1. from lxml import etree
    2. import requests
    3. from useragent.useragent import get_useragent
    4. url = 'https://www.qiushibaike.com/text/page/1/'
    5. headers = {
    6.     'User-Agent': get_useragent()
    7. }
    8. resp = requests.get(url = url, headers = headers)
    9. html = resp.text
    10. e = etree.HTML(html)
    11. # xpath 规则查找
    12. content = e.xpath('//div[@class="content"]/span/text()')
    13. print(content)
    14. print(len(content))