help

林森森

做一个爬虫程序，爬取页面的url为：http://books.toscrape.com，打印该页面的标题（<title>标记）和第一个超链接的文本（<a>标记

suchocolate

import requests
from lxml import etree


def main():
    url = 'http://books.toscrape.com/'
    headers = {'user-agent': 'firefox'}
    r = requests.get(url, headers=headers)
    html = etree.HTML(r.text)
    title = html.xpath('normalize-space(//title/text())')
    link = html.xpath('//a[@href]/text()')[0]
    print(title)
    print(link)


if __name__ == '__main__':
    main()