Python爬虫库BeautifulSoup获取对象(标签)名,属性,内容,注释

from bs4 import BeautifulSoup
soup = BeautifulSoup('<b class="boldest">Extremely bold</b>','lxml')
tag = soup.b
type(tag)

bs4.element.Tag

tag.name

'b'

tag.name = "blockquote" # 对原始文档进行修改
tag

<blockquote class="boldest">Extremely bold</blockquote>

tag['class']

['boldest']

tag.attrs

{'class': ['boldest']}

tag['class'] = 'verybold'
tag['id'] = 1
print(tag)

<blockquote class="verybold" id="1">Extremely bold</blockquote>

del tag['class']
del tag['id']
tag

<blockquote>Extremely bold</blockquote>

css_soup = BeautifulSoup('<p class="body strikeout"></p>','lxml')
print(css_soup.p['class'])

['body', 'strikeout']

rel_soup = BeautifulSoup('<p>Back to the <a rel="index">homepage</a></p>','lxml')
print(rel_soup.a['rel'])
rel_soup.a['rel'] = ['index', 'contents']
print(rel_soup.p)

['index']
<p>Back to the <a rel="index contents">homepage</a></p>

xml_soup = BeautifulSoup('<p class="body strikeout"></p>', 'xml')
xml_soup.p['class']

'body strikeout'

from bs4 import BeautifulSoup
soup = BeautifulSoup('<b class="boldest">Extremely bold</b>','lxml')
tag = soup.b
print(tag.string)
print(type(tag.string))

Extremely bold
<class 'bs4.element.NavigableString'>

unicode_string = str(tag.string)
print(unicode_string)
print(type(unicode_string))

Extremely bold
<class 'str'>

tag.string.replace_with("No longer bold")
tag

<b class="boldest">No longer bold</b>

markup = "<b><!--Hey, buddy. Want to buy a used parser?--></b>"
soup = BeautifulSoup(markup,'lxml')
comment = soup.b.string
type(comment)

bs4.element.Comment

comment

'Hey, buddy. Want to buy a used parser?'