/usr/share/doc/python3-docs/html/_sources/library/

/usr/share/doc/python3-docs/html/_sources/library

Name	Size	Mode	Actions
2to3.rst.txt	15898	0644	edit dl rm
abc.rst.txt	11805	0644	edit dl rm
aifc.rst.txt	7503	0644	edit dl rm
allos.rst.txt	678	0644	edit dl rm
archiving.rst.txt	440	0644	edit dl rm
argparse.rst.txt	77480	0644	edit dl rm
array.rst.txt	10812	0644	edit dl rm
ast.rst.txt	10159	0644	edit dl rm
asynchat.rst.txt	8528	0644	edit dl rm
asyncio-dev.rst.txt	13398	0644	edit dl rm
asyncio-eventloop.rst.txt	33701	0644	edit dl rm
asyncio-eventloops.rst.txt	7660	0644	edit dl rm
asyncio-protocol.rst.txt	25170	0644	edit dl rm
asyncio-queue.rst.txt	4328	0644	edit dl rm
asyncio-stream.rst.txt	14363	0644	edit dl rm
asyncio-subprocess.rst.txt	15544	0644	edit dl rm
asyncio-sync.rst.txt	9078	0644	edit dl rm
asyncio-task.rst.txt	25406	0644	edit dl rm
asyncio.rst.txt	2272	0644	edit dl rm
asyncore.rst.txt	13624	0644	edit dl rm
atexit.rst.txt	3669	0644	edit dl rm
audioop.rst.txt	10712	0644	edit dl rm
base64.rst.txt	10371	0644	edit dl rm
bdb.rst.txt	12985	0644	edit dl rm
binary.rst.txt	654	0644	edit dl rm
binascii.rst.txt	6539	0644	edit dl rm
binhex.rst.txt	1709	0644	edit dl rm
bisect.rst.txt	5398	0644	edit dl rm
builtins.rst.txt	1465	0644	edit dl rm
bz2.rst.txt	8825	0644	edit dl rm
calendar.rst.txt	10988	0644	edit dl rm
cgi.rst.txt	22650	0644	edit dl rm
cgitb.rst.txt	2918	0644	edit dl rm
chunk.rst.txt	5094	0644	edit dl rm
cmath.rst.txt	9326	0644	edit dl rm
cmd.rst.txt	13795	0644	edit dl rm
code.rst.txt	7817	0644	edit dl rm
codecs.rst.txt	75564	0644	edit dl rm
codeop.rst.txt	3021	0644	edit dl rm
collections.abc.rst.txt	12861	0644	edit dl rm
collections.rst.txt	46063	0644	edit dl rm
colorsys.rst.txt	1820	0644	edit dl rm
compileall.rst.txt	8975	0644	edit dl rm
concurrency.rst.txt	673	0644	edit dl rm
concurrent.futures.rst.txt	16910	0644	edit dl rm
concurrent.rst.txt	171	0644	edit dl rm
configparser.rst.txt	48756	0644	edit dl rm
constants.rst.txt	3331	0644	edit dl rm
contextlib.rst.txt	28175	0644	edit dl rm
copy.rst.txt	3378	0644	edit dl rm
copyreg.rst.txt	2182	0644	edit dl rm
crypt.rst.txt	5122	0644	edit dl rm
crypto.rst.txt	411	0644	edit dl rm
csv.rst.txt	19902	0644	edit dl rm
ctypes.rst.txt	88613	0644	edit dl rm
curses.ascii.rst.txt	8920	0644	edit dl rm
curses.panel.rst.txt	2764	0644	edit dl rm
curses.rst.txt	76397	0644	edit dl rm
custominterp.rst.txt	569	0644	edit dl rm
datatypes.rst.txt	751	0644	edit dl rm
datetime.rst.txt	90524	0644	edit dl rm
dbm.rst.txt	14293	0644	edit dl rm
debug.rst.txt	471	0644	edit dl rm
decimal.rst.txt	74869	0644	edit dl rm
development.rst.txt	704	0644	edit dl rm
difflib.rst.txt	29861	0644	edit dl rm
dis.rst.txt	32567	0644	edit dl rm
distribution.rst.txt	452	0644	edit dl rm
distutils.rst.txt	1974	0644	edit dl rm
doctest.rst.txt	71743	0644	edit dl rm
dummy_threading.rst.txt	784	0644	edit dl rm
email.charset.rst.txt	9293	0644	edit dl rm
email.compat32-message.rst.txt	33493	0644	edit dl rm
