from bs4 import BeautifulSoup# html_doc = """#The Dormouse's story # ###Once upon a time there were three little sisters; and their names were# Elsie,# Lacie and# Tillie;# and they lived at the bottom of a well.
##...
# """# soup=BeautifulSoup(html_doc,'lxml')# print(soup) #会将不完整的html文本补充完成# print(soup.prettify()) #将html文本进行结构划分# print(soup.p.b) #查找文本的第一个标签The Dormouse's story
#查找子孙节点# print(list(soup.p.descendants))# print(soup.p.a.text) #显示标签内的文本# print(soup.p.children) #,迭代器使用list()转为列表形式# print(list(soup.p.children)) #['Once upon a time there were three little sisters; and their names were\n', Elsie, ',\n', Lacie, ' and\n', Tillie, ';\nand they lived at the bottom of a well.']# print(soup.p.contents)# print(soup.a.parent) #查找标签a的父标签，包括子标签和内容# print(soup.a.parents) # # print(list(soup.a.parents)) #结果类型为列表，查找所有父标签包括父标签的内容，直到document
find和findall
html_doc = """The Dormouse's story The Dormouse's story
Once upon a time there were three little sisters; and their names wereElsie,Lacie andTillie;and they lived at the bottom of a well.
...
"""soup=BeautifulSoup(html_doc,'lxml')# print(soup.find_all('a')) #[Elsie, Lacie, Tillie]# print(soup.find_all('a',id='link2')) #[Lacie]# print(soup.find('a',id='link2')) #Lacie# print(soup.find(id='link2').attrs['href']) #http://example.C/lacie# print(soup.find_all(attrs={'class':'sister'})) #[Elsie, Lacie, Tillie]# print(soup.find('p').find('b')) #The Dormouse's story
CSS选择器
from bs4 import BeautifulSouphtml_doc = """The Dormouse's story The Dormouse's story
Once upon a time there were three little sisters; and their names wereElsie,Lacie andTillie;and they lived at the bottom of a well.
...
"""soup=BeautifulSoup(html_doc,'lxml')# print(soup.select('p b')) #[The Dormouse's story] 查找p标签下的b标签# print(soup.select('p')[1].select('#link2')[0].attrs['href']) #http://example.com/lacie 获取标签的属性# print(soup.select('p')[1].get_text()) #获取标签的文本内容