Python lxml.html.Element() Examples

def get_user_rating(username, data):
    if not data:
        element = Element('span')
        element.text = username
        return element

    rating = data[1]
    element = Element('a', {'class': 'rate-group', 'href': reverse('user_page', args=[username])})
    if rating:
        rating_css = rating_class(rating)
        rate_box = Element('span', {'class': 'rate-box ' + rating_css})
        rate_box.append(Element('span', {'style': 'height: %3.fem' % rating_progress(rating)}))
        user = Element('span', {'class': 'rating ' + rating_css})
        user.text = username
        element.append(rate_box)
        element.append(user)
    else:
        element.text = username
    return element 

def __init__(self, str):
        try:
            self._tree = html.fromstring(str, parser=html.HTMLParser(recover=True))
        except (XMLSyntaxError, ParserError) as e:
            if str and (not isinstance(e, ParserError) or e.args[0] != 'Document is empty'):
                logger.exception('Failed to parse HTML string')
            self._tree = html.Element('div') 

def get_user(username, data):
    if not data:
        element = Element('span')
        element.text = username
        return element

    element = Element('span', {'class': Profile.get_user_css_class(*data)})
    link = Element('a', {'href': reverse('user_page', args=[username])})
    link.text = username
    element.append(link)
    return element 

def lazy_load(tree):
    blank = static('blank.gif')
    for img in tree.xpath('.//img'):
        src = img.get('src', '')
        if src.startswith('data') or '-math' in img.get('class', ''):
            continue
        noscript = html.Element('noscript')
        copy = deepcopy(img)
        copy.tail = ''
        noscript.append(copy)
        img.addprevious(noscript)
        img.set('data-src', src)
        img.set('src', blank)
        img.set('class', img.get('class') + ' unveil' if img.get('class') else 'unveil') 

def fragments_to_tree(fragment):
    tree = html.Element('div')
    try:
        parsed = html.fragments_fromstring(fragment, parser=html.HTMLParser(recover=True))
    except (XMLSyntaxError, ParserError) as e:
        if fragment and (not isinstance(e, ParserError) or e.args[0] != 'Document is empty'):
            logger.exception('Failed to parse HTML string')
        return tree

    if parsed and isinstance(parsed[0], str):
        tree.text = parsed[0]
        parsed = parsed[1:]
    tree.extend(parsed)
    return tree 

def fragment_fromstring(html, create_parent=False,
                        guess_charset=False, 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 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 fragment_fromstring(html, create_parent=False,
                        guess_charset=False, 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 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 fragment_fromstring(html, create_parent=False,
                        guess_charset=False, 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 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 fragment_fromstring(html, create_parent=False,
                        guess_charset=False, 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 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 fragment_fromstring(html, create_parent=False,
                        guess_charset=False, 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 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 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 parse_rsc_html(htmlstring):
    """Messy RSC HTML needs this special parser to fix problems before creating selector."""
    converted = UnicodeDammit(htmlstring)
    if not converted.unicode_markup:
        raise UnicodeDecodeError('Failed to detect encoding, tried [%s]')
    root = fromstring(htmlstring, parser=HTMLParser(recover=True, encoding=converted.original_encoding))
    # Add p.otherpara tags around orphan text
    newp = None
    for child in root.get_element_by_id('wrapper'):
        if newp is not None:
            if child.tag in BLOCK_ELEMENTS or child.get('id', '').startswith('sect') or child.getnext() is None:
                child.addprevious(newp)
                newp = None
            else:
                newp.append(child)
        if newp is None and child.tag in BLOCK_ELEMENTS and child.tail and child.tail.strip():
            newp = Element('p', **{'class': 'otherpara'})
            newp.text = child.tail
            child.tail = ''
    return root 

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 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