from bs4 import BeautifulSoup
import re
def main():
html = """
首页
Hello, world!
这是一个神奇的网站！
这是一个例子程序
静夜思
床前明月光
疑似地上霜
举头望明月
腾讯网
"""
soup = BeautifulSoup(html, 'lxml')
# JavaScript - document.title
print(soup.title)
# JavaScript - document.body.h1
print(soup.body.h1)
print(soup.find_all(re.compile(r'^h')))
print(soup.find_all(re.compile(r'r$')))
print(soup.find_all('img', {'src': re.compile(r'\./img/\w+.png')}))
print(soup.find_all(lambda x: len(x.attrs) == 2))
print(soup.find_all('p', {'class': 'foo'}))
for elem in soup.select('a[href]'):
print(elem.attrs['href'])
if __name__ == '__main__':
main()