Linux iad1-shared-b7-18 6.6.49-grsec-jammy+ #10 SMP Thu Sep 12 23:23:08 UTC 2024 x86_64
Apache
: 67.205.6.31 | : 216.73.216.20
Cant Read [ /etc/named.conf ]
8.2.29
fernandoquevedo
Terminal
AUTO ROOT
Adminer
Backdoor Destroyer
Linux Exploit
Lock Shell
Lock File
Create User
CREATE RDP
PHP Mailer
BACKCONNECT
UNLOCK SHELL
HASH IDENTIFIER
README
+ Create Folder
+ Create File
/
usr /
share /
doc /
python3.10 /
html /
_sources /
library /
[ HOME SHELL ]
Name
Size
Permission
Action
2to3.rst.txt
16.15
KB
-rw-r--r--
__future__.rst.txt
6
KB
-rw-r--r--
__main__.rst.txt
12.34
KB
-rw-r--r--
_thread.rst.txt
7.88
KB
-rw-r--r--
abc.rst.txt
12.19
KB
-rw-r--r--
aifc.rst.txt
7.48
KB
-rw-r--r--
allos.rst.txt
678
B
-rw-r--r--
archiving.rst.txt
440
B
-rw-r--r--
argparse.rst.txt
80.31
KB
-rw-r--r--
array.rst.txt
10.45
KB
-rw-r--r--
ast.rst.txt
75.95
KB
-rw-r--r--
asynchat.rst.txt
8.44
KB
-rw-r--r--
asyncio-api-index.rst.txt
4.61
KB
-rw-r--r--
asyncio-dev.rst.txt
7.31
KB
-rw-r--r--
asyncio-eventloop.rst.txt
59.23
KB
-rw-r--r--
asyncio-exceptions.rst.txt
1.7
KB
-rw-r--r--
asyncio-future.rst.txt
8.31
KB
-rw-r--r--
asyncio-llapi-index.rst.txt
14.06
KB
-rw-r--r--
asyncio-platforms.rst.txt
3.03
KB
-rw-r--r--
asyncio-policy.rst.txt
9.17
KB
-rw-r--r--
asyncio-protocol.rst.txt
31.55
KB
-rw-r--r--
asyncio-queue.rst.txt
5.5
KB
-rw-r--r--
asyncio-stream.rst.txt
14.88
KB
-rw-r--r--
asyncio-subprocess.rst.txt
11.4
KB
-rw-r--r--
asyncio-sync.rst.txt
8.84
KB
-rw-r--r--
asyncio-task.rst.txt
32.29
KB
-rw-r--r--
asyncio.rst.txt
2.63
KB
-rw-r--r--
asyncore.rst.txt
13.43
KB
-rw-r--r--
atexit.rst.txt
3.84
KB
-rw-r--r--
audioop.rst.txt
10.59
KB
-rw-r--r--
audit_events.rst.txt
2.29
KB
-rw-r--r--
base64.rst.txt
10.87
KB
-rw-r--r--
bdb.rst.txt
14.54
KB
-rw-r--r--
binary.rst.txt
654
B
-rw-r--r--
binascii.rst.txt
7.66
KB
-rw-r--r--
binhex.rst.txt
1.69
KB
-rw-r--r--
bisect.rst.txt
9.06
KB
-rw-r--r--
builtins.rst.txt
1.43
KB
-rw-r--r--
bz2.rst.txt
11.87
KB
-rw-r--r--
calendar.rst.txt
14.17
KB
-rw-r--r--
cgi.rst.txt
21.49
KB
-rw-r--r--
cgitb.rst.txt
3.75
KB
-rw-r--r--
chunk.rst.txt
5.1
KB
-rw-r--r--
cmath.rst.txt
9.42
KB
-rw-r--r--
cmd.rst.txt
13.6
KB
-rw-r--r--
code.rst.txt
7.64
KB
-rw-r--r--
codecs.rst.txt
75.37
KB
-rw-r--r--
codeop.rst.txt
3
KB
-rw-r--r--
collections.abc.rst.txt
16.73
KB
-rw-r--r--
collections.rst.txt
52.13
KB
-rw-r--r--
colorsys.rst.txt
1.77
KB
-rw-r--r--
compileall.rst.txt
13.45
KB
-rw-r--r--
concurrency.rst.txt
685
B
-rw-r--r--
concurrent.futures.rst.txt
20.76
KB
-rw-r--r--
concurrent.rst.txt
171
B
-rw-r--r--
configparser.rst.txt
49.91
KB
-rw-r--r--
constants.rst.txt
3.77
KB
-rw-r--r--
contextlib.rst.txt
34.35
KB
-rw-r--r--
contextvars.rst.txt
8.32
KB
-rw-r--r--
copy.rst.txt
3.39
KB
-rw-r--r--
copyreg.rst.txt
1.97
KB
-rw-r--r--
crypt.rst.txt
5.84
KB
-rw-r--r--
crypto.rst.txt
411
B
-rw-r--r--
csv.rst.txt
20.91
KB
-rw-r--r--
ctypes.rst.txt
90.63
KB
-rw-r--r--
curses.ascii.rst.txt
8.85
KB
-rw-r--r--
curses.panel.rst.txt
2.7
KB
-rw-r--r--
curses.rst.txt
77.03
KB
-rw-r--r--
custominterp.rst.txt
569
B
-rw-r--r--
dataclasses.rst.txt
29.22
KB
-rw-r--r--
datatypes.rst.txt
817
B
-rw-r--r--
datetime.rst.txt
101.93
KB
-rw-r--r--
dbm.rst.txt
15.05
KB
-rw-r--r--
debug.rst.txt
611
B
-rw-r--r--
decimal.rst.txt
76.21
KB
-rw-r--r--
development.rst.txt
719
B
-rw-r--r--
devmode.rst.txt
7.28
KB
-rw-r--r--
dialog.rst.txt
6.12
KB
-rw-r--r--
difflib.rst.txt
29.76
KB
-rw-r--r--
dis.rst.txt
35.33
KB
-rw-r--r--
distribution.rst.txt
452
B
-rw-r--r--
distutils.rst.txt
2.09
KB
-rw-r--r--
doctest.rst.txt
69.87
KB
-rw-r--r--
email.charset.rst.txt
7.83
KB
-rw-r--r--
email.compat32-message.rst.txt
32.89
KB
-rw-r--r--
email.contentmanager.rst.txt
8.9
KB
-rw-r--r--
email.encoders.rst.txt
2.92
KB
-rw-r--r--
email.errors.rst.txt
4.92
KB
-rw-r--r--
email.examples.rst.txt
1.87
KB
-rw-r--r--
email.generator.rst.txt
13.49
KB
-rw-r--r--
email.header.rst.txt
8.97
KB
-rw-r--r--
email.headerregistry.rst.txt
18.04
KB
-rw-r--r--
email.iterators.rst.txt
2.73
KB
-rw-r--r--
email.message.rst.txt
32.25
KB
-rw-r--r--
email.mime.rst.txt
11.45
KB
-rw-r--r--
email.parser.rst.txt
13.76
KB
-rw-r--r--
email.policy.rst.txt
27.03
KB
-rw-r--r--
email.rst.txt
6.63
KB
-rw-r--r--
email.utils.rst.txt
9.57
KB
-rw-r--r--
ensurepip.rst.txt
4.9
KB
-rw-r--r--
enum.rst.txt
35.96
KB
-rw-r--r--
errno.rst.txt
7.81
KB
-rw-r--r--
exceptions.rst.txt
29.86
KB
-rw-r--r--
faulthandler.rst.txt
6.51
KB
-rw-r--r--
fcntl.rst.txt
7.99
KB
-rw-r--r--
filecmp.rst.txt
5.89
KB
-rw-r--r--
fileformats.rst.txt
273
B
-rw-r--r--
fileinput.rst.txt
8.99
KB
-rw-r--r--
filesys.rst.txt
946
B
-rw-r--r--
fnmatch.rst.txt
3.31
KB
-rw-r--r--
fractions.rst.txt
6.2
KB
-rw-r--r--
frameworks.rst.txt
391
B
-rw-r--r--
ftplib.rst.txt
18.13
KB
-rw-r--r--
functional.rst.txt
365
B
-rw-r--r--
functions.rst.txt
84.5
KB
-rw-r--r--
functools.rst.txt
25.99
KB
-rw-r--r--
gc.rst.txt
11.16
KB
-rw-r--r--
getopt.rst.txt
6.4
KB
-rw-r--r--
getpass.rst.txt
1.84
KB
-rw-r--r--
gettext.rst.txt
27.35
KB
-rw-r--r--
glob.rst.txt
5.07
KB
-rw-r--r--
graphlib.rst.txt
8.56
KB
-rw-r--r--
grp.rst.txt
2.32
KB
-rw-r--r--
gzip.rst.txt
9.7
KB
-rw-r--r--
hashlib.rst.txt
27.32
KB
-rw-r--r--
heapq.rst.txt
13.59
KB
-rw-r--r--
hmac.rst.txt
4.93
KB
-rw-r--r--
html.entities.rst.txt
1.31
KB
-rw-r--r--
html.parser.rst.txt
11.02
KB
-rw-r--r--
html.rst.txt
1.27
KB
-rw-r--r--
http.client.rst.txt
20.86
KB
-rw-r--r--
http.cookiejar.rst.txt
27.68
KB
-rw-r--r--
http.cookies.rst.txt
8.78
KB
-rw-r--r--
http.rst.txt
7.61
KB
-rw-r--r--
http.server.rst.txt
19.68
KB
-rw-r--r--
i18n.rst.txt
408
B
-rw-r--r--
idle.rst.txt
38.83
KB
-rw-r--r--
imaplib.rst.txt
21.42
KB
-rw-r--r--
imghdr.rst.txt
3.01
KB
-rw-r--r--
imp.rst.txt
15.15
KB
-rw-r--r--
importlib.metadata.rst.txt
12.12
KB
-rw-r--r--
importlib.rst.txt
66.95
KB
-rw-r--r--
index.rst.txt
2.37
KB
-rw-r--r--
inspect.rst.txt
59.36
KB
-rw-r--r--
internet.rst.txt
923
B
-rw-r--r--
intro.rst.txt
2.95
KB
-rw-r--r--
io.rst.txt
44.14
KB
-rw-r--r--
ipaddress.rst.txt
36.99
KB
-rw-r--r--
ipc.rst.txt
643
B
-rw-r--r--
itertools.rst.txt
42.1
KB
-rw-r--r--
json.rst.txt
28.07
KB
-rw-r--r--
keyword.rst.txt
1.12
KB
-rw-r--r--
language.rst.txt
494
B
-rw-r--r--
linecache.rst.txt
2.49
KB
-rw-r--r--
locale.rst.txt
26.03
KB
-rw-r--r--
logging.config.rst.txt
36.69
KB
-rw-r--r--
logging.handlers.rst.txt
47.53
KB
-rw-r--r--
logging.rst.txt
66.77
KB
-rw-r--r--
lzma.rst.txt
16.95
KB
-rw-r--r--
mailbox.rst.txt
61.47
KB
-rw-r--r--
mailcap.rst.txt
4.43
KB
-rw-r--r--
markup.rst.txt
679
B
-rw-r--r--
marshal.rst.txt
5.35
KB
-rw-r--r--
math.rst.txt
21.01
KB
-rw-r--r--
mimetypes.rst.txt
9.96
KB
-rw-r--r--
mm.rst.txt
331
B
-rw-r--r--
mmap.rst.txt
13.41
KB
-rw-r--r--
modulefinder.rst.txt
3.16
KB
-rw-r--r--
modules.rst.txt
381
B
-rw-r--r--
msilib.rst.txt
18.51
KB
-rw-r--r--
msvcrt.rst.txt
4.5
KB
-rw-r--r--
multiprocessing.rst.txt
108.08
KB
-rw-r--r--
multiprocessing.shared_memory....
14.44
KB
-rw-r--r--
netdata.rst.txt
314
B
-rw-r--r--
netrc.rst.txt
3.32
KB
-rw-r--r--
nis.rst.txt
2.07
KB
-rw-r--r--
nntplib.rst.txt
21.25
KB
-rw-r--r--
numbers.rst.txt
8.09
KB
-rw-r--r--
numeric.rst.txt
696
B
-rw-r--r--
operator.rst.txt
18.84
KB
-rw-r--r--
optparse.rst.txt
75.3
KB
-rw-r--r--
os.path.rst.txt
17.4
KB
-rw-r--r--
os.rst.txt
168.21
KB
-rw-r--r--
ossaudiodev.rst.txt
17.56
KB
-rw-r--r--
pathlib.rst.txt
39.66
KB
-rw-r--r--
pdb.rst.txt
20.26
KB
-rw-r--r--
persistence.rst.txt
591
B
-rw-r--r--
pickle.rst.txt
46.52
KB
-rw-r--r--
pickletools.rst.txt
3.64
KB
-rw-r--r--
pipes.rst.txt
2.72
KB
-rw-r--r--
pkgutil.rst.txt
10.26
KB
-rw-r--r--
platform.rst.txt
9.7
KB
-rw-r--r--
plistlib.rst.txt
5.32
KB
-rw-r--r--
poplib.rst.txt
8.98
KB
-rw-r--r--
posix.rst.txt
3.52
KB
-rw-r--r--
pprint.rst.txt
16.34
KB
-rw-r--r--
profile.rst.txt
29.55
KB
-rw-r--r--
pty.rst.txt
4.5
KB
-rw-r--r--
pwd.rst.txt
2.67
KB
-rw-r--r--
py_compile.rst.txt
6.52
KB
-rw-r--r--
pyclbr.rst.txt
4.45
KB
-rw-r--r--
pydoc.rst.txt
5.01
KB
-rw-r--r--
pyexpat.rst.txt
27.95
KB
-rw-r--r--
python.rst.txt
