lxml 6.0.0__cp312-cp312-macosx_10_13_x86_64.whl

lxml/html/formfill.py

@@ -0,0 +1,299 @@
+from lxml.etree import XPath, ElementBase
+from lxml.html import fromstring, XHTML_NAMESPACE
+from lxml.html import _forms_xpath, _options_xpath, _nons, _transform_result
+from lxml.html import defs
+import copy
+
+try:
+    basestring
+except NameError:
+    # Python 3
+    basestring = str
+
+__all__ = ['FormNotFound', 'fill_form', 'fill_form_html',
+           'insert_errors', 'insert_errors_html',
+           'DefaultErrorCreator']
+
+class FormNotFound(LookupError):
+    """
+    Raised when no form can be found
+    """
+
+_form_name_xpath = XPath('descendant-or-self::form[name=$name]|descendant-or-self::x:form[name=$name]', namespaces={'x':XHTML_NAMESPACE})
+_input_xpath = XPath('|'.join(['descendant-or-self::'+_tag for _tag in ('input','select','textarea','x:input','x:select','x:textarea')]),
+                               namespaces={'x':XHTML_NAMESPACE})
+_label_for_xpath = XPath('//label[@for=$for_id]|//x:label[@for=$for_id]',
+                               namespaces={'x':XHTML_NAMESPACE})
+_name_xpath = XPath('descendant-or-self::*[@name=$name]')
+
+def fill_form(
+    el,
+    values,
+    form_id=None,
+    form_index=None,
+    ):
+    el = _find_form(el, form_id=form_id, form_index=form_index)
+    _fill_form(el, values)
+
+def fill_form_html(html, values, form_id=None, form_index=None):
+    result_type = type(html)
+    if isinstance(html, basestring):
+        doc = fromstring(html)
+    else:
+        doc = copy.deepcopy(html)
+    fill_form(doc, values, form_id=form_id, form_index=form_index)
+    return _transform_result(result_type, doc)
+
+def _fill_form(el, values):
+    counts = {}
+    if hasattr(values, 'mixed'):
+        # For Paste request parameters
+        values = values.mixed()
+    inputs = _input_xpath(el)
+    for input in inputs:
+        name = input.get('name')
+        if not name:
+            continue
+        if _takes_multiple(input):
+            value = values.get(name, [])
+            if not isinstance(value, (list, tuple)):
+                value = [value]
+            _fill_multiple(input, value)
+        elif name not in values:
+            continue
+        else:
+            index = counts.get(name, 0)
+            counts[name] = index + 1
+            value = values[name]
+            if isinstance(value, (list, tuple)):
+                try:
+                    value = value[index]
+                except IndexError:
+                    continue
+            elif index > 0:
+                continue
+            _fill_single(input, value)
+
+def _takes_multiple(input):
+    if _nons(input.tag) == 'select' and input.get('multiple'):
+        # FIXME: multiple="0"?
+        return True
+    type = input.get('type', '').lower()
+    if type in ('radio', 'checkbox'):
+        return True
+    return False
+
+def _fill_multiple(input, value):
+    type = input.get('type', '').lower()
+    if type == 'checkbox':
+        v = input.get('value')
+        if v is None:
+            if not value:
+                result = False
+            else:
+                result = value[0]
+                if isinstance(value, basestring):
+                    # The only valid "on" value for an unnamed checkbox is 'on'
+                    result = result == 'on'
+            _check(input, result)
+        else:
+            _check(input, v in value)
+    elif type == 'radio':
+        v = input.get('value')
+        _check(input, v in value)
+    else:
+        assert _nons(input.tag) == 'select'
+        for option in _options_xpath(input):
+            v = option.get('value')
+            if v is None:
+                # This seems to be the default, at least on IE
+                # FIXME: but I'm not sure
+                v = option.text_content()
+            _select(option, v in value)
+
+def _check(el, check):
+    if check:
+        el.set('checked', '')
+    else:
+        if 'checked' in el.attrib:
+            del el.attrib['checked']
+
+def _select(el, select):
+    if select:
+        el.set('selected', '')
+    else:
+        if 'selected' in el.attrib:
+            del el.attrib['selected']
+
+def _fill_single(input, value):
+    if _nons(input.tag) == 'textarea':
+        input.text = value
+    else:
+        input.set('value', value)
+
+def _find_form(el, form_id=None, form_index=None):
+    if form_id is None and form_index is None:
+        forms = _forms_xpath(el)
+        for form in forms:
+            return form
+        raise FormNotFound(
+            "No forms in page")
+    if form_id is not None:
+        form = el.get_element_by_id(form_id)
+        if form is not None:
+            return form
+        forms = _form_name_xpath(el, name=form_id)
+        if forms:
+            return forms[0]
+        else:
+            raise FormNotFound(
