使用Python爬虫库BeautifulSoup遍历文档树并对标签进行操作详解

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.

...
"""

from bs4 import BeautifulSoup
soup = BeautifulSoup(html_doc,'lxml')

print(soup.head)
print(soup.title)

soup.find_all('a')

[Elsie,
 Lacie,
 Tillie]

head_tag = soup.head
head_tag.contents

[]

title_tag = head_tag.contents[0]
title_tag

title_tag.contents

["The Dormouse's story"]

for child in title_tag.children:
  print(child)

The Dormouse's story

for child in head_tag.children:
  print(child)

for child in head_tag.descendants:
  print(child)

The Dormouse's story

title_tag.string

"The Dormouse's story"

head_tag.string

"The Dormouse's story"

print(soup.html.string)

None

for string in soup.strings:
  print(string)

The Dormouse's story


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.


...

for string in soup.stripped_strings:
  print(string)

The Dormouse's story
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.
...

title_tag = soup.title
title_tag.parent

title_tag.string.parent

link = soup.a
for parent in link.parents:
  if parent is None:
    print(parent)
  else:
    print(parent.name)

p
body
html
[document]

sibling_soup = BeautifulSoup("text1text2",'lxml')
print(sibling_soup.prettify())

 
 
  
  text1
  
  
  text2
  
 
 

sibling_soup.b.next_sibling

text2

sibling_soup.c.previous_sibling

text1

soup.find_all('a')

[Elsie,
 Lacie,
 Tillie]

soup.a.next_sibling # 第一个的next_sibling是,\n

',\n'

soup.a.next_sibling.next_sibling

Lacie

for sibling in soup.a.next_siblings:
  print(repr(sibling))

',\n'
Lacie
' and\n'
Tillie
';\nand they lived at the bottom of a well.'

for sibling in soup.find(id="link3").previous_siblings:
  print(repr(sibling))

' and\n'
Lacie
',\n'
Elsie
'Once upon a time there were three little sisters; and their names were\n'

last_a_tag = soup.find("a", id="link3")
print(last_a_tag.next_sibling)
print(last_a_tag.next_element)

;
and they lived at the bottom of a well.
Tillie

last_a_tag.previous_element

' and\n'

for element in last_a_tag.next_elements:
  print(repr(element))

'Tillie'
';\nand they lived at the bottom of a well.'
'\n'
...
'...'
'\n'