\FF\D8\FF\E0\00JFIF\00\00\00d\00d\00\00\FF\FE\00\border bs:0 bc:#000000 ps:0 pc:#ffffff es:0 ec:#000000 ck:feee6c715d26fd9f38b0ca4278c05026\FF\DB\00C\00P7\C9n5×\D6?\BDê\9Ds\EBp\9F[`8m\B7)o\B5\E8\E6I\99\FE3]]A2\BA\8Cw\D6E\93\\DEv\C8\009\F2\F1NI?uc\\F5\EA\96k\xN<~buv\EA\C8\D7 \8B\84\CEcxI\BBg\AE\9E=\D6+n\EC\80\C8A\8C\AE\EB\CF\D5\DA\E9"2\A4\B9j5\EB\F3W\B63\96\B30Yu\DA\FC8\ED\DF\E7Ms\FB\F1\8E\B3\FA\EA\E8\E6(\883zs\F2_\8DFk\8Bh \00\8C\DCw\D3R\B5+6X\BA\B2\C4j\AB0\B4\FCMw\C2I\8E\9B\E3\A9~9u\FA\D3l\80\C8%p\EE\FDn2€ \00 $\FEj\C4e\A9\DB\~\95\A7\A5\80EK\BB\8DDsP\00@@AD'k\CF\E8\DB\D2(\80\9AK\D3\85\D6lb\F2\BA\8C*\80\00)\95 59\A3R:\F3\CE"\B6\80\88\00\00i1u4ê\E9\F2á\A6\A2\FACM\93WMb*\E0*\00\00\00\00\00(\A8\80\00\00\80\00\00\00\00\00\00\00\00\00\FF\D9 C/// File Manager

File Manager

Path: /lib64/python2.7/site-packages/lxml/html/

Viewing File: 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)