抓取百度贴吧网页前五张

[python]代码库

from urllib.request import urlopen

# url = 'http://tieba.baidu.com/f?kw=%E4%BE%AF%E6%98%8E%E6%98%8A&ie=utf-8&pn=100'
# response = urlopen(url)
# print(response.read().decode())

def get_one_page(index):
    url = 'http://tieba.baidu.com/f?kw=%E4%BE%AF%E6%98%8E%E6%98%8A&ie=utf-8&pn={}'.format(index*50)
    response = urlopen(url)
    return response.read().decode()

def save_one_page(index, html):
    file_name = 'tieba\\houminghao_page_{}.html'.format(index+1)
    with open(file_name, 'w', encoding='utf-8') as file:
        file.write(html)
    pass

if __name__ == '__main__':
    for index in range(0, 5):
        html = get_one_page(index)
        save_one_page(index, html)