1) find_all( name , attrs , recursive , text , **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
可根据标签名、属性、内容查找文档
html = """ <div class="panel"> <div class="panel-heading"> <h4>Hello</h4> <div class="panel-body"> <ul class="list" id="list-1"> <li class="element">Foo</li> <li class="element">Bar</li> <li class="element">Jay</li> </ul> <ul class="list list-small" id="list-2"> <li class="element">Foo</li> <li class="element">Bar</li> </ul> </div> </div> """ from bs4 import BeautifulSoup soup = BeautifulSoup(html, 'html5lib') print(soup.find_all('ul')) #find_all根据标签名'ul'都查找出来,放入列表当中 print(type(soup.find_all('ul')[0]))
[<ul class="list" id="list-1"> <li class="element">Foo</li> <li class="element">Bar</li> <li class="element">Jay</li> </ul>, <ul class="list list-small" id="list-2"> <li class="element">Foo</li> <li class="element">Bar</li> </ul>] <class 'bs4.element.Tag'>
html = """ <div class="panel"> <div class="panel-heading"> <h4>Hello</h4> <div class="panel-body"> <ul class="list" id="list-1"> <li class="element">Foo</li> <li class="element">Bar</li> <li class="element">Jay</li> </ul> <ul class="list list-small" id="list-2"> <li class="element">Foo</li> <li class="element">Bar</li> </ul> </div> </div> """ from bs4 import BeautifulSoup soup = BeautifulSoup(html, 'html5lib') for ul in soup.find_all('ul'): #通过两次for循环表示出来 print (ul.find_all('li'))
[<li class="element">Foo</li>, <li class="element">Bar</li>, <li class="element">Jay</li>] [<li class="element">Foo</li>, <li class="element">Bar</li>]
attrs
html = """ <div class="panel"> <div class="panel-heading"> <h4>Hello</h4> <div class="panel-body"> <ul class="list" id="list-1" name="elements"> <li class="element">Foo</li> <li class="element">Bar</li> <li class="element">Jay</li> </ul> <ul class="list list-small" id="list-2"> <li class="element">Foo</li> <li class="element">Bar</li> </ul> </div> </div> """ from bs4 import BeautifulSoup soup = BeautifulSoup(html, 'html5lib') print(soup.find_all(attrs={'id':'list-1'})) print(soup.find_all(attrs={'name':'elements'}))
[<ul class="list" id="list-1" name="elements"> <li class="element">Foo</li> <li class="element">Bar</li> <li class="element">Jay</li> </ul>] [<ul class="list" id="list-1" name="elements"> <li class="element">Foo</li> <li class="element">Bar</li> <li class="element">Jay</li> </ul>]
html = """ <div class="panel"> <div class="panel-heading"> <h4>Hello</h4> <div class="panel-body"> <ul class="list" id="list-1" name="elements"> <li class="element">Foo</li> <li class="element">Bar</li> <li class="element">Jay</li> </ul> <ul class="list list-small" id="list-2"> <li class="element">Foo</li> <li class="element">Bar</li> </ul> </div> </div> """ from bs4 import BeautifulSoup soup = BeautifulSoup(html, 'html5lib') print(soup.find_all(id='list-1')) print(soup.find_all(class_='element')) #因为class在python中有特别意义,所有加多一个下滑线
[<ul class="list" id="list-1" name="elements"> <li class="element">Foo</li> <li class="element">Bar</li> <li class="element">Jay</li> </ul>] [<li class="element">Foo</li>, <li class="element">Bar</li>, <li class="element">Jay</li>, <li class="element">Foo</li>, <li class="element">Bar</li>]
text
html = """ <div class="panel"> <div class="panel-heading"> <h4>Hello</h4> <div class="panel-body"> <ul class="list" id="list-1" name="elements"> <li class="element">Foo</li> <li class="element">Bar</li> <li class="element">Jay</li> </ul> <ul class="list list-small" id="list-2"> <li class="element">Foo</li> <li class="element">Bar</li> </ul> </div> </div> """ from bs4 import BeautifulSoup soup = BeautifulSoup(html, 'html5lib') print(soup.find_all(text='Foo'))
['Foo', 'Foo']
2) find( name , attrs , recursive , text , **kwargs )
基本和find_all一样,只不过只查找一个标签,第一个标签
html = """ <div class="panel"> <div class="panel-heading"> <h4>Hello</h4> <div class="panel-body"> <ul class="list" id="list-1" name="elements"> <li class="element">Foo</li> <li class="element">Bar</li> <li class="element">Jay</li> </ul> <ul class="list list-small" id="list-2"> <li class="element">Foo</li> <li class="element">Bar</li> </ul> </div> </div> """ from bs4 import BeautifulSoup soup = BeautifulSoup(html, 'html5lib') print(soup.find('ul')) print(type(soup.find('ul'))) print(soup.find('page'))
<ul class="list" id="list-1" name="elements"> <li class="element">Foo</li> <li class="element">Bar</li> <li class="element">Jay</li> </ul> <class 'bs4.element.Tag'> None
(3)find_parents() find_parent()
find_all() 和 find() 只搜索当前节点的所有子节点,孙子节点等. find_parents() 和 find_parent() 用来搜索当前节点的父辈节点,搜索方法与普通tag的搜索方法相同,搜索文档搜索文档包含的内容
(4)find_next_siblings() find_next_sibling()
这2个方法通过 .next_siblings 属性对当 tag 的所有后面解析的兄弟 tag 节点进行迭代, find_next_siblings()方法返回所有符合条件的后面的兄弟节点,find_next_sibling() 只返回符合条件的后面的第一个tag节点
(5)find_previous_siblings() find_previous_sibling()
这2个方法通过 .previous_siblings 属性对当前 tag 的前面解析的兄弟 tag 节点进行迭代, find_previous_siblings() 方法返回所有符合条件的前面的兄弟节点, find_previous_sibling() 方法返回第一个符合条件的前面的兄弟节点
(6)find_all_next() find_next()
这2个方法通过 .next_elements 属性对当前 tag 的之后的 tag 和字符串进行迭代, find_all_next() 方法返回所有符合条件的节点, find_next() 方法返回第一个符合条件的节点
(7)find_all_previous() 和 find_previous()
这2个方法通过 .previous_elements 属性对当前节点前面的 tag 和字符串进行迭代, find_all_previous() 方法返回所有符合条件的节点, find_previous()方法返回第一个符合条件的节点