Python BS4 instalacja
pip install bs4 #this'll do the work
SilverShade
pip install bs4 #this'll do the worksoup.find_all("a", string="Elsie")
# [<a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>]soup.find_all("a", class_="sister")
# [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>,
# <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>,
# <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]soup.find_all(id='link2')
# [<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>]soup.find_all("title")
# [<title>The Dormouse's story</title>]
soup.find_all("p", "title")
# [<p class="title"><b>The Dormouse's story</b></p>]
soup.find_all("a")
# [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>,
# <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>,
# <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]
soup.find_all(id="link2")
# [<a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>]
import re
soup.find(string=re.compile("sisters"))
# 'Once upon a time there were three little sisters; and their names were\n'soup.find_all(class_=re.compile("itl"))
# [<p class="title"><b>The Dormouse's story</b></p>]
def has_six_characters(css_class):
return css_class is not None and len(css_class) == 6
soup.find_all(class_=has_six_characters)
# [<a class="sister" href="http://example.com/elsie" id="link1">Elsie</a>,
# <a class="sister" href="http://example.com/lacie" id="link2">Lacie</a>,
# <a class="sister" href="http://example.com/tillie" id="link3">Tillie</a>]