+                "No form with the name or id of %r (forms: %s)"
+                % (id, ', '.join(_find_form_ids(el))))               
+    if form_index is not None:
+        forms = _forms_xpath(el)
+        try:
+            return forms[form_index]
+        except IndexError:
+            raise FormNotFound(
+                "There is no form with the index %r (%i forms found)"
+                % (form_index, len(forms)))
+
+def _find_form_ids(el):
+    forms = _forms_xpath(el)
+    if not forms:
+        yield '(no forms)'
+        return
+    for index, form in enumerate(forms):
+        if form.get('id'):
+            if form.get('name'):
+                yield '%s or %s' % (form.get('id'),
+                                     form.get('name'))
+            else:
+                yield form.get('id')
+        elif form.get('name'):
+            yield form.get('name')
+        else:
+            yield '(unnamed form %s)' % index
+
+############################################################
+## Error filling
+############################################################
+
+class DefaultErrorCreator:
+    insert_before = True
+    block_inside = True
+    error_container_tag = 'div'
+    error_message_class = 'error-message'
+    error_block_class = 'error-block'
+    default_message = "Invalid"
+
+    def __init__(self, **kw):
+        for name, value in kw.items():
+            if not hasattr(self, name):
+                raise TypeError(
+                    "Unexpected keyword argument: %s" % name)
+            setattr(self, name, value)
+
+    def __call__(self, el, is_block, message):
+        error_el = el.makeelement(self.error_container_tag)
+        if self.error_message_class:
+            error_el.set('class', self.error_message_class)
+        if is_block and self.error_block_class:
+            error_el.set('class', error_el.get('class', '')+' '+self.error_block_class)
+        if message is None or message == '':
+            message = self.default_message
+        if isinstance(message, ElementBase):
+            error_el.append(message)
+        else:
+            assert isinstance(message, basestring), (
+                "Bad message; should be a string or element: %r" % message)
+            error_el.text = message or self.default_message
+        if is_block and self.block_inside:
+            if self.insert_before:
+                error_el.tail = el.text
+                el.text = None
+                el.insert(0, error_el)
+            else:
+                el.append(error_el)
+        else:
+            parent = el.getparent()
+            pos = parent.index(el)
+            if self.insert_before:
+                parent.insert(pos, error_el)
+            else:
+                error_el.tail = el.tail
+                el.tail = None
+                parent.insert(pos+1, error_el)
+
+default_error_creator = DefaultErrorCreator()
+    
+
+def insert_errors(
+    el,
+    errors,
+    form_id=None,
+    form_index=None,
+    error_class="error",
+    error_creator=default_error_creator,
+    ):
+    el = _find_form(el, form_id=form_id, form_index=form_index)
+    for name, error in errors.items():
+        if error is None:
+            continue
+        for error_el, message in _find_elements_for_name(el, name, error):
+            assert isinstance(message, (basestring, type(None), ElementBase)), (
+                "Bad message: %r" % message)
+            _insert_error(error_el, message, error_class, error_creator)
+
+def insert_errors_html(html, values, **kw):
+    result_type = type(html)
+    if isinstance(html, basestring):
+        doc = fromstring(html)
+    else:
+        doc = copy.deepcopy(html)
+    insert_errors(doc, values, **kw)
+    return _transform_result(result_type, doc)
+
+def _insert_error(el, error, error_class, error_creator):
+    if _nons(el.tag) in defs.empty_tags or _nons(el.tag) == 'textarea':
+        is_block = False
+    else:
+        is_block = True
+    if _nons(el.tag) != 'form' and error_class:
+        _add_class(el, error_class)
+    if el.get('id'):
+        labels = _label_for_xpath(el, for_id=el.get('id'))
+        if labels:
+            for label in labels:
+                _add_class(label, error_class)
+    error_creator(el, is_block, error)
+
+def _add_class(el, class_name):
+    if el.get('class'):
+        el.set('class', el.get('class')+' '+class_name)
+    else:
+        el.set('class', class_name)
+
+def _find_elements_for_name(form, name, error):
+    if name is None:
+        # An error for the entire form
+        yield form, error
+        return
+    if name.startswith('#'):
+        # By id
+        el = form.get_element_by_id(name[1:])
+        if el is not None:
+            yield el, error
+        return
+    els = _name_xpath(form, name=name)
+    if not els:
+        # FIXME: should this raise an exception?
