py-instagram-robot/util/url_util.py

import re

import requests
from urllib.parse import urlparse


def get_expanded_url(url: str) -> str:
    """
    展开短链接到完整URL
    """
    try:
        response = requests.head(url, allow_redirects=True)
        return response.url
    except Exception as e:
        return url


def get_id_by_url(url: str) -> str:
    """
    从URL中提取ID
    
    Args:
        url: 输入的URL字符串
    
    Returns:
        从URL路径中提取的最后一个部分作为ID
    """
    # 短链接匹配模式（这里假设使用类似的正则表达式）
    # https://www.instagram.com/share/_nFwInAGM
    short_link_pattern = re.compile(r'http[s]?://www\.instagram\.com/share')

    # 如果是短链接，先展开
    if short_link_pattern.search(url):
        url = get_expanded_url(url)

    # 解析URL并获取路径
    parsed_url = urlparse(url)
    path_parts = parsed_url.path.split('/')

    # 返回路径最后一个部分
    return path_parts[-1]