Function plaintext

pattern/web/__init__.py:880–906

Returns a string with all HTML tags removed. Content inside HTML comments, the tag and the tags is removed. - keep : a list of tags to keep. Element attributes are stripped. To preserve attributes a dict of (tag name, [attribute])-item

(html, keep=[], replace=blocks, linebreaks=2, indentation=False)

    return string

def plaintext(html, keep=[], replace=blocks, linebreaks=2, indentation=False):
    """ Returns a string with all HTML tags removed.
        Content inside HTML comments, the <style> tag and the <script> tags is removed.
        - keep        : a list of tags to keep. Element attributes are stripped.
                        To preserve attributes a dict of (tag name, [attribute])-items can be given.
        - replace     : a dictionary of (tag name, (replace_before, replace_after))-items.
                        By default, block-level elements are followed by linebreaks.
        - linebreaks  : the maximum amount of consecutive linebreaks,
        - indentation : keep left line indentation (tabs and spaces)?
    """
    if not keep.__contains__("script"):
        html = strip_javascript(html)
    if not keep.__contains__("style"):
        html = strip_inline_css(html)
    if not keep.__contains__("form"):
        html = strip_forms(html)
    if not keep.__contains__("comment") and \
       not keep.__contains__("!--"):
        html = strip_comments(html)
    html = html.replace("\r", "\n")
    html = strip_tags(html, exclude=keep, replace=replace)
    html = decode_entities(html)
    html = collapse_spaces(html, indentation)
    html = collapse_tabs(html, indentation)
    html = collapse_linebreaks(html, linebreaks)
    html = html.strip()
    return html

#### SEARCH ENGINE #################################################################################