email.contentmanager.rst.txt	9112	0644	edit dl rm
email.encoders.rst.txt	2715	0644	edit dl rm
email.errors.rst.txt	4792	0644	edit dl rm
email.examples.rst.txt	1915	0644	edit dl rm
email.generator.rst.txt	13637	0644	edit dl rm
email.header.rst.txt	9188	0644	edit dl rm
email.headerregistry.rst.txt	17957	0644	edit dl rm
email.iterators.rst.txt	2795	0644	edit dl rm
email.message.rst.txt	33008	0644	edit dl rm
email.mime.rst.txt	11721	0644	edit dl rm
email.parser.rst.txt	14092	0644	edit dl rm
email.policy.rst.txt	27022	0644	edit dl rm
email.rst.txt	6785	0644	edit dl rm
email.util.rst.txt	9214	0644	edit dl rm
ensurepip.rst.txt	4987	0644	edit dl rm
enum.rst.txt	32751	0644	edit dl rm
errno.rst.txt	6811	0644	edit dl rm
exceptions.rst.txt	25570	0644	edit dl rm
faulthandler.rst.txt	6136	0644	edit dl rm
fcntl.rst.txt	7152	0644	edit dl rm
filecmp.rst.txt	5623	0644	edit dl rm
fileformats.rst.txt	287	0644	edit dl rm
fileinput.rst.txt	8051	0644	edit dl rm
filesys.rst.txt	961	0644	edit dl rm
fnmatch.rst.txt	3103	0644	edit dl rm
formatter.rst.txt	13242	0644	edit dl rm
fpectl.rst.txt	4180	0644	edit dl rm
fractions.rst.txt	6364	0644	edit dl rm
frameworks.rst.txt	391	0644	edit dl rm
ftplib.rst.txt	17552	0644	edit dl rm
functional.rst.txt	365	0644	edit dl rm
functions.rst.txt	71621	0644	edit dl rm
functools.rst.txt	18503	0644	edit dl rm
gc.rst.txt	9694	0644	edit dl rm
getopt.rst.txt	6557	0644	edit dl rm
getpass.rst.txt	1882	0644	edit dl rm
gettext.rst.txt	25588	0644	edit dl rm
glob.rst.txt	3508	0644	edit dl rm
grp.rst.txt	2417	0644	edit dl rm
gzip.rst.txt	8301	0644	edit dl rm
hashlib.rst.txt	26523	0644	edit dl rm
heapq.rst.txt	13402	0644	edit dl rm
hmac.rst.txt	4020	0644	edit dl rm
html.entities.rst.txt	1319	0644	edit dl rm
html.parser.rst.txt	11275	0644	edit dl rm
html.rst.txt	1304	0644	edit dl rm
http.client.rst.txt	18870	0644	edit dl rm
http.cookiejar.rst.txt	27832	0644	edit dl rm
http.cookies.rst.txt	8645	0644	edit dl rm
http.rst.txt	7096	0644	edit dl rm
http.server.rst.txt	17639	0644	edit dl rm
i18n.rst.txt	408	0644	edit dl rm
idle.rst.txt	25834	0644	edit dl rm
imaplib.rst.txt	20367	0644	edit dl rm
imghdr.rst.txt	2938	0644	edit dl rm
imp.rst.txt	15548	0644	edit dl rm
importlib.rst.txt	53563	0644	edit dl rm
index.rst.txt	2258	0644	edit dl rm
inspect.rst.txt	53928	0644	edit dl rm
internet.rst.txt	992	0644	edit dl rm
intro.rst.txt	2645	0644	edit dl rm
io.rst.txt	40328	0644	edit dl rm
ipaddress.rst.txt	32340	0644	edit dl rm
ipc.rst.txt	649	0644	edit dl rm
itertools.rst.txt	38459	0644	edit dl rm
json.rst.txt	27876	0644	edit dl rm
keyword.rst.txt	617	0644	edit dl rm
language.rst.txt	522	0644	edit dl rm
linecache.rst.txt	2408	0644	edit dl rm
locale.rst.txt	25470	0644	edit dl rm
logging.config.rst.txt	33886	0644	edit dl rm
logging.handlers.rst.txt	42497	0644	edit dl rm
logging.rst.txt	60479	0644	edit dl rm
lzma.rst.txt	17361	0644	edit dl rm
macpath.rst.txt	707	0644	edit dl rm
