File Manager

Hackfut Security File Manager

Current Path: /opt/alt/python27/lib64/python2.7/site-packages/lxml/html

opt / alt / python27 / lib64 / python2.7 / site-packages / lxml / html /

📁 ..
📄 ElementSoup.py(319 B)
📄 ElementSoup.pyc(648 B)
📄 ElementSoup.pyo(648 B)
📄 __init__.py(57.73 KB)
📄 __init__.pyc(61.3 KB)
📄 __init__.pyo(61.05 KB)
📄 _diffcommand.py(2.04 KB)
📄 _diffcommand.pyc(2.85 KB)
📄 _diffcommand.pyo(2.85 KB)
📄 _html5builder.py(3.17 KB)
📄 _html5builder.pyc(4.68 KB)
📄 _html5builder.pyo(4.68 KB)
📄 _setmixin.py(2.43 KB)
📄 _setmixin.pyc(5.39 KB)
📄 _setmixin.pyo(5.39 KB)
📄 builder.py(4.21 KB)
📄 builder.pyc(3.86 KB)
📄 builder.pyo(3.86 KB)
📄 clean.py(25.25 KB)
📄 clean.pyc(19.27 KB)
📄 clean.pyo(19.17 KB)
📄 defs.py(4.15 KB)
📄 defs.pyc(3.93 KB)
📄 defs.pyo(3.93 KB)
📄 diff.py(29.79 KB)
📄 diff.pyc(28.94 KB)
📄 diff.pyo(28.6 KB)
📄 formfill.py(9.49 KB)
📄 formfill.pyc(9.99 KB)
📄 formfill.pyo(9.74 KB)
📄 html5parser.py(6.09 KB)
📄 html5parser.pyc(6.71 KB)
📄 html5parser.pyo(6.71 KB)
📄 soupparser.py(4.26 KB)
📄 soupparser.pyc(4.92 KB)
📄 soupparser.pyo(4.92 KB)
📄 usedoctest.py(249 B)
📄 usedoctest.pyc(477 B)
📄 usedoctest.pyo(477 B)

Editing: soupparser.py

__doc__ = """External interface to the BeautifulSoup HTML parser.
"""

__all__ = ["fromstring", "parse", "convert_tree"]

from lxml import etree, html
from BeautifulSoup import \
     BeautifulSoup, Tag, Comment, ProcessingInstruction, NavigableString

def fromstring(data, beautifulsoup=None, makeelement=None, **bsargs):
    """Parse a string of HTML data into an Element tree using the
    BeautifulSoup parser.

Returns the root ``<html>`` Element of the tree.

You can pass a different BeautifulSoup parser through the
    `beautifulsoup` keyword, and a diffent Element factory function
    through the `makeelement` keyword.  By default, the standard
    ``BeautifulSoup`` class and the default factory of `lxml.html` are
    used.
    """
    return _parse(data, beautifulsoup, makeelement, **bsargs)

def parse(file, beautifulsoup=None, makeelement=None, **bsargs):
    """Parse a file into an ElemenTree using the BeautifulSoup parser.

You can pass a different BeautifulSoup parser through the
    `beautifulsoup` keyword, and a diffent Element factory function
    through the `makeelement` keyword.  By default, the standard
    ``BeautifulSoup`` class and the default factory of `lxml.html` are
    used.
    """
    if not hasattr(file, 'read'):
        file = open(file)
    root = _parse(file, beautifulsoup, makeelement, **bsargs)
    return etree.ElementTree(root)

def convert_tree(beautiful_soup_tree, makeelement=None):
    """Convert a BeautifulSoup tree to a list of Element trees.

Returns a list instead of a single root Element to support
    HTML-like soup with more than one root element.

You can pass a different Element factory through the `makeelement`
    keyword.
    """
    if makeelement is None:
        makeelement = html.html_parser.makeelement
    root = _convert_tree(beautiful_soup_tree, makeelement)
    children = root.getchildren()
    for child in children:
        root.remove(child)
    return children

# helpers

def _parse(source, beautifulsoup, makeelement, **bsargs):
    if beautifulsoup is None:
        beautifulsoup = BeautifulSoup
    if makeelement is None:
        makeelement = html.html_parser.makeelement
    if 'convertEntities' not in bsargs:
        bsargs['convertEntities'] = 'html'
    tree = beautifulsoup(source, **bsargs)
    root = _convert_tree(tree, makeelement)
    # from ET: wrap the document in a html root element, if necessary
    if len(root) == 1 and root[0].tag == "html":
        return root[0]
    root.tag = "html"
    return root

def _convert_tree(beautiful_soup_tree, makeelement):
    root = makeelement(beautiful_soup_tree.name,
                       attrib=dict(beautiful_soup_tree.attrs))
    _convert_children(root, beautiful_soup_tree, makeelement)
    return root

def _convert_children(parent, beautiful_soup_tree, makeelement):
    SubElement = etree.SubElement
    et_child = None
    for child in beautiful_soup_tree:
        if isinstance(child, Tag):
            et_child = SubElement(parent, child.name, attrib=dict(
                [(k, unescape(v)) for (k,v) in child.attrs]))
            _convert_children(et_child, child, makeelement)
        elif type(child) is NavigableString:
            _append_text(parent, et_child, unescape(child))
        else:
            if isinstance(child, Comment):
                parent.append(etree.Comment(child))
            elif isinstance(child, ProcessingInstruction):
                parent.append(etree.ProcessingInstruction(
                    *child.split(' ', 1)))
            else: # CData
                _append_text(parent, et_child, unescape(child))

def _append_text(parent, element, text):
    if element is None:
        parent.text = (parent.text or '') + text
    else:
        element.tail = (element.tail or '') + text

# copied from ET's ElementSoup

try:
    from html.entities import name2codepoint # Python 3
except ImportError:
    from htmlentitydefs import name2codepoint
import re

handle_entities = re.compile("&(\w+);").sub

def unescape(string):
    if not string:
        return ''
    # work around oddities in BeautifulSoup's entity handling
    def unescape_entity(m):
        try:
            return unichr(name2codepoint[m.group(1)])
        except KeyError:
            return m.group(0) # use as is
    return handle_entities(unescape_entity, string)

Hackfut Security File Manager

Editing: soupparser.py

Upload File

Create Folder