyphens = re.findall(r'(?<=\w)-(?=\w)', text) # 前面是單詞字符，后面也是單詞字符的連字符
print(hyphens) # ['-', '-']  (匹配到 purpose和known中的連字符，但沒匹配abc-123，因為123不是單詞字符\w)

# nginx_log_analyzer.py
import re
from collections import Counter, defaultdict
from pathlib import Path

def analyze_nginx_log(log_path):
    """
    分析Nginx訪問日志
    """
    # 使用編譯正則表達式提高效率
    # 分解日志行的正則模式
    log_pattern = re.compile(
        r'(?P<ip>\d+\.\d+\.\d+\.\d+)'          # IP地址
        r' - - '                               # 忽略的標識
        r'\[(?P<time>.*?)\]'                   # 時間戳
        r' "(?P<request>.*?)"'                 # 請求行 (GET /url HTTP/1.1)
        r' (?P<status>\d{3})'                  # 狀態(tài)碼
        r' (?P<size>\d+)'                      # 響應大小
        r' "(?P<referer>.*?)"'                 # 來源頁
        r' "(?P<agent>.*?)"'                   # User-Agent
    )

    # 用于統(tǒng)計的數(shù)據(jù)結構
    ip_counter = Counter()          # IP訪問次數(shù) (PV)
    status_counter = Counter()      # 狀態(tài)碼出現(xiàn)次數(shù)
    url_counter = Counter()         # 請求URL出現(xiàn)次數(shù)
    # 使用 defaultdict(set) 來記錄每個IP對應的唯一User-Agent
    ip_ua_dict = defaultdict(set)   # key: ip, value: set(user_agent1, user_agent2...)

    try:
        with open(log_path, 'r', encoding='utf-8') as f:
            for line in f:
                match = log_pattern.search(line)
                if not match:
                    # 跳過無法識別的行
                    continue

                # 從匹配結果中提取數(shù)據(jù)
                data = match.groupdict()
                ip = data['ip']
                status = data['status']
                request = data['request']
                user_agent = data['agent']

                # 1. 統(tǒng)計IP PV
                ip_counter[ip] += 1

                # 2. 記錄IP和User-Agent（用于估算UV）
                ip_ua_dict[ip].add(user_agent) # 使用set自動去重

                # 3. 統(tǒng)計狀態(tài)碼
                status_counter[status] += 1

                # 4. 從請求行中提取URL（簡單處理，提取第一個單詞后的部分）
                parts = request.split()
                if len(parts) >= 2:
                    url = parts[1] # 例如 "/articles/python.html"
                    url_counter[url] += 1

    except FileNotFoundError:
        print(f"Error: File {log_path} not found.")
        return

    # --- 輸出分析報告 ---
    print("=" * 50)
    print("Nginx Log Analysis Report")
    print("=" * 50)

    print(f"\n1. Top 10 IP Addresses by Page Views (PV):")
    for ip, count in ip_counter.most_common(10):
        print(f"   {ip:15} : {count:4}")

    print(f"\n2. Estimated Unique Visitors (UV) per IP (by unique User-Agent):")
    # 計算每個IP的UV（即其唯一User-Agent集合的大小）
    ip_uv = {ip: len(ua_set) for ip, ua_set in ip_ua_dict.items()}
    for ip, uv_count in sorted(ip_uv.items(), key=lambda x: x[1], reverse=True)[:10]:
        print(f"   {ip:15} : {uv_count:4} (PV: {ip_counter[ip]})")

    print(f"\n3. HTTP Status Code Distribution:")
    for status, count in status_counter.most_common():
        print(f"   {status} : {count}")

    print(f"\n4. Top 10 Most Frequently Requested URLs:")
    for url, count in url_counter.most_common(10):
        print(f"   {count:4} : {url}")

if __name__ == "__main__":
    log_file = "access.log"  # 替換為你的日志文件路徑
    analyze_nginx_log(log_file)