BeautifulSoup用法

中文文档手册

https://beautifulsoup.readthedocs.io/zh_CN/v4.4.0/

find_all()

find_all( name , attrs , recursive , string , **kwargs )

find_all() 方法搜索当前tag的所有tag子节点,并判断是否符合过滤器的条件.这里有几个例子:

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"))
# u'Once upon a time there were three little sisters; and their names were\n'

//使用多个条件过滤
soup.find_all(href=re.compile("elsie"), id='link1')
# [<a class="sister" href="http://example.com/elsie" id="link1">three</a>]

//自定义属性的过滤方法
data_soup.find_all(attrs={"data-foo": "value"})
# [<div data-foo="value">foo!</div>]

//根据class的名字过滤标签
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(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>]


css_soup = BeautifulSoup('<p class="body strikeout"></p>')
css_soup.find_all("p", class_="strikeout")
# [<p class="body strikeout"></p>]

css_soup.find_all("p", class_="body")
# [<p class="body strikeout"></p>]

//使用string参数根据字符串中的内容进行过滤
soup.find_all("a", string="Elsie")
# [<a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>]