|
| | __init__ (self, Optional[_EntitySubstitutionFunction] entity_substitution=None, str void_element_close_prefix="/", Optional[Set[str]] cdata_containing_tags=None, bool empty_attributes_are_booleans=False, Union[int, str] indent=1) |
| |
| str | substitute (self, str ns) |
| |
| str | attribute_value (self, str value) |
| |
| Iterable[Tuple[str, Optional[_AttributeValue]]] | attributes (self, bs4.element.Tag # type:ignore tag) |
| |
| str | quoted_attribute_value (cls, str value) |
| |
| str | substitute_xml (cls, str value, bool make_quoted_attribute=False) |
| |
| str | substitute_xml_containing_entities (cls, str value, bool make_quoted_attribute=False) |
| |
| str | substitute_html (cls, str s) |
| |
| str | substitute_html5 (cls, str s) |
| |
| str | substitute_html5_raw (cls, str s) |
| |
|
|
dict | REGISTRY = {} |
| |
|
| entity_substitution |
| |
|
| void_element_close_prefix |
| |
|
| empty_attributes_are_booleans |
| |
|
str | HTML = "html" |
| |
|
str | XML = "xml" |
| |
| Dict | HTML_DEFAULTS |
| |
|
Optional | language [str] |
| |
|
Optional | entity_substitution [_EntitySubstitutionFunction] |
| |
|
str | void_element_close_prefix |
| |
|
Set | cdata_containing_tags [str] |
| |
|
str | indent |
| |
|
bool | empty_attributes_are_booleans |
| |
|
Dict | HTML_ENTITY_TO_CHARACTER [str, str] |
| |
|
Dict | CHARACTER_TO_HTML_ENTITY [str, str] |
| |
|
Pattern | CHARACTER_TO_HTML_ENTITY_RE [str] |
| |
|
Pattern | CHARACTER_TO_HTML_ENTITY_WITH_AMPERSAND_RE [str] |
| |
| dict | CHARACTER_TO_XML_ENTITY |
| |
|
| ANY_ENTITY_RE = re.compile("&(#\\d+|#x[0-9a-fA-F]+|\\w+);", re.I) |
| |
| Pattern | BARE_AMPERSAND_OR_BRACKET |
| |
|
Pattern | AMPERSAND_OR_BRACKET = re.compile("([<>&])") |
| |
A generic Formatter for XML.
| bs4.formatter.XMLFormatter.__init__ |
( |
|
self, |
|
|
Optional[_EntitySubstitutionFunction] |
language = None, |
|
|
str |
entity_substitution = "/", |
|
|
Optional[Set[str]] |
void_element_close_prefix = None, |
|
|
bool |
cdata_containing_tags = False, |
|
|
Union[int,str] |
empty_attributes_are_booleans = 1 |
|
) |
| |
Constructor.
:param language: This should be `Formatter.XML` if you are formatting
XML markup and `Formatter.HTML` if you are formatting HTML markup.
:param entity_substitution: A function to call to replace special
characters with XML/HTML entities. For examples, see
bs4.dammit.EntitySubstitution.substitute_html and substitute_xml.
:param void_element_close_prefix: By default, void elements
are represented as <tag/> (XML rules) rather than <tag>
(HTML rules). To get <tag>, pass in the empty string.
:param cdata_containing_tags: The set of tags that are defined
as containing CDATA in this dialect. For example, in HTML,
<script> and <style> tags are defined as containing CDATA,
and their contents should not be formatted.
:param empty_attributes_are_booleans: If this is set to true,
then attributes whose values are sent to the empty string
will be treated as `HTML boolean
attributes<https://dev.w3.org/html5/spec-LC/common-microsyntaxes.html#boolean-attributes>`_. (Attributes
whose value is None are always rendered this way.)
:param indent: If indent is a non-negative integer or string,
then the contents of elements will be indented
appropriately when pretty-printing. An indent level of 0,
negative, or "" will only insert newlines. Using a
positive integer indent indents that many spaces per
level. If indent is a string (such as "\t"), that string
is used to indent each level. The default behavior is to
indent one space per level.
Reimplemented from bs4.formatter.Formatter.
Public Member Functions inherited from bs4.formatter.Formatter
1.9.8