FM / html

/usr/lib64/python2.6/site-packages/lxml/html/

/usr/lib64/python2.6/site-packages/lxml/html

Name	Size	Mode	Actions
builder.py	4310	0644	edit dl rm
builder.pyc	3918	0644	edit dl rm
builder.pyo	3918	0644	edit dl rm
clean.py	25017	0644	edit dl rm
clean.pyc	18900	0644	edit dl rm
clean.pyo	18799	0644	edit dl rm
defs.py	3800	0644	edit dl rm
defs.pyc	3578	0644	edit dl rm
defs.pyo	3578	0644	edit dl rm
diff.py	30375	0644	edit dl rm
diff.pyc	28696	0644	edit dl rm
diff.pyo	28346	0644	edit dl rm
ElementSoup.py	319	0644	edit dl rm
ElementSoup.pyc	622	0644	edit dl rm
ElementSoup.pyo	622	0644	edit dl rm
formfill.py	9761	0644	edit dl rm
formfill.pyc	10015	0644	edit dl rm
formfill.pyo	9761	0644	edit dl rm
html5parser.py	5304	0644	edit dl rm
html5parser.pyc	5870	0644	edit dl rm
html5parser.pyo	5870	0644	edit dl rm
soupparser.py	4275	0644	edit dl rm
soupparser.pyc	4831	0644	edit dl rm
soupparser.pyo	4831	0644	edit dl rm
usedoctest.py	249	0644	edit dl rm
usedoctest.pyc	464	0644	edit dl rm
usedoctest.pyo	464	0644	edit dl rm
_dictmixin.py	3539	0644	edit dl rm
_dictmixin.pyc	4688	0644	edit dl rm
_dictmixin.pyo	4688	0644	edit dl rm
_diffcommand.py	2082	0644	edit dl rm
_diffcommand.pyc	2856	0644	edit dl rm
_diffcommand.pyo	2856	0644	edit dl rm
_html5builder.py	3124	0644	edit dl rm
_html5builder.pyc	4498	0644	edit dl rm
_html5builder.pyo	4498	0644	edit dl rm
_setmixin.py	2488	0644	edit dl rm
_setmixin.pyc	5194	0644	edit dl rm
_setmixin.pyo	5194	0644	edit dl rm
__init__.py	52137	0644	edit dl rm
__init__.pyc	56364	0644	edit dl rm
__init__.pyo	56110	0644	edit dl rm

Edit: /usr/lib64/python2.6/site-packages/lxml/html/soupparser.py (4275B)

__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

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)

cmd: