# encoding: utf-8 # module lxml.html.diff # from D:\project\A_Board\.venv\Lib\site-packages\lxml\html\diff.cp313-win_amd64.pyd # by generator 1.147 # no doc # imports import builtins as __builtins__ # import lxml.html._difflib as difflib # C:\Programs\Python\Python313\Lib\site-packages\lxml\html\_difflib.cp313-win_amd64.pyd import inspect as inspect # C:\Programs\Python\Python313\Lib\inspect.py import itertools as itertools # import functools as functools # C:\Programs\Python\Python313\Lib\functools.py import operator as operator # C:\Programs\Python\Python313\Lib\operator.py import re as re # C:\Programs\Python\Python313\Lib\re\__init__.py import lxml.etree as etree # C:\Programs\Python\Python313\Lib\site-packages\lxml\etree.cp313-win_amd64.pyd import lxml.html.defs as defs # C:\Programs\Python\Python313\Lib\site-packages\lxml\html\defs.py import lxml.html._difflib as __lxml_html__difflib # functions def cleanup_delete(*args, **kwargs): # real signature unknown """ Cleans up any DEL_START/DEL_END markers in the document, replacing them with . To do this while keeping the document valid, it may need to drop some tags (either start or end tags). It may also move the del into adjacent tags to try to move it to a similar location where it was originally located (e.g., moving a delete into preceding
tag, if the del looks like (DEL_START, 'Text
', DEL_END) """ pass def cleanup_html(*args, **kwargs): # real signature unknown """ This 'cleans' the HTML, meaning that any page structure is removed (only the contents of are used, if there is any and tags are removed. """ pass def compress_tokens(*args, **kwargs): # real signature unknown """ Combine adjacent tokens when there is no HTML between the tokens, and they share an annotation """ pass def copy_annotations(*args, **kwargs): # real signature unknown """ Copy annotations from the tokens listed in src to the tokens in dest """ pass def default_markup(*args, **kwargs): # real signature unknown pass def end_tag(*args, **kwargs): # real signature unknown """ The text representation of an end tag for a tag. Includes trailing whitespace when appropriate. """ pass def expand_tokens(*args, **kwargs): # real signature unknown """ Given a list of tokens, return a generator of the chunks of text for the data in the tokens. """ pass def fixup_chunks(*args, **kwargs): # real signature unknown """ This function takes a list of chunks and produces a list of tokens. """ pass def fixup_ins_del_tags(*args, **kwargs): # real signature unknown """ Given an html string, move any or tags inside of any block-level elements, e.g. transform