+        return
+    if not isinstance(error, (list, tuple)):
+        yield els[0], error
+        return
+    # FIXME: if error is longer than els, should it raise an error?
+    for el, err in zip(els, error):
+        if err is None:
+            continue
+        yield el, err

lxml/html/html5parser.py

@@ -0,0 +1,260 @@
+"""
+An interface to html5lib that mimics the lxml.html interface.
+"""
+import sys
+import string
+
+from html5lib import HTMLParser as _HTMLParser
+from html5lib.treebuilders.etree_lxml import TreeBuilder
+from lxml import etree
+from lxml.html import Element, XHTML_NAMESPACE, _contains_block_level_tag
+
+# python3 compatibility
+try:
+    _strings = basestring
+except NameError:
+    _strings = (bytes, str)
+try:
+    from urllib2 import urlopen
+except ImportError:
+    from urllib.request import urlopen
+try:
+    from urlparse import urlparse
+except ImportError:
+    from urllib.parse import urlparse
+
+
+class HTMLParser(_HTMLParser):
+    """An html5lib HTML parser with lxml as tree."""
+
+    def __init__(self, strict=False, **kwargs):
+        _HTMLParser.__init__(self, strict=strict, tree=TreeBuilder, **kwargs)
+
+
+try:
+    from html5lib import XHTMLParser as _XHTMLParser
+except ImportError:
+    pass
+else:
+    class XHTMLParser(_XHTMLParser):
+        """An html5lib XHTML Parser with lxml as tree."""
+
+        def __init__(self, strict=False, **kwargs):
+            _XHTMLParser.__init__(self, strict=strict, tree=TreeBuilder, **kwargs)
+
+    xhtml_parser = XHTMLParser()
+
+
+def _find_tag(tree, tag):
+    elem = tree.find(tag)
+    if elem is not None:
+        return elem
+    return tree.find('{%s}%s' % (XHTML_NAMESPACE, tag))
+
+
+def document_fromstring(html, guess_charset=None, parser=None):
+    """
+    Parse a whole document into a string.
+
+    If `guess_charset` is true, or if the input is not Unicode but a
+    byte string, the `chardet` library will perform charset guessing
+    on the string.
+    """
+    if not isinstance(html, _strings):
+        raise TypeError('string required')
+
+    if parser is None:
+        parser = html_parser
+
+    options = {}
+    if guess_charset is None and isinstance(html, bytes):
+        # html5lib does not accept useChardet as an argument, if it
+        # detected the html argument would produce unicode objects.
+        guess_charset = True
+    if guess_charset is not None:
+        options['useChardet'] = guess_charset
+    return parser.parse(html, **options).getroot()
+
+
+def fragments_fromstring(html, no_leading_text=False,
+                         guess_charset=None, parser=None):
+    """Parses several HTML elements, returning a list of elements.
+
+    The first item in the list may be a string.  If no_leading_text is true,
+    then it will be an error if there is leading text, and it will always be
+    a list of only elements.
+
+    If `guess_charset` is true, the `chardet` library will perform charset
+    guessing on the string.
+    """
+    if not isinstance(html, _strings):
+        raise TypeError('string required')
+
+    if parser is None:
+        parser = html_parser
+
+    options = {}
+    if guess_charset is None and isinstance(html, bytes):
+        # html5lib does not accept useChardet as an argument, if it
+        # detected the html argument would produce unicode objects.
+        guess_charset = False
+    if guess_charset is not None:
+        options['useChardet'] = guess_charset
+    children = parser.parseFragment(html, 'div', **options)
+    if children and isinstance(children[0], _strings):
+        if no_leading_text:
+            if children[0].strip():
+                raise etree.ParserError('There is leading text: %r' %
+                                        children[0])
+            del children[0]
+    return children
+
+
+def fragment_fromstring(html, create_parent=False,
+                        guess_charset=None, parser=None):
+    """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 allowed.
+
+    If `guess_charset` is true, the `chardet` library will perform charset
+    guessing on the string.
