See the HTML 2.0 specification:
http://www.w3.org/hypertext/WWW/MarkUp/html-spec/html-spec_toc.html
from warnings import warnpy3k
warnpy3k("the htmllib module has been removed in Python 3.0",
from formatter import AS_IS
__all__ = ["HTMLParser", "HTMLParseError"]
class HTMLParseError(sgmllib.SGMLParseError):
"""Error raised when an HTML document can't be parsed."""
class HTMLParser(sgmllib.SGMLParser):
"""This is the basic HTML parser class.
It supports all entity names required by the XHTML 1.0 Recommendation.
It also defines handlers for all HTML 2.0 and many HTML 3.0 and 3.2
from htmlentitydefs import entitydefs
def __init__(self, formatter, verbose=0):
"""Creates an instance of the HTMLParser class.
The formatter parameter is the formatter instance associated with
sgmllib.SGMLParser.__init__(self, verbose)
self.formatter = formatter
def error(self, message):
raise HTMLParseError(message)
sgmllib.SGMLParser.reset(self)
# ------ Methods used internally; some may be overridden
# --- Formatter interface, taking care of 'savedata' mode;
# shouldn't need to be overridden
def handle_data(self, data):
if self.savedata is not None:
self.savedata = self.savedata + data
self.formatter.add_literal_data(data)
self.formatter.add_flowing_data(data)
# --- Hooks to save data; shouldn't need to be overridden
"""Begins saving character data in a buffer instead of sending it
Retrieve the stored data via the save_end() method. Use of the
save_bgn() / save_end() pair may not be nested.
"""Ends buffering character data and returns all data saved since
the preceding call to the save_bgn() method.
If the nofill flag is false, whitespace is collapsed to single
spaces. A call to this method without a preceding call to the
save_bgn() method will raise a TypeError exception.
data = ' '.join(data.split())
# --- Hooks for anchors; should probably be overridden
def anchor_bgn(self, href, name, type):
"""This method is called at the start of an anchor region.
The arguments correspond to the attributes of the <A> tag with
the same names. The default implementation maintains a list of
hyperlinks (defined by the HREF attribute for <A> tags) within
the document. The list of hyperlinks is available as the data
self.anchorlist.append(href)
"""This method is called at the end of an anchor region.
The default implementation adds a textual footnote marker using an
index into the list of hyperlinks created by the anchor_bgn()method.
self.handle_data("[%d]" % len(self.anchorlist))
# --- Hook for images; should probably be overridden
def handle_image(self, src, alt, *args):
"""This method is called to handle images.
The default implementation simply passes the alt value to the
# --------- Top level elememts
def start_html(self, attrs): pass
def start_head(self, attrs): pass
def start_body(self, attrs): pass
def start_title(self, attrs):
self.title = self.save_end()
def do_base(self, attrs):
def do_isindex(self, attrs):
def do_link(self, attrs):
def do_meta(self, attrs):
def do_nextid(self, attrs): # Deprecated
def start_h1(self, attrs):
self.formatter.end_paragraph(1)
self.formatter.push_font(('h1', 0, 1, 0))
self.formatter.end_paragraph(1)
self.formatter.pop_font()
def start_h2(self, attrs):
self.formatter.end_paragraph(1)
self.formatter.push_font(('h2', 0, 1, 0))
self.formatter.end_paragraph(1)
self.formatter.pop_font()
def start_h3(self, attrs):
self.formatter.end_paragraph(1)
self.formatter.push_font(('h3', 0, 1, 0))
self.formatter.end_paragraph(1)
self.formatter.pop_font()
def start_h4(self, attrs):
self.formatter.end_paragraph(1)
self.formatter.push_font(('h4', 0, 1, 0))
self.formatter.end_paragraph(1)
self.formatter.pop_font()
def start_h5(self, attrs):
self.formatter.end_paragraph(1)
