BeautifulSoup 库中的 prettify() 方法可以将 HTML 或 XML 文档格式化为更易于阅读的格式。默认情况下，prettify() 方法会将所有标签换行，但有时我们希望某些标签不换行，以保持内容的完整性。例如，我们可能希望 <span> 和 <a> 标签不换行，以便它们在页面上保持在一起。
解决方案
要自定义 prettify() 方法以不换行某些标签，我们可以使用以下步骤：
- 首先，我们需要创建一个子类，继承自
BeautifulSoup.Tag和BeautifulSoup.BeautifulStoneSoup类。 - 然后，我们需要覆盖
__str__()和renderContents()方法，以自定义格式化标签和标签的内容。 - 最后，我们需要创建
PumpkinSoup类，继承自我们的子类和BeautifulSoup.BeautifulSoup类。PumpkinSoup类将具有一个pprint_exs属性，该属性用于指定不换行的标签列表。
以下是可以实现自定义 prettify() 方法的代码示例：
import sys
import BeautifulSoup
class Tag(BeautifulSoup.Tag):
def __str__(self, encoding=BeautifulSoup.DEFAULT_OUTPUT_ENCODING,
prettyPrint=False, indentLevel=0, pprint_exs=[]):
"""Returns a string or Unicode representation of this tag and
its contents. To get Unicode, pass None for encoding.
NOTE: since Python's HTML parser consumes whitespace, this
method is not certain to reproduce the whitespace present in
the original string."""
encodedName = self.toEncoding(self.name, encoding)
unflatten_here = (not self.name in pprint_exs)
attrs = []
if self.attrs:
for key, val in self.attrs:
fmt = '%s="%s"'
if isinstance(val, basestring):
if self.containsSubstitutions and '%SOUP-ENCODING%' in val:
val = self.substituteEncoding(val, encoding)
# The attribute value either:
#
# * Contains no embedded double quotes or single quotes.
# No problem: we enclose it in double quotes.
# * Contains embedded single quotes. No problem:
# double quotes work here too.
# * Contains embedded double quotes. No problem:
# we enclose it in single quotes.
# * Embeds both single _and_ double quotes. This
# can't happen naturally, but it can happen if
# you modify an attribute value after parsing
# the document. Now we have a bit of a
# problem. We solve it by enclosing the
# attribute in single quotes, and escaping any
# embedded single quotes to XML entities.
if '"' in val:
fmt = "%s='%s'"
if "'" in val:
# TODO: replace with apos when
# appropriate.
val = val.replace("'", "&squot;")
# Now we're okay w/r/t quotes. But the attribute
# value might also contain angle brackets, or
# ampersands that aren't part of entities. We need
# to escape those to XML entities too.
val = self.BARE_AMPERSAND_OR_BRACKET.sub(self._sub_entity, val)
attrs.append(fmt % (self.toEncoding(key, encoding),
self.toEncoding(val, encoding)))
close = ''
closeTag = ''
if self.isSelfClosing:
close = ' /'
else:
closeTag = '</%s>' % encodedName
prev = self.findPrevious(lambda x: isinstance(x, Tag))
prev_sib = self.findPreviousSibling(lambda x: isinstance(x, Tag))
ex_break_detected = (self.name != prev_sib.name) if(prev_sib and prev_sib.name in pprint_exs) else False
break_detected = (self.name != prev.name) if(prev) else False
indentTag, indentContents = 0, 0
if prettyPrint:
if(break_detected or unflatten_here):
indentContents = indentLevel + 1
indentTag = indentLevel
space = (' ' * (indentTag-1))
contents = self.renderContents(encoding, prettyPrint, indentContents, pprint_exs, unflatten_here)
if self.hidden:
s = contents
else:
s = []
attributeString = ''
if attrs:
attributeString = ' ' + ' '.join(attrs)
if prettyPrint and ex_break_detected and not unflatten_here:
s.append("\n")
if prettyPrint and (unflatten_here or break_detected):
s.append(space)
s.append('<%s%s%s>' % (encodedName, attributeString, close))
if prettyPrint and unflatten_here:
s.append("\n")
s.append(contents)
if prettyPrint and contents and contents[-1] != "\n" and unflatten_here:
s.append("\n")
if prettyPrint and closeTag and unflatten_here:
s.append(space)
s.append(closeTag)
if prettyPrint and closeTag and self.nextSibling and unflatten_here:
s.append("\n")
if prettyPrint and isinstance(self.nextSibling, Tag) and self.nextSibling.name != self.name and not unflatten_here:
s.append("\n")
s = ''.join(s)
return s
def renderContents(self, encoding=BeautifulSoup.DEFAULT_OUTPUT_ENCODING,
prettyPrint=False, indentLevel=0, pprint_exs=[], unflatten=True):
"""Renders the contents of this tag as a string in the given
encoding. If encoding is None, returns a Unicode string.."""
s=[]
for c in self:
text = None
if isinstance(c, BeautifulSoup.NavigableString):
text = c.__str__(encoding)
elif isinstance(c, Tag):
s.append(c.__str__(encoding, prettyPrint, indentLevel, pprint_exs))
if text and prettyPrint:
text = text.strip()
if text:
if prettyPrint and unflatten:
s.append(" " * (indentLevel-1))
s.append(text)
if prettyPrint and unflatten:
s.append("\n")
return ''.join(s)
BeautifulSoup.Tag = Tag
class BeautifulStoneSoup(Tag, BeautifulSoup.BeautifulStoneSoup):
pass
BeautifulSoup.BeautifulStoneSoup = BeautifulStoneSoup
class PumpkinSoup(BeautifulStoneSoup, BeautifulSoup.BeautifulSoup):
def __init__(self, *args, **kwargs):
self.pprint_exs = kwargs.pop("pprint_exs", [])
super(BeautifulSoup.BeautifulSoup, self).__init__(*args, **kwargs)
def prettify(self, encoding=BeautifulSoup.DEFAULT_OUTPUT_ENCODING):
return self.__str__(encoding, True, pprint_exs=self.pprint_exs)
doc = \
'''
<div>
<div>
<span>a</span><span>b</span>
<a>link1</a>
<a>link2</a>
<span>c</span>
</div>
<a>link3</a><a>link4</a>
</div>
'''
soup = PumpkinSoup(doc, pprint_exs = ["a", "span"])
print soup.prettify()
输出结果：
<div>
<div>
<span>a</span><span>b</span>
<a>link1</a>
<a>link2</a>
<span>c</span>
</div>
<a>link3</a><a>link4</a>
</div>
从输出结果可以看出，<span> 和 <a> 标签没有换行，保持了内容的完整性。