mailbox.rst.txt	63055	0644	edit dl rm
mailcap.rst.txt	3691	0644	edit dl rm
markup.rst.txt	679	0644	edit dl rm
marshal.rst.txt	4855	0644	edit dl rm
math.rst.txt	14375	0644	edit dl rm
mimetypes.rst.txt	9839	0644	edit dl rm
misc.rst.txt	247	0644	edit dl rm
mm.rst.txt	431	0644	edit dl rm
mmap.rst.txt	11232	0644	edit dl rm
modulefinder.rst.txt	3240	0644	edit dl rm
modules.rst.txt	355	0644	edit dl rm
msilib.rst.txt	18612	0644	edit dl rm
msvcrt.rst.txt	4392	0644	edit dl rm
multiprocessing.rst.txt	104494	0644	edit dl rm
netdata.rst.txt	339	0644	edit dl rm
netrc.rst.txt	3007	0644	edit dl rm
nis.rst.txt	1993	0644	edit dl rm
nntplib.rst.txt	21821	0644	edit dl rm
numbers.rst.txt	8089	0644	edit dl rm
numeric.rst.txt	696	0644	edit dl rm
operator.rst.txt	18989	0644	edit dl rm
optparse.rst.txt	76996	0644	edit dl rm
os.path.rst.txt	16419	0644	edit dl rm
os.rst.txt	137534	0644	edit dl rm
ossaudiodev.rst.txt	17845	0644	edit dl rm
othergui.rst.txt	2822	0644	edit dl rm
parser.rst.txt	15148	0644	edit dl rm
pathlib.rst.txt	30045	0644	edit dl rm
pdb.rst.txt	19454	0644	edit dl rm
persistence.rst.txt	591	0644	edit dl rm
pickle.rst.txt	37440	0644	edit dl rm
pickletools.rst.txt	3729	0644	edit dl rm
pipes.rst.txt	2557	0644	edit dl rm
pkgutil.rst.txt	8730	0644	edit dl rm
platform.rst.txt	9624	0644	edit dl rm
plistlib.rst.txt	7398	0644	edit dl rm
poplib.rst.txt	8197	0644	edit dl rm
posix.rst.txt	3694	0644	edit dl rm
pprint.rst.txt	14274	0644	edit dl rm
profile.rst.txt	27969	0644	edit dl rm
pty.rst.txt	3123	0644	edit dl rm
pwd.rst.txt	2739	0644	edit dl rm
pyclbr.rst.txt	3297	0644	edit dl rm
pydoc.rst.txt	4688	0644	edit dl rm
pyexpat.rst.txt	28620	0644	edit dl rm
python.rst.txt	475	0644	edit dl rm
py_compile.rst.txt	3851	0644	edit dl rm
queue.rst.txt	7268	0644	edit dl rm
quopri.rst.txt	2571	0644	edit dl rm
random.rst.txt	18503	0644	edit dl rm
re.rst.txt	64936	0644	edit dl rm
readline.rst.txt	11943	0644	edit dl rm
reprlib.rst.txt	5162	0644	edit dl rm
resource.rst.txt	12291	0644	edit dl rm
rlcompleter.rst.txt	2294	0644	edit dl rm
runpy.rst.txt	8285	0644	edit dl rm
sched.rst.txt	4842	0644	edit dl rm
secrets.rst.txt	5930	0644	edit dl rm
select.rst.txt	28175	0644	edit dl rm
selectors.rst.txt	8925	0644	edit dl rm
shelve.rst.txt	8390	0644	edit dl rm
shlex.rst.txt	16441	0644	edit dl rm
shutil.rst.txt	26014	0644	edit dl rm
signal.rst.txt	17218	0644	edit dl rm
site.rst.txt	9628	0644	edit dl rm
smtpd.rst.txt	10806	0644	edit dl rm
smtplib.rst.txt	23439	0644	edit dl rm
sndhdr.rst.txt	1994	0644	edit dl rm
socket.rst.txt	68202	0644	edit dl rm
socketserver.rst.txt	23712	0644	edit dl rm
spwd.rst.txt	2958	0644	edit dl rm
sqlite3.rst.txt	39215	0644	edit dl rm
ssl.rst.txt	96021	0644	edit dl rm
stat.rst.txt	9805	0644	edit dl rm
statistics.rst.txt	15301	0644	edit dl rm
stdtypes.rst.txt	179240	0644	edit dl rm
string.rst.txt	35374	0644	edit dl rm
stringprep.rst.txt	4279	0644	edit dl rm
struct.rst.txt	19581	0644	edit dl rm