self.formatter.push_font(('h5', 0, 1, 0))
self.formatter.end_paragraph(1)
self.formatter.pop_font()
def start_h6(self, attrs):
self.formatter.end_paragraph(1)
self.formatter.push_font(('h6', 0, 1, 0))
self.formatter.end_paragraph(1)
self.formatter.pop_font()
# --- Block Structuring Elements
self.formatter.end_paragraph(1)
def start_pre(self, attrs):
self.formatter.end_paragraph(1)
self.formatter.push_font((AS_IS, AS_IS, AS_IS, 1))
self.nofill = self.nofill + 1
self.formatter.end_paragraph(1)
self.formatter.pop_font()
self.nofill = max(0, self.nofill - 1)
def start_xmp(self, attrs):
self.setliteral('xmp') # Tell SGML parser
def start_listing(self, attrs):
self.setliteral('listing') # Tell SGML parser
def start_address(self, attrs):
self.formatter.end_paragraph(0)
self.formatter.push_font((AS_IS, 1, AS_IS, AS_IS))
self.formatter.end_paragraph(0)
self.formatter.pop_font()
def start_blockquote(self, attrs):
self.formatter.end_paragraph(1)
self.formatter.push_margin('blockquote')
def end_blockquote(self):
self.formatter.end_paragraph(1)
self.formatter.pop_margin()
def start_ul(self, attrs):
self.formatter.end_paragraph(not self.list_stack)
self.formatter.push_margin('ul')
self.list_stack.append(['ul', '*', 0])
if self.list_stack: del self.list_stack[-1]
self.formatter.end_paragraph(not self.list_stack)
self.formatter.pop_margin()
self.formatter.end_paragraph(0)
[dummy, label, counter] = top = self.list_stack[-1]
top[2] = counter = counter+1
self.formatter.add_label_data(label, counter)
def start_ol(self, attrs):
self.formatter.end_paragraph(not self.list_stack)
self.formatter.push_margin('ol')
if len(v) == 1: v = v + '.'
self.list_stack.append(['ol', label, 0])
if self.list_stack: del self.list_stack[-1]
self.formatter.end_paragraph(not self.list_stack)
self.formatter.pop_margin()
def start_menu(self, attrs):
def start_dir(self, attrs):
def start_dl(self, attrs):
self.formatter.end_paragraph(1)
self.list_stack.append(['dl', '', 0])
if self.list_stack: del self.list_stack[-1]
self.formatter.push_margin('dd')
self.list_stack.append(['dd', '', 0])
self.formatter.end_paragraph(bl)
if self.list_stack[-1][0] == 'dd':
self.formatter.pop_margin()
def start_cite(self, attrs): self.start_i(attrs)
def end_cite(self): self.end_i()
def start_code(self, attrs): self.start_tt(attrs)
def end_code(self): self.end_tt()
def start_em(self, attrs): self.start_i(attrs)
def end_em(self): self.end_i()
def start_kbd(self, attrs): self.start_tt(attrs)
def end_kbd(self): self.end_tt()
def start_samp(self, attrs): self.start_tt(attrs)
def end_samp(self): self.end_tt()
def start_strong(self, attrs): self.start_b(attrs)
def end_strong(self): self.end_b()
def start_var(self, attrs): self.start_i(attrs)
def end_var(self): self.end_i()
def start_i(self, attrs):
self.formatter.push_font((AS_IS, 1, AS_IS, AS_IS))
self.formatter.pop_font()
def start_b(self, attrs):
self.formatter.push_font((AS_IS, AS_IS, 1, AS_IS))
self.formatter.pop_font()
def start_tt(self, attrs):
self.formatter.push_font((AS_IS, AS_IS, AS_IS, 1))
self.formatter.pop_font()
def start_a(self, attrs):
for attrname, value in attrs:
self.anchor_bgn(href, name, type)
self.formatter.add_line_break()
self.formatter.add_hor_rule()
for attrname, value in attrs:
self.handle_image(src, alt, ismap, align, width, height)
# --- Really Old Unofficial Deprecated Stuff
def do_plaintext(self, attrs):
self.setnomoretags() # Tell SGML parser
def unknown_starttag(self, tag, attrs):
def unknown_endtag(self, tag):
silent = args and args[0] == '-s'
f = formatter.NullFormatter()
f = formatter.AbstractFormatter(formatter.DumbWriter())
if __name__ == '__main__':
It is recommended that you Edit text format, this type of Fix handles quite a lot in one request
