from requests_html import HTMLSession

session=HTMLSession()

r=session.get('https://news.baidu.com/')

#获取页面上的所有链接

all_links=r.html.links

print(all_links)

#获取页面上的所有链接，以绝对路径的方式

all_absolute_links=r.html.absolute_links

print(all_absolute_links)

from requests_html import HTMLSession

session=HTMLSession()

r=session.get('https://www.cnblogs.com/')

news=r.html.find('#post_list > div:nth-child(n) > div.post_item_body > h3 > a')

for new in news:

    print(new.text)

    print(new.absolute_links)

>>> about = r.html.find('#about', first=True)

>>> print(about.text)

>>> about.attrs

{'id': 'about', 'class': ('tier-1', 'element-1'), 'aria-haspopup': 'true'}

>>> about.html