subprocess.rst.txt	45793	0644	edit dl rm
sunau.rst.txt	7390	0644	edit dl rm
superseded.rst.txt	258	0644	edit dl rm
symbol.rst.txt	975	0644	edit dl rm
symtable.rst.txt	4964	0644	edit dl rm
sys.rst.txt	58273	0644	edit dl rm
sysconfig.rst.txt	8749	0644	edit dl rm
syslog.rst.txt	4302	0644	edit dl rm
tabnanny.rst.txt	2007	0644	edit dl rm
tarfile.rst.txt	31749	0644	edit dl rm
telnetlib.rst.txt	7899	0644	edit dl rm
tempfile.rst.txt	13857	0644	edit dl rm
termios.rst.txt	3751	0644	edit dl rm
test.rst.txt	25764	0644	edit dl rm
text.rst.txt	584	0644	edit dl rm
textwrap.rst.txt	10519	0644	edit dl rm
threading.rst.txt	39257	0644	edit dl rm
time.rst.txt	32967	0644	edit dl rm
timeit.rst.txt	13000	0644	edit dl rm
tk.rst.txt	1639	0644	edit dl rm
tkinter.rst.txt	33027	0644	edit dl rm
tkinter.scrolledtext.rst.txt	1255	0644	edit dl rm
tkinter.tix.rst.txt	22653	0644	edit dl rm
tkinter.ttk.rst.txt	58489	0644	edit dl rm
token.rst.txt	2607	0644	edit dl rm
tokenize.rst.txt	10002	0644	edit dl rm
trace.rst.txt	6914	0644	edit dl rm
traceback.rst.txt	17854	0644	edit dl rm
tracemalloc.rst.txt	22089	0644	edit dl rm
tty.rst.txt	1097	0644	edit dl rm
turtle.rst.txt	71221	0644	edit dl rm
types.rst.txt	9999	0644	edit dl rm
typing.rst.txt	34332	0644	edit dl rm
undoc.rst.txt	780	0644	edit dl rm
unicodedata.rst.txt	5762	0644	edit dl rm
unittest.mock-examples.rst.txt	46206	0644	edit dl rm
unittest.mock.rst.txt	85991	0644	edit dl rm
unittest.rst.txt	93304	0644	edit dl rm
unix.rst.txt	446	0644	edit dl rm
urllib.error.rst.txt	2199	0644	edit dl rm
urllib.parse.rst.txt	27332	0644	edit dl rm
urllib.request.rst.txt	59360	0644	edit dl rm
urllib.robotparser.rst.txt	2969	0644	edit dl rm
urllib.rst.txt	466	0644	edit dl rm
uu.rst.txt	2387	0644	edit dl rm
uuid.rst.txt	8760	0644	edit dl rm
venv.rst.txt	20621	0644	edit dl rm
warnings.rst.txt	20152	0644	edit dl rm
wave.rst.txt	6870	0644	edit dl rm
weakref.rst.txt	21328	0644	edit dl rm
webbrowser.rst.txt	9783	0644	edit dl rm
windows.rst.txt	272	0644	edit dl rm
winreg.rst.txt	24073	0644	edit dl rm
winsound.rst.txt	5134	0644	edit dl rm
wsgiref.rst.txt	33047	0644	edit dl rm
xdrlib.rst.txt	8078	0644	edit dl rm
xml.dom.minidom.rst.txt	10198	0644	edit dl rm
xml.dom.pulldom.rst.txt	5186	0644	edit dl rm
xml.dom.rst.txt	39507	0644	edit dl rm
xml.etree.elementtree.rst.txt	43871	0644	edit dl rm
xml.rst.txt	6071	0644	edit dl rm
xml.sax.handler.rst.txt	15399	0644	edit dl rm
xml.sax.reader.rst.txt	12133	0644	edit dl rm
xml.sax.rst.txt	7159	0644	edit dl rm
xml.sax.utils.rst.txt	3901	0644	edit dl rm
xmlrpc.client.rst.txt	23071	0644	edit dl rm
xmlrpc.rst.txt	475	0644	edit dl rm
xmlrpc.server.rst.txt	14990	0644	edit dl rm
zipapp.rst.txt	17392	0644	edit dl rm
zipfile.rst.txt	24005	0644	edit dl rm
zipimport.rst.txt	5805	0644	edit dl rm
zlib.rst.txt	13912	0644	edit dl rm
_dummy_thread.rst.txt	762	0644	edit dl rm
_thread.rst.txt	6886	0644	edit dl rm
__future__.rst.txt	5245	0644	edit dl rm
__main__.rst.txt	904	0644	edit dl rm