+    """
+    if not isinstance(html, _strings):
+        raise TypeError('string required')
+
+    accept_leading_text = bool(create_parent)
+
+    elements = fragments_fromstring(
+        html, guess_charset=guess_charset, parser=parser,
+        no_leading_text=not accept_leading_text)
+
+    if create_parent:
+        if not isinstance(create_parent, _strings):
+            create_parent = 'div'
+        new_root = Element(create_parent)
+        if elements:
+            if isinstance(elements[0], _strings):
+                new_root.text = elements[0]
+                del elements[0]
+            new_root.extend(elements)
+        return new_root
+
+    if not elements:
+        raise etree.ParserError('No elements found')
+    if len(elements) > 1:
+        raise etree.ParserError('Multiple elements found')
+    result = elements[0]
+    if result.tail and result.tail.strip():
+        raise etree.ParserError('Element followed by text: %r' % result.tail)
+    result.tail = None
+    return result
+
+
+def fromstring(html, guess_charset=None, parser=None):
+    """Parse the html, returning a single element/document.
+
+    This tries to minimally parse the chunk of text, without knowing if it
+    is a fragment or a document.
+
+    'base_url' will set the document's base_url attribute (and the tree's
+    docinfo.URL)
+
+    If `guess_charset` is true, or if the input is not Unicode but a
+    byte string, the `chardet` library will perform charset guessing
+    on the string.
+    """
+    if not isinstance(html, _strings):
+        raise TypeError('string required')
+    doc = document_fromstring(html, parser=parser,
+                              guess_charset=guess_charset)
+
+    # document starts with doctype or <html>, full document!
+    start = html[:50]
+    if isinstance(start, bytes):
+        # Allow text comparison in python3.
+        # Decode as ascii, that also covers latin-1 and utf-8 for the
+        # characters we need.
+        start = start.decode('ascii', 'replace')
+
+    start = start.lstrip().lower()
+    if start.startswith('<html') or start.startswith('<!doctype'):
+        return doc
+
+    head = _find_tag(doc, 'head')
+
+    # if the head is not empty we have a full document
+    if len(head):
+        return doc
+
+    body = _find_tag(doc, 'body')
+
+    # The body has just one element, so it was probably a single
+    # element passed in
+    if (len(body) == 1 and (not body.text or not body.text.strip())
+        and (not body[-1].tail or not body[-1].tail.strip())):
+        return body[0]
+
+    # Now we have a body which represents a bunch of tags which have the
+    # content that was passed in.  We will create a fake container, which
+    # is the body tag, except <body> implies too much structure.
+    if _contains_block_level_tag(body):
+        body.tag = 'div'
+    else:
+        body.tag = 'span'
+    return body
+
+
+def parse(filename_url_or_file, guess_charset=None, parser=None):
+    """Parse a filename, URL, or file-like object into an HTML document
+    tree.  Note: this returns a tree, not an element.  Use
+    ``parse(...).getroot()`` to get the document root.
+
+    If ``guess_charset`` is true, the ``useChardet`` option is passed into
+    html5lib to enable character detection.  This option is on by default
+    when parsing from URLs, off by default when parsing from file(-like)
+    objects (which tend to return Unicode more often than not), and on by
+    default when parsing from a file path (which is read in binary mode).
+    """
+    if parser is None:
+        parser = html_parser
+    if not isinstance(filename_url_or_file, _strings):
+        fp = filename_url_or_file
+        if guess_charset is None:
+            # assume that file-like objects return Unicode more often than bytes
+            guess_charset = False
+    elif _looks_like_url(filename_url_or_file):
+        fp = urlopen(filename_url_or_file)
+        if guess_charset is None:
+            # assume that URLs return bytes
+            guess_charset = True
+    else:
+        fp = open(filename_url_or_file, 'rb')
+        if guess_charset is None:
+            guess_charset = True
+
+    options = {}
+    # html5lib does not accept useChardet as an argument, if it
+    # detected the html argument would produce unicode objects.
+    if guess_charset:
+        options['useChardet'] = guess_charset
+    return parser.parse(fp, **options)
+
+
+def _looks_like_url(str):
+    scheme = urlparse(str)[0]
+    if not scheme:
+        return False
+    elif (sys.platform == 'win32' and
+            scheme in string.ascii_letters
+            and len(scheme) == 1):
+        # looks like a 'normal' absolute path
+        return False
+    else:
+        return True
+
+
+html_parser = HTMLParser()