word

 to

word

""" pass def flatten_el(*args, **kwargs): # real signature unknown """ Takes an lxml element el, and generates all the text chunks for that tag. Each start tag is a chunk, each word is a chunk, and each end tag is a chunk. If skip_tag is true, then the outermost container tag is not returned (just its contents). """ pass def fragment_fromstring(html, create_parent=False, base_url=None, parser=None, **kw): # reliably restored by inspect """ Parses a single HTML element; it is an error if there is more than one element, or if anything but whitespace precedes or follows the element. If ``create_parent`` is true (or is a tag name) then a parent node will be created to encapsulate the HTML in a single element. In this case, leading or trailing text is also allowed, as are multiple elements as result of the parsing. Passing a ``base_url`` will set the document's ``base_url`` attribute (and the tree's docinfo.URL). """ pass def group_by_first_item(*args, **kwargs): # real signature unknown """ Create a new function with partial application of the given arguments and keywords. """ pass def htmldiff(*args, **kwargs): # real signature unknown """ Do a diff of the old and new document. The documents are HTML *fragments* (str/UTF8 or unicode), they are not complete documents (i.e., no tag). Returns HTML with and tags added around the appropriate text. Markup is generally ignored, with the markup from new_html preserved, and possibly some markup from old_html (though it is considered acceptable to lose some of the old markup). Only the words in the HTML are diffed. The exception is tags, which are treated like words, and the href attribute of tags, which are noted inside the tag itself when there are changes. """ pass def htmldiff_tokens(*args, **kwargs): # real signature unknown """ Does a diff on the tokens themselves, returning a list of text chunks (not tokens). """ pass def html_annotate(*args, **kwargs): # real signature unknown; NOTE: unreliably restored from __doc__ """ doclist should be ordered from oldest to newest, like:: >>> version1 = 'Hello World' >>> version2 = 'Goodbye World' >>> print(html_annotate([(version1, 'version 1'), ... (version2, 'version 2')])) Goodbye World The documents must be *fragments* (str/UTF8 or unicode), not complete documents The markup argument is a function to markup the spans of words. This function is called like markup('Hello', 'version 2'), and returns HTML. The first argument is text and never includes any markup. The default uses a span with a title: >>> print(default_markup('Some Text', 'by Joe')) Some Text """ pass def html_annotate_merge_annotations(*args, **kwargs): # real signature unknown """ Merge the annotations from tokens_old into tokens_new, when the tokens in the new document already existed in the old document. """ pass def is_end_tag(*args, **kwargs): # real signature unknown pass def is_start_tag(*args, **kwargs): # real signature unknown pass def is_word(*args, **kwargs): # real signature unknown pass def markup_serialize_tokens(*args, **kwargs): # real signature unknown """ Serialize the list of tokens into a list of text chunks, calling markup_func around text to add annotations. """ pass def merge_delete(*args, **kwargs): # real signature unknown """ Adds the text chunks in del_chunks to the document doc (another list of text chunks) with marker to show it is a delete. cleanup_delete later resolves these markers into tags. """ pass def merge_insert(*args, **kwargs): # real signature unknown """ doc is the already-handled document (as a list of text chunks); here we add ins_chunks to the end of that. """ pass def operator(*args, **kwargs): # real signature unknown """ Operator interface. This module exports a set of functions implemented in C corresponding to the intrinsic operators of Python. For example, operator.add(x, y) is equivalent to the expression x+y. The function names are those used for special methods; variants without leading and trailing '__' are also provided for convenience. """ pass def parse_html(*args, **kwargs): # real signature unknown """ Parses an HTML fragment, returning an lxml element. Note that the HTML will be wrapped in a
tag that was not in the original document. If cleanup is true, make sure there's no or , and get rid of any and tags. """ pass def serialize_html_fragment(*args, **kwargs): # real signature unknown """ Serialize a single lxml element as HTML. The serialized form includes the elements tail. If skip_outer is true, then don't serialize the outermost tag """ pass def split_trailing_whitespace(*args, **kwargs): # real signature unknown """ This function takes a word, such as 'test ' and returns ('test',' ') """ pass def split_words(*args, **kwargs): # real signature unknown """ Splits some text into words. Includes trailing whitespace on each word when appropriate. """ pass def start_tag(*args, **kwargs): # real signature unknown """ The text representation of the start tag for a tag. """ pass def tokenize(*args, **kwargs): # real signature unknown """ Parse the given HTML and returns token objects (words with attached tags). This parses only the content of a page; anything in the head is ignored, and the and elements are themselves optional. The content is then parsed by lxml, which ensures the validity of the resulting parsed document (though lxml may make incorrect guesses when the markup is particular bad). and tags are also eliminated from the document, as that gets confusing. If include_hrefs is true, then the href attribute of tags is included as a special kind of diffable token. """ pass def tokenize_annotated(*args, **kwargs): # real signature unknown """ Tokenize a document and add an annotation attribute to each token """ pass def _find_words(*args, **kwargs): # real signature unknown """ Return a list of all non-overlapping matches of pattern in string. """ pass def _has_start_whitespace(*args, **kwargs): # real signature unknown pass def _merge_element_contents(*args, **kwargs): # real signature unknown """ Removes an element, but merges its contents into its place, e.g., given

Hi there!

, if you remove the element you get

Hi there!