Edit: /usr/share/doc/python3-docs/html/_sources/library/html.parser.rst.txt (11275B)

:mod:`html.parser` --- Simple HTML and XHTML parser
===================================================

.. module:: html.parser
   :synopsis: A simple parser that can handle HTML and XHTML.

**Source code:** :source:`Lib/html/parser.py`

.. index::
   single: HTML
   single: XHTML

--------------

This module defines a class :class:`HTMLParser` which serves as the basis for
parsing text files formatted in HTML (HyperText Mark-up Language) and XHTML.

.. class:: HTMLParser(*, convert_charrefs=True)

Create a parser instance able to parse invalid markup.

If *convert_charrefs* is ``True`` (the default), all character
   references (except the ones in ``script``/``style`` elements) are
   automatically converted to the corresponding Unicode characters.

An :class:`.HTMLParser` instance is fed HTML data and calls handler methods
   when start tags, end tags, text, comments, and other markup elements are
   encountered.  The user should subclass :class:`.HTMLParser` and override its
   methods to implement the desired behavior.

This parser does not check that end tags match start tags or call the end-tag
   handler for elements which are closed implicitly by closing an outer element.

.. versionchanged:: 3.4
      *convert_charrefs* keyword argument added.

.. versionchanged:: 3.5
      The default value for argument *convert_charrefs* is now ``True``.

Example HTML Parser Application
-------------------------------

As a basic example, below is a simple HTML parser that uses the
:class:`HTMLParser` class to print out start tags, end tags, and data
as they are encountered::

from html.parser import HTMLParser

class MyHTMLParser(HTMLParser):
       def handle_starttag(self, tag, attrs):
           print("Encountered a start tag:", tag)

def handle_endtag(self, tag):
           print("Encountered an end tag :", tag)

def handle_data(self, data):
           print("Encountered some data  :", data)

parser = MyHTMLParser()
   parser.feed('<html><head><title>Test</title></head>'
               '<body><h1>Parse me!</h1></body></html>')

The output will then be:

.. code-block:: none

Encountered a start tag: html
   Encountered a start tag: head
   Encountered a start tag: title
   Encountered some data  : Test
   Encountered an end tag : title
   Encountered an end tag : head
   Encountered a start tag: body
   Encountered a start tag: h1
   Encountered some data  : Parse me!
   Encountered an end tag : h1
   Encountered an end tag : body
   Encountered an end tag : html

:class:`.HTMLParser` Methods
----------------------------

:class:`HTMLParser` instances have the following methods:

.. method:: HTMLParser.feed(data)

Feed some text to the parser.  It is processed insofar as it consists of
   complete elements; incomplete data is buffered until more data is fed or
   :meth:`close` is called.  *data* must be :class:`str`.

.. method:: HTMLParser.close()

Force processing of all buffered data as if it were followed by an end-of-file
   mark.  This method may be redefined by a derived class to define additional
   processing at the end of the input, but the redefined version should always call
   the :class:`HTMLParser` base class method :meth:`close`.

.. method:: HTMLParser.reset()

Reset the instance.  Loses all unprocessed data.  This is called implicitly at
   instantiation time.

.. method:: HTMLParser.getpos()

Return current line number and offset.

.. method:: HTMLParser.get_starttag_text()

Return the text of the most recently opened start tag.  This should not normally
   be needed for structured processing, but may be useful in dealing with HTML "as
   deployed" or for re-generating input with minimal changes (whitespace between
   attributes can be preserved, etc.).

The following methods are called when data or markup elements are encountered
and they are meant to be overridden in a subclass.  The base class
implementations do nothing (except for :meth:`~HTMLParser.handle_startendtag`):

.. method:: HTMLParser.handle_starttag(tag, attrs)

This method is called to handle the start of a tag (e.g. ``<div id="main">``).

The *tag* argument is the name of the tag converted to lower case. The *attrs*
   argument is a list of ``(name, value)`` pairs containing the attributes found
   inside the tag's ``<>`` brackets.  The *name* will be translated to lower case,
   and quotes in the *value* have been removed, and character and entity references
   have been replaced.

For instance, for the tag ``<A HREF="https://www.cwi.nl/">``, this method
   would be called as ``handle_starttag('a', [('href', 'https://www.cwi.nl/')])``.

All entity references from :mod:`html.entities` are replaced in the attribute
   values.

.. method:: HTMLParser.handle_endtag(tag)

This method is called to handle the end tag of an element (e.g. ``</div>``).

The *tag* argument is the name of the tag converted to lower case.

.. method:: HTMLParser.handle_startendtag(tag, attrs)

Similar to :meth:`handle_starttag`, but called when the parser encounters an
   XHTML-style empty tag (``<img ... />``).  This method may be overridden by
   subclasses which require this particular lexical information; the default
   implementation simply calls :meth:`handle_starttag` and :meth:`handle_endtag`.

.. method:: HTMLParser.handle_data(data)

This method is called to process arbitrary data (e.g. text nodes and the
   content of ``<script>...</script>`` and ``<style>...</style>``).

