Python栈的应用：网页爬虫的实现

import requests
from bs4 import BeautifulSoup

# Create a stack to store URLs to crawl
stack = ["https://pidancode.com"]

# Start the crawling process
while stack:
    # Pop the next URL from the stack
    url = stack.pop()

    # Print the URL being crawled
    print("Crawling:", url)

    # Send a GET request to the URL
    response = requests.get(url)

    # Parse the HTML content of the page
    soup = BeautifulSoup(response.content, "html.parser")

    # Find all links on the page
    links = soup.find_all("a")

    # Add each link to the stack for crawling
    for link in links:
        href = link.get("href")
        if href not in stack:
            stack.append(href)