Saturday, February 8, 2025¶

>>> from bs4 import BeautifulSoup
>>> from pprint import pprint
>>> html = '''<p>The <a href="foo"><b>quick</b></a>, brown fox jumps over a lazy dog.</p>'''
>>> # soup = BeautifulSoup(html, "html.parser")
>>> soup = BeautifulSoup(html, features="lxml")
>>> p = soup.find('p')
>>> print(p.string)
None
>>> list(p.children)
['The ', <a href="foo"><b>quick</b></a>, ', brown fox jumps over a lazy dog.']
>>> pprint([c.__class__ for c in p.children])
[<class 'bs4.element.NavigableString'>,
 <class 'bs4.element.Tag'>,
 <class 'bs4.element.NavigableString'>]
>>> a = p.find('a')
>>> b = a.find('b')
>>> assert b == p.find('b')

>>> list(a.children)
[<b>quick</b>]
>>> list(b.children)
['quick']

>>> a.string.__class__
<class 'bs4.element.NavigableString'>
>>> b.string.__class__
<class 'bs4.element.NavigableString'>

>>> a.string
'quick'
>>> b.string
'quick'

>>> a.string.string
'quick'
>>> a.string.string.string.string
'quick'

>>> a
<a href="foo"><b>quick</b></a>
>>> b
<b>quick</b>

>>> old = a.string.replace_with("foo")
>>> a
<a href="foo"><b>foo</b></a>

>>> old = a.replace_with("bar")
>>> a
<a href="foo"><b>foo</b></a>

>>> b.string.string.replace_with("bar")
'foo'
>>> a
<a href="foo"><b>bar</b></a>
>>> b
<b>bar</b>

>>> html = '<p>Before <a href="foo"><b>bar</b></a> and after.</p>'
>>> soup = BeautifulSoup(html, features="lxml")
>>> p = soup.find('p')
>>> list(p.descendants)
['Before ', <a href="foo"><b>bar</b></a>, <b>bar</b>, 'bar', ' and after.']
>>> print(p.string)
None
>>> print(list(p))
['Before ', <a href="foo"><b>bar</b></a>, ' and after.']
>>> a = soup.find('a')
>>> print(a.string)
bar
>>> list(a.children)
[<b>bar</b>]

>>> html = '<p>Lorem ipsum dolor sit amet, consectetur adipiscing elit.</p>'
>>> soup = BeautifulSoup(html, features="lxml")
>>> p = soup.find('p')
>>> s = p.string
>>> print(s)
Lorem ipsum dolor sit amet, consectetur adipiscing elit.
>>> unused = p.string.replace_with("foo")
>>> print(p)
<p>foo</p>

>>> html = "<p>A <b>bold</b></p><p>\n\n and <i>italic</i> thing.</p>"
>>> soup = BeautifulSoup(html, features="lxml")
>>> p = soup.find('p')
>>> list(p.children)
['A ', <b>bold</b>]

>>> html = """<p>foo <html><head><base href="bar" target="_blank"></head><body></p><p>baz</p>"""
>>> soup = BeautifulSoup(html, features="lxml")
>>> for c in soup.children:
...     print(c)
<html><body><p>foo </p><base href="bar" target="_blank"/><p>baz</p></body></html>