.. method:: HTMLParser.handle_entityref(name)

This method is called to process a named character reference of the form
   ``&name;`` (e.g. ``&gt;``), where *name* is a general entity reference
   (e.g. ``'gt'``).  This method is never called if *convert_charrefs* is
   ``True``.

.. method:: HTMLParser.handle_charref(name)

This method is called to process decimal and hexadecimal numeric character
   references of the form ``&#NNN;`` and ``&#xNNN;``.  For example, the decimal
   equivalent for ``&gt;`` is ``&#62;``, whereas the hexadecimal is ``&#x3E;``;
   in this case the method will receive ``'62'`` or ``'x3E'``.  This method
   is never called if *convert_charrefs* is ``True``.

.. method:: HTMLParser.handle_comment(data)

This method is called when a comment is encountered (e.g. ````).

For example, the comment ```` will cause this method to be
   called with the argument ``' comment '``.

The content of Internet Explorer conditional comments (condcoms) will also be
   sent to this method, so, for ````,
   this method will receive ``'[if IE 9]>IE9-specific content<![endif]'``.

.. method:: HTMLParser.handle_decl(decl)

This method is called to handle an HTML doctype declaration (e.g.
   ``<!DOCTYPE html>``).

The *decl* parameter will be the entire contents of the declaration inside
   the ``<!...>`` markup (e.g. ``'DOCTYPE html'``).

.. method:: HTMLParser.handle_pi(data)

Method called when a processing instruction is encountered.  The *data*
   parameter will contain the entire processing instruction. For example, for the
   processing instruction ``<?proc color='red'>``, this method would be called as
   ``handle_pi("proc color='red'")``.  It is intended to be overridden by a derived
   class; the base class implementation does nothing.

.. note::

The :class:`HTMLParser` class uses the SGML syntactic rules for processing
      instructions.  An XHTML processing instruction using the trailing ``'?'`` will
      cause the ``'?'`` to be included in *data*.

.. method:: HTMLParser.unknown_decl(data)

This method is called when an unrecognized declaration is read by the parser.

The *data* parameter will be the entire contents of the declaration inside
   the ``<![...]>`` markup.  It is sometimes useful to be overridden by a
   derived class.  The base class implementation does nothing.

.. _htmlparser-examples:

Examples
--------

The following class implements a parser that will be used to illustrate more
examples::

from html.parser import HTMLParser
   from html.entities import name2codepoint

class MyHTMLParser(HTMLParser):
       def handle_starttag(self, tag, attrs):
           print("Start tag:", tag)
           for attr in attrs:
               print("     attr:", attr)

def handle_endtag(self, tag):
           print("End tag  :", tag)

def handle_data(self, data):
           print("Data     :", data)

def handle_comment(self, data):
           print("Comment  :", data)

def handle_entityref(self, name):
           c = chr(name2codepoint[name])
           print("Named ent:", c)

def handle_charref(self, name):
           if name.startswith('x'):
               c = chr(int(name[1:], 16))
           else:
               c = chr(int(name))
           print("Num ent  :", c)

def handle_decl(self, data):
           print("Decl     :", data)

parser = MyHTMLParser()

Parsing a doctype::

>>> parser.feed('<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" '
   ...             '"http://www.w3.org/TR/html4/strict.dtd">')
   Decl     : DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd"

Parsing an element with a few attributes and a title::

>>> parser.feed('<img src="python-logo.png" alt="The Python logo">')
   Start tag: img
        attr: ('src', 'python-logo.png')
        attr: ('alt', 'The Python logo')
   >>>
   >>> parser.feed('<h1>Python</h1>')
   Start tag: h1
   Data     : Python
   End tag  : h1

The content of ``script`` and ``style`` elements is returned as is, without
further parsing::

>>> parser.feed('<style type="text/css">#python { color: green }</style>')
   Start tag: style
        attr: ('type', 'text/css')
   Data     : #python { color: green }
   End tag  : style

>>> parser.feed('<script type="text/javascript">'
   ...             'alert("<strong>hello!</strong>");</script>')
   Start tag: script
        attr: ('type', 'text/javascript')
   Data     : alert("<strong>hello!</strong>");
   End tag  : script

Parsing comments::

>>> parser.feed(''
   ...             '')
   Comment  :  a comment
   Comment  : [if IE 9]>IE-specific content<![endif]

Parsing named and numeric character references and converting them to the
correct char (note: these 3 references are all equivalent to ``'>'``)::

>>> parser.feed('&gt;&#62;&#x3E;')
   Named ent: >
   Num ent  : >
   Num ent  : >

