Python编写一个简单的爬虫示例

import requests
from bs4 import BeautifulSoup

# 获取要爬取的网页链接（1-9表示翻页）
urls = [f'https://www.cnblogs.com/#p{i}' for i in range(1, 10)]

# 循环请求每个网页链接，并把请求到的页面内容返回
def crew():
    for url in urls:
        r = requests.get(url)
        return r.text

# 解析crew()函数返回的每个网页链接内容，并将符合参数中的要求匹配的内容过滤出来
def parse(html):
    soup = BeautifulSoup(html, 'html.parser')
    links = soup.find_all('a', class_='post-item-title')
    return [(link['href'], link.get_text()) for link in links]

if __name__ == '__main__':
    for ret in parse(crew()):
        print(ret)