""" pass def _replace_ins_del(*args, **kwargs): # real signature unknown pass def _search_body(*args, **kwargs): # real signature unknown pass def _search_end_body(*args, **kwargs): # real signature unknown pass def __pyx_unpickle_InsensitiveSequenceMatcher(*args, **kwargs): # real signature unknown pass # classes class DEL_END(object): # no doc def __init__(self, *args, **kwargs): # real signature unknown pass __weakref__ = property(lambda self: object(), lambda self, v: None, lambda self: None) # default """list of weak references to the object""" __dict__ = None # (!) real value is "mappingproxy({'__module__': 'lxml.html.diff', '__dict__': , '__weakref__': , '__doc__': None})" class DEL_START(object): # no doc def __init__(self, *args, **kwargs): # real signature unknown pass __weakref__ = property(lambda self: object(), lambda self, v: None, lambda self: None) # default """list of weak references to the object""" __dict__ = None # (!) real value is "mappingproxy({'__module__': 'lxml.html.diff', '__dict__': , '__weakref__': , '__doc__': None})" class token(str): """ Represents a diffable token, generally a word that is displayed to the user. Opening tags are attached to this token when they are adjacent (pre_tags) and closing tags that follow the word (post_tags). Some exceptions occur when there are empty tags adjacent to a word, so there may be close tags in pre_tags, or open tags in post_tags. We also keep track of whether the word was originally followed by whitespace, even though we do not want to treat the word as equivalent to a similar word that does not have a trailing space. """ def html(self, *args, **kwargs): # real signature unknown pass def __init__(self, *args, **kwargs): # real signature unknown pass @staticmethod # known case of __new__ def __new__(*args, **kwargs): # real signature unknown pass def __repr__(self, *args, **kwargs): # real signature unknown pass __weakref__ = property(lambda self: object(), lambda self, v: None, lambda self: None) # default """list of weak references to the object""" hide_when_equal = False __dict__ = None # (!) real value is "mappingproxy({'__module__': 'lxml.html.diff', '__doc__': ' Represents a diffable token, generally a word that is displayed to\\n the user. Opening tags are attached to this token when they are\\n adjacent (pre_tags) and closing tags that follow the word\\n (post_tags). Some exceptions occur when there are empty tags\\n adjacent to a word, so there may be close tags in pre_tags, or\\n open tags in post_tags.\\n\\n We also keep track of whether the word was originally followed by\\n whitespace, even though we do not want to treat the word as\\n equivalent to a similar word that does not have a trailing\\n space.', 'hide_when_equal': False, '__new__': )>, '__repr__': , 'html': , '__dict__': , '__weakref__': })" class href_token(token): """ Represents the href in an anchor tag. Unlike other words, we only show the href when it changes. """ def html(self, *args, **kwargs): # real signature unknown pass def __init__(self, *args, **kwargs): # real signature unknown pass hide_when_equal = True class InsensitiveSequenceMatcher(__lxml_html__difflib.SequenceMatcher): """ Acts like SequenceMatcher, but tries not to find very small equal blocks amidst large spans of changes """ def __init__(self, *args, **kwargs): # real signature unknown """ Construct a SequenceMatcher. Optional arg isjunk is None (the default), or a one-argument function that takes a sequence element and returns true iff the element is junk. None is equivalent to passing "lambda x: 0", i.e. no elements are considered to be junk. For example, pass lambda x: x in " \t" if you're comparing lines as sequences of characters, and don't want to synch up on blanks or hard tabs. Optional arg a is the first of two sequences to be compared. By default, an empty string. The elements of a must be hashable. See also .set_seqs() and .set_seq1(). Optional arg b is the second of two sequences to be compared. By default, an empty string. The elements of b must be hashable. See also .set_seqs() and .set_seq2(). Optional arg autojunk should be set to False to disable the "automatic junk heuristic" that treats popular elements as junk (see module documentation for more information). """ pass @staticmethod # known case of __new__ def __new__(*args, **kwargs): # real signature unknown """ Create and return a new object. See help(type) for accurate signature. """ pass def __reduce_cython__(self, *args, **kwargs): # real signature unknown pass def __reduce__(self, *args, **kwargs): # real signature unknown pass def __setstate_cython__(self, *args, **kwargs): # real signature unknown pass def __setstate__(self, *args, **kwargs): # real signature unknown pass threshold = 2 __pyx_vtable__ = None # (!) real value is '' class tag_token(token): """ Represents a token that is actually a tag. Currently this is just the tag, which takes up visible space just like a word but is only represented in a document by a tag. """ def html(self, *args, **kwargs): # real signature unknown pass def __init__(self, *args, **kwargs): # real signature unknown pass @staticmethod # known case of __new__ def __new__(*args, **kwargs): # real signature unknown pass def __repr__(self, *args, **kwargs): # real signature unknown pass # variables with complex values __all__ = [ 'html_annotate', 'htmldiff', ] __loader__ = None # (!) real value is '<_frozen_importlib_external.ExtensionFileLoader object at 0x000001C944CC2B50>' __spec__ = None # (!) real value is "ModuleSpec(name='lxml.html.diff', loader=<_frozen_importlib_external.ExtensionFileLoader object at 0x000001C944CC2B50>, origin='C:\\\\Programs\\\\Python\\\\Python313\\\\Lib\\\\site-packages\\\\lxml\\\\html\\\\diff.cp313-win_amd64.pyd')" __test__ = { 'html_annotate (line 73)': '\n doclist should be ordered from oldest to newest, like::\n\n >>> version1 = \'Hello World\'\n >>> version2 = \'Goodbye World\'\n >>> print(html_annotate([(version1, \'version 1\'),\n ... (version2, \'version 2\')]))\n Goodbye World\n\n The documents must be *fragments* (str/UTF8 or unicode), not\n complete documents\n\n The markup argument is a function to markup the spans of words.\n This function is called like markup(\'Hello\', \'version 2\'), and\n returns HTML. The first argument is text and never includes any\n markup. The default uses a span with a title:\n\n >>> print(default_markup(\'Some Text\', \'by Joe\'))\n Some Text\n ', }