Feeding incomplete chunks to :meth:`~HTMLParser.feed` works, but
:meth:`~HTMLParser.handle_data` might be called more than once
(unless *convert_charrefs* is set to ``True``)::

>>> for chunk in ['<sp', 'an>buff', 'ered ', 'text</s', 'pan>']:
   ...     parser.feed(chunk)
   ...
   Start tag: span
   Data     : buff
   Data     : ered
   Data     : text
   End tag  : span

Parsing invalid HTML (e.g. unquoted attributes) also works::

>>> parser.feed('<p><a class=link href=#main>tag soup</p ></a>')
   Start tag: p
   Start tag: a
        attr: ('class', 'link')
        attr: ('href', '#main')
   Data     : tag soup
   End tag  : p
   End tag  : a

:mod:`html.parser` --- Simple HTML and XHTML parser =================================================== .. module:: html.parser :synopsis: A simple parser that can handle HTML and XHTML. **Source code:** :source:`Lib/html/parser.py` .. index:: single: HTML single: XHTML -------------- This module defines a class :class:`HTMLParser` which serves as the basis for parsing text files formatted in HTML (HyperText Mark-up Language) and XHTML. .. class:: HTMLParser(*, convert_charrefs=True) Create a parser instance able to parse invalid markup. If *convert_charrefs* is ``True`` (the default), all character references (except the ones in ``script``/``style`` elements) are automatically converted to the corresponding Unicode characters. An :class:`.HTMLParser` instance is fed HTML data and calls handler methods when start tags, end tags, text, comments, and other markup elements are encountered. The user should subclass :class:`.HTMLParser` and override its methods to implement the desired behavior. This parser does not check that end tags match start tags or call the end-tag handler for elements which are closed implicitly by closing an outer element. .. versionchanged:: 3.4 *convert_charrefs* keyword argument added. .. versionchanged:: 3.5 The default value for argument *convert_charrefs* is now ``True``. Example HTML Parser Application ------------------------------- As a basic example, below is a simple HTML parser that uses the :class:`HTMLParser` class to print out start tags, end tags, and data as they are encountered:: from html.parser import HTMLParser class MyHTMLParser(HTMLParser): def handle_starttag(self, tag, attrs): print("Encountered a start tag:", tag) def handle_endtag(self, tag): print("Encountered an end tag :", tag) def handle_data(self, data): print("Encountered some data :", data) parser = MyHTMLParser() parser.feed('Test' '

Parse me!

') The output will then be: .. code-block:: none Encountered a start tag: html Encountered a start tag: head Encountered a start tag: title Encountered some data : Test Encountered an end tag : title Encountered an end tag : head Encountered a start tag: body Encountered a start tag: h1 Encountered some data : Parse me! Encountered an end tag : h1 Encountered an end tag : body Encountered an end tag : html :class:`.HTMLParser` Methods ---------------------------- :class:`HTMLParser` instances have the following methods: .. method:: HTMLParser.feed(data) Feed some text to the parser. It is processed insofar as it consists of complete elements; incomplete data is buffered until more data is fed or :meth:`close` is called. *data* must be :class:`str`. .. method:: HTMLParser.close() Force processing of all buffered data as if it were followed by an end-of-file mark. This method may be redefined by a derived class to define additional processing at the end of the input, but the redefined version should always call the :class:`HTMLParser` base class method :meth:`close`. .. method:: HTMLParser.reset() Reset the instance. Loses all unprocessed data. This is called implicitly at instantiation time. .. method:: HTMLParser.getpos() Return current line number and offset. .. method:: HTMLParser.get_starttag_text() Return the text of the most recently opened start tag. This should not normally be needed for structured processing, but may be useful in dealing with HTML "as deployed" or for re-generating input with minimal changes (whitespace between attributes can be preserved, etc.). The following methods are called when data or markup elements are encountered and they are meant to be overridden in a subclass. The base class implementations do nothing (except for :meth:`~HTMLParser.handle_startendtag`): .. method:: HTMLParser.handle_starttag(tag, attrs) This method is called to handle the start of a tag (e.g. ``

``). The *tag* argument is the name of the tag converted to lower case. The *attrs* argument is a list of ``(name, value)`` pairs containing the attributes found inside the tag's ``<>`` brackets. The *name* will be translated to lower case, and quotes in the *value* have been removed, and character and entity references have been replaced. For instance, for the tag ````, this method would be called as ``handle_starttag('a', [('href', 'https://www.cwi.nl/')])``. All entity references from :mod:`html.entities` are replaced in the attribute values. .. method:: HTMLParser.handle_endtag(tag) This method is called to handle the end tag of an element (e.g. ``

