我的假设是 BeautifulSoup.prettify 正在添加这些
默认情况下多余/无偿的换行符，并且没有出现
是修改这种行为的好方法。
是
它在bs4.Tag 类decode 和decode_contents 的两个方法中这样做。
参考：Source file on github
如果你只是需要一个临时修复，你可以猴子补丁这两种方法
这是我的实现
from bs4 import Tag, NavigableString, BeautifulSoup
from bs4.element import AttributeValueWithCharsetSubstitution, EntitySubstitution
def decode(
self, indent_level=None,
eventual_encoding="utf-8", formatter="minimal"
):
if not callable(formatter):
formatter = self._formatter_for_name(formatter)
attrs = []
if self.attrs:
for key, val in sorted(self.attrs.items()):
if val is None:
decoded = key
else:
if isinstance(val, list) or isinstance(val, tuple):
val = ' '.join(val)
elif not isinstance(val, str):
val = str(val)
elif (
isinstance(val, AttributeValueWithCharsetSubstitution)
and eventual_encoding is not None
):
val = val.encode(eventual_encoding)
text = self.format_string(val, formatter)
decoded = (
str(key) + '='
+ EntitySubstitution.quoted_attribute_value(text))
attrs.append(decoded)
close = ''
closeTag = ''
prefix = ''
if self.prefix:
prefix = self.prefix + ":"
if self.is_empty_element:
close = '/'
else:
closeTag = '</%s%s>' % (prefix, self.name)
pretty_print = self._should_pretty_print(indent_level)
space = ''
indent_space = ''
if indent_level is not None:
indent_space = (' ' * (indent_level - 1))
if pretty_print:
space = indent_space
indent_contents = indent_level + 1
else:
indent_contents = None
contents = self.decode_contents(
indent_contents, eventual_encoding, formatter)
if self.hidden:
# This is the 'document root' object.
s = contents
else:
s = []
attribute_string = ''
if attrs:
attribute_string = ' ' + ' '.join(attrs)
if indent_level is not None:
# Even if this particular tag is not pretty-printed,
# we should indent up to the start of the tag.
s.append(indent_space)
s.append('<%s%s%s%s>' % (
prefix, self.name, attribute_string, close))
has_tag_child = False
if pretty_print:
for item in self.children:
if isinstance(item, Tag):
has_tag_child = True
break
if has_tag_child:
s.append("\n")
s.append(contents)
if not has_tag_child:
s[-1] = s[-1].strip()
if pretty_print and contents and contents[-1] != "\n":
s.append("")
if pretty_print and closeTag:
if has_tag_child:
s.append(space)
s.append(closeTag)
if indent_level is not None and closeTag and self.next_sibling:
# Even if this particular tag is not pretty-printed,
# we're now done with the tag, and we should add a
# newline if appropriate.
s.append("\n")
s = ''.join(s)
return s
def decode_contents(
self,
indent_level=None,
eventual_encoding="utf-8",
formatter="minimal"
):
# First off, turn a string formatter into a function. This
# will stop the lookup from happening over and over again.
if not callable(formatter):
formatter = self._formatter_for_name(formatter)
pretty_print = (indent_level is not None)
s = []
for c in self:
text = None
if isinstance(c, NavigableString):
text = c.output_ready(formatter)
elif isinstance(c, Tag):
s.append(
c.decode(indent_level, eventual_encoding, formatter)
)
if text and indent_level and not self.name == 'pre':
text = text.strip()
if text:
if pretty_print and not self.name == 'pre':
s.append(" " * (indent_level - 1))
s.append(text)
if pretty_print and not self.name == 'pre':
s.append("")
return ''.join(s)
Tag.decode = decode
Tag.decode_contents= decode_contents
在这之后，当我做print(soup.prettify)时，输出是
<annotation>
<folder>Definitiva</folder>
<filename>armas_229.jpg</filename>
<path>/tmp/tmpygedczp5/handgun/images/armas_229.jpg</path>
<size>
<width>1800</width>
<height>1426</height>
<depth>3</depth>
</size>
<segmented>0</segmented>
<object>
<name>handgun</name>
<pose>Unspecified</pose>
<truncated>0</truncated>
<difficult>0</difficult>
<bndbox>
<xmin>1001</xmin>
<ymin>549</ymin>
<xmax>1453</xmax>
<ymax>1147</ymax>
</bndbox>
</object>
</annotation>
我在做这个的时候做了很多假设。只是想证明这是可能的。