text = "Hello, World!"
# 提取第 2-5 個(gè)字符（索引從0開(kāi)始）
substring = text[1:5]  # "ello"
# 提取前 5 個(gè)字符
first_five = text[:5]  # "Hello"
# 提取從第 7 個(gè)字符到末尾
from_seven = text[7:]  # "World!"
# 提取最后 6 個(gè)字符
last_six = text[-6:]  # "World!"

# 提取偶數(shù)索引字符
even_chars = text[::2]  # "Hlo ol!"
# 反轉(zhuǎn)字符串
reversed_text = text[::-1]  # "!dlroW ,olleH"

data = "John,Doe,30,New York"
# 提取名字
first_name = data.split(",")[0]  # "John"
# 提取城市
city = data.split(",")[-1]  # "New York"
# 限制分割次數(shù)
parts = data.split(",", 2)  # ['John', 'Doe', '30,New York']

url = "https://www.example.com/page?query=value"
# 提取域名
protocol, separator, domain = url.partition("://")
domain = domain.split("/")[0]  # "www.example.com"
# 提取查詢參數(shù)
base, separator, query = url.rpartition("?")
query_params = query  # "query=value"

import re
text = "訂單號(hào): ABC-12345, 金額: $150.75"
# 提取訂單號(hào)
order_match = re.search(r"訂單號(hào): (\w+-\d+)", text)
order_number = order_match.group(1) if order_match else None  # "ABC-12345"
# 提取金額
amount_match = re.search(r"\$(\d+\.\d+)", text)
amount = float(amount_match.group(1)) if amount_match else 0.0  # 150.75

def extract_between(text, start_marker, end_marker):
    start = text.find(start_marker) + len(start_marker)
    end = text.find(end_marker, start)
    return text[start:end] if start != -1 and end != -1 else ""
# 使用示例
html = '<div class="content">重要信息</div>'
content = extract_between(html, '>', '<')  # "重要信息"

# 從索引 7 開(kāi)始提取 5 個(gè)字符
sub = text[7:7+5]  # "World"

sentence = "The quick brown fox jumps over the lazy dog"
# 提取第 3 個(gè)單詞（索引從0開(kāi)始）
words = sentence.split()
third_word = words[2] if len(words) > 2 else ""  # "brown"
# 提取最后兩個(gè)單詞
last_two = " ".join(words[-2:])  # "lazy dog"

def safe_slice(text, start, end=None):
    """安全切片，避免索引越界"""
    if end is None:
        return text[start:] if start < len(text) else ""
    return text[start:min(end, len(text))]
# 使用示例
result = safe_slice("short", 3, 10)  # "rt"

def extract_all(text, pattern):
    """使用正則提取所有匹配項(xiàng)"""
    return re.findall(pattern, text)
# 使用示例
text = "電話: 138-1234-5678, 備用: 139-8765-4321"
phones = extract_all(text, r"\d{3}-\d{4}-\d{4}")  # ['138-1234-5678', '139-8765-4321']

def extract_numbers(text):
    """提取所有數(shù)字并轉(zhuǎn)換為整數(shù)"""
    return [int(num) for num in re.findall(r'\d+', text)]
# 使用示例
data = "產(chǎn)品A: 庫(kù)存50, 價(jià)格$120; 產(chǎn)品B: 庫(kù)存30, 價(jià)格$85"
numbers = extract_numbers(data)  # [50, 120, 30, 85]

# 處理非ASCII字符
text = "中文示例"
substring = text[2:4].encode('utf-8').decode('utf-8')  # "文"

pattern = re.compile(r'\b\w{5}\b')  # 預(yù)編譯
five_letter_words = pattern.findall(large_text)

try:
    result = text.split(":")[1]
except IndexError:
    result = "默認(rèn)值"

import unicodedata

# 標(biāo)準(zhǔn)化Unicode字符串
normalized = unicodedata.normalize('NFC', text)

# 提取日期并轉(zhuǎn)換為datetime
from datetime import datetime

date_str = "2023-08-15"
date_obj = datetime.strptime(date_str, "%Y-%m-%d")