``). The *tag* argument is the name of the tag converted to lower case. .. method:: HTMLParser.handle_startendtag(tag, attrs) Similar to :meth:`handle_starttag`, but called when the parser encounters an XHTML-style empty tag (````). This method may be overridden by subclasses which require this particular lexical information; the default implementation simply calls :meth:`handle_starttag` and :meth:`handle_endtag`. .. method:: HTMLParser.handle_data(data) This method is called to process arbitrary data (e.g. text nodes and the content of ```` and ````). .. method:: HTMLParser.handle_entityref(name) This method is called to process a named character reference of the form ``&name;`` (e.g. ``>``), where *name* is a general entity reference (e.g. ``'gt'``). This method is never called if *convert_charrefs* is ``True``. .. method:: HTMLParser.handle_charref(name) This method is called to process decimal and hexadecimal numeric character references of the form ``&#NNN;`` and ``&#xNNN;``. For example, the decimal equivalent for ``>`` is ``>``, whereas the hexadecimal is ``>``; in this case the method will receive ``'62'`` or ``'x3E'``. This method is never called if *convert_charrefs* is ``True``. .. method:: HTMLParser.handle_comment(data) This method is called when a comment is encountered (e.g. ````). For example, the comment ```` will cause this method to be called with the argument ``' comment '``. The content of Internet Explorer conditional comments (condcoms) will also be sent to this method, so, for ````, this method will receive ``'[if IE 9]>IE9-specific content``). The *decl* parameter will be the entire contents of the declaration inside the ```` markup (e.g. ``'DOCTYPE html'``). .. method:: HTMLParser.handle_pi(data) Method called when a processing instruction is encountered. The *data* parameter will contain the entire processing instruction. For example, for the processing instruction ````, this method would be called as ``handle_pi("proc color='red'")``. It is intended to be overridden by a derived class; the base class implementation does nothing. .. note:: The :class:`HTMLParser` class uses the SGML syntactic rules for processing instructions. An XHTML processing instruction using the trailing ``'?'`` will cause the ``'?'`` to be included in *data*. .. method:: HTMLParser.unknown_decl(data) This method is called when an unrecognized declaration is read by the parser. The *data* parameter will be the entire contents of the declaration inside the ```` markup. It is sometimes useful to be overridden by a derived class. The base class implementation does nothing. .. _htmlparser-examples: Examples -------- The following class implements a parser that will be used to illustrate more examples:: from html.parser import HTMLParser from html.entities import name2codepoint class MyHTMLParser(HTMLParser): def handle_starttag(self, tag, attrs): print("Start tag:", tag) for attr in attrs: print(" attr:", attr) def handle_endtag(self, tag): print("End tag :", tag) def handle_data(self, data): print("Data :", data) def handle_comment(self, data): print("Comment :", data) def handle_entityref(self, name): c = chr(name2codepoint[name]) print("Named ent:", c) def handle_charref(self, name): if name.startswith('x'): c = chr(int(name[1:], 16)) else: c = chr(int(name)) print("Num ent :", c) def handle_decl(self, data): print("Decl :", data) parser = MyHTMLParser() Parsing a doctype:: >>> parser.feed('') Decl : DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd" Parsing an element with a few attributes and a title:: >>> parser.feed('

') Start tag: img attr: ('src', 'python-logo.png') attr: ('alt', 'The Python logo') >>> >>> parser.feed('

Python

') Start tag: h1 Data : Python End tag : h1 The content of ``script`` and ``style`` elements is returned as is, without further parsing:: >>> parser.feed('') Start tag: style attr: ('type', 'text/css') Data : #python { color: green } End tag : style >>> parser.feed('') Start tag: script attr: ('type', 'text/javascript') Data : alert("hello!"); End tag : script Parsing comments:: >>> parser.feed('' ... '') Comment : a comment Comment : [if IE 9]>IE-specific content'``):: >>> parser.feed('>>>') Named ent: > Num ent : > Num ent : > Feeding incomplete chunks to :meth:`~HTMLParser.feed` works, but :meth:`~HTMLParser.handle_data` might be called more than once (unless *convert_charrefs* is set to ``True``):: >>> for chunk in ['buff', 'ered ', 'text']: ... parser.feed(chunk) ... Start tag: span Data : buff Data : ered Data : text End tag : span Parsing invalid HTML (e.g. unquoted attributes) also works:: >>> parser.feed('

tag soup

') Start tag: p Start tag: a attr: ('class', 'link') attr: ('href', '#main') Data : tag soup End tag : p End tag : a