Python: التعبيرات العادية

import re

# أبسط تعبير عادي: طابق سلسلة مباشرة
pattern = r"hello"
text = "hello world"

result = re.search(pattern, text)
if result:
    print("Found!")                 # Found!
    print(result.group())           # hello
    print(result.start())           # 0 (موضع البداية)
    print(result.end())             # 5 (موضع النهاية)

import re

text = "My email is alice@example.com, also bob@test.com"

# search() — ابحث عن أول تطابق
result = re.search(r"\w+@\w+\.\w+", text)
print(result.group())               # alice@example.com

# findall() — ابحث عن جميع التطابقات
emails = re.findall(r"\w+@\w+\.\w+", text)
print(emails)                       # ['alice@example.com', 'bob@test.com']

# match() — طابق من البداية
print(re.match(r"My", text))        # تطابق (في البداية)
print(re.match(r"email", text))     # None (ليس في البداية)

# sub() — استبدال
masked = re.sub(r"\w+@", "***@", text)
print(masked)                       # My email is ***@example.com, also ***@test.com

import re

def is_valid_phone(phone):
    """تحقق من رقم هاتف محمول صيني (11 رقماً، يبدأ بـ 1)"""
    pattern = r"^1[3-9]\d{9}$"
    return bool(re.match(pattern, phone))

phones = ["13800138000", "12345678901", "010-12345678", "1380013800a"]
for p in phones:
    print(f"{p}: {'✅' if is_valid_phone(p) else '❌'}")

# استخرج جميع أرقام الهواتف من النص
text = "Contact: 13800138000, backup: 13912345678, landline: 010-12345678"
phones = re.findall(r"1[3-9]\d{9}", text)
print(f"Found phones: {phones}")

# Function defined successfully

import re

# استخرج اسم المستخدم والنطاق من البريد الإلكتروني
email = "alice@example.com"
pattern = r"(\w+)@(\w+\.\w+)"
result = re.search(pattern, email)

if result:
    print(f"Full match: {result.group(0)}")    # alice@example.com
    print(f"Username: {result.group(1)}")      # alice
    print(f"Domain: {result.group(2)}")        # example.com

# استخرج معلومات من سجل
log = "2026-06-23 15:30:45 ERROR Database connection timeout"
pattern = r"(\d{4}-\d{2}-\d{2}) (\d{2}:\d{2}:\d{2}) (\w+) (.+)"
result = re.search(pattern, log)
print(f"Date: {result.group(1)}")           # 2026-06-23
print(f"Time: {result.group(2)}")           # 15:30:45
print(f"Level: {result.group(3)}")          # ERROR
print(f"Message: {result.group(4)}")        # Database connection timeout

import re

def parse_url(url):
    """حلل URL لاستخراج البروتوكول والنطاق والمسار ومعاملات الاستعلام"""
    pattern = r"(https?)://([^/]+)(/[^?]*)?(?:\?([^#]*))?"
    result = re.search(pattern, url)
    if not result:
        return None
    
    return {
        "protocol": result.group(1),
        "domain": result.group(2),
        "path": result.group(3) or "/",
        "query": result.group(4) or ""
    }

urls = [
    "https://www.example.com/path/page.html?id=123&name=test",
    "http://localhost:8080/api/users",
    "https://google.com"
]

for url in urls:
    info = parse_url(url)
    if info:
        print(f"\nURL: {url}")
        for key, value in info.items():
            print(f"  {key}: {value}")

# Function defined successfully

import re

text = "User Alice's phone is 13800138000, email is alice@example.com, ID 110101199001011234"

phone_masked = re.sub(r"(1[3-9]\d)\d{4}(\d{4})", r"\1****\2", text)
print(f"Phone masked: {phone_masked}")

email_masked = re.sub(r"(\w{2})\w+(@\w+\.\w+)", r"\1***\2", text)
print(f"Email masked: {email_masked}")

id_masked = re.sub(r"(\d{4})\d{10}(\d{4})", r"\1**********\2", text)
print(f"ID masked: {id_masked}")

template = "Hello, {name}! Order {order_id} has been shipped."
data = {"name": "Alice", "order_id": "ORD2024001"}
result = re.sub(r"\{(\w+)\}", lambda m: data.get(m.group(1), m.group(0)), template)
print(f"Template result: {result}")

Phone masked: User Alice's phone is 138****8000, email is alice@example.com, ID 110101199001011234
Email masked: User Alice's phone is 13800138000, email is al***@example.com, ID 110101199001011234
ID masked: User Alice's phone is 13800138000, email is alice@example.com, ID 1101**********1234
Template result: Hello, Alice! Order ORD2024001 has been shipped.

import re

text = "<h1>Title</h1><p>Paragraph</p>"

# الوضع الجشع — يطابق أكبر قدر ممكن
greedy = re.search(r"<.+>", text)
print(greedy.group())               # <h1>Title</h1><p>Paragraph</p>

# الوضع الكسول — يطابق أقل قدر ممكن (أضف ?)
lazy = re.search(r"<.+?>", text)
print(lazy.group())                 # <h1>