480
B
-rw-r--r--
queue.rst.txt
10
KB
-rw-r--r--
quopri.rst.txt
2.51
KB
-rw-r--r--
random.rst.txt
22.98
KB
-rw-r--r--
re.rst.txt
68.48
KB
-rw-r--r--
readline.rst.txt
12.13
KB
-rw-r--r--
reprlib.rst.txt
5.12
KB
-rw-r--r--
resource.rst.txt
13
KB
-rw-r--r--
rlcompleter.rst.txt
2.24
KB
-rw-r--r--
runpy.rst.txt
8.09
KB
-rw-r--r--
sched.rst.txt
5.05
KB
-rw-r--r--
secrets.rst.txt
5.96
KB
-rw-r--r--
security_warnings.rst.txt
1.56
KB
-rw-r--r--
select.rst.txt
27.78
KB
-rw-r--r--
selectors.rst.txt
8.72
KB
-rw-r--r--
shelve.rst.txt
8.6
KB
-rw-r--r--
shlex.rst.txt
17.62
KB
-rw-r--r--
shutil.rst.txt
31.13
KB
-rw-r--r--
signal.rst.txt
25.12
KB
-rw-r--r--
site.rst.txt
10.38
KB
-rw-r--r--
smtpd.rst.txt
10.79
KB
-rw-r--r--
smtplib.rst.txt
23.66
KB
-rw-r--r--
sndhdr.rst.txt
2.09
KB
-rw-r--r--
socket.rst.txt
77.52
KB
-rw-r--r--
socketserver.rst.txt
24.01
KB
-rw-r--r--
spwd.rst.txt
3.03
KB
-rw-r--r--
sqlite3.rst.txt
66.94
KB
-rw-r--r--
ssl.rst.txt
104.53
KB
-rw-r--r--
stat.rst.txt
9.89
KB
-rw-r--r--
statistics.rst.txt
35.59
KB
-rw-r--r--
stdtypes.rst.txt
205.7
KB
-rw-r--r--
string.rst.txt
38.87
KB
-rw-r--r--
stringprep.rst.txt
4.18
KB
-rw-r--r--
struct.rst.txt
24.29
KB
-rw-r--r--
subprocess.rst.txt
57.99
KB
-rw-r--r--
sunau.rst.txt
7.24
KB
-rw-r--r--
superseded.rst.txt
561
B
-rw-r--r--
symtable.rst.txt
5.14
KB
-rw-r--r--
sys.rst.txt
76.16
KB
-rw-r--r--
sysconfig.rst.txt
9.7
KB
-rw-r--r--
syslog.rst.txt
4.55
KB
-rw-r--r--
tabnanny.rst.txt
1.96
KB
-rw-r--r--
tarfile.rst.txt
46.93
KB
-rw-r--r--
telnetlib.rst.txt
8.03
KB
-rw-r--r--
tempfile.rst.txt
15.69
KB
-rw-r--r--
termios.rst.txt
3.66
KB
-rw-r--r--
test.rst.txt
54.87
KB
-rw-r--r--
text.rst.txt
584
B
-rw-r--r--
textwrap.rst.txt
11.18
KB
-rw-r--r--
threading.rst.txt
42.74
KB
-rw-r--r--
time.rst.txt
36.47
KB
-rw-r--r--
timeit.rst.txt
13.32
KB
-rw-r--r--
tk.rst.txt
1.6
KB
-rw-r--r--
tkinter.colorchooser.rst.txt
906
B
-rw-r--r--
tkinter.dnd.rst.txt
2.07
KB
-rw-r--r--
tkinter.font.rst.txt
2.91
KB
-rw-r--r--
tkinter.messagebox.rst.txt
1.27
KB
-rw-r--r--
tkinter.rst.txt
40.8
KB
-rw-r--r--
tkinter.scrolledtext.rst.txt
1.18
KB
-rw-r--r--
tkinter.tix.rst.txt
21.59
KB
-rw-r--r--
tkinter.ttk.rst.txt
61.02
KB
-rw-r--r--
token.rst.txt
2.7
KB
-rw-r--r--
tokenize.rst.txt
10.24
KB
-rw-r--r--
trace.rst.txt
6.82
KB
-rw-r--r--
traceback.rst.txt
18.93
KB
-rw-r--r--
tracemalloc.rst.txt
24.96
KB
-rw-r--r--
tty.rst.txt
1.07
KB
-rw-r--r--
turtle.rst.txt
72.59
KB
-rw-r--r--
types.rst.txt
14.9
KB
-rw-r--r--
typing.rst.txt
77.48
KB
-rw-r--r--
unicodedata.rst.txt
5.83
KB
-rw-r--r--
unittest.mock-examples.rst.txt
47.14
KB
-rw-r--r--
unittest.mock.rst.txt
97.32
KB
-rw-r--r--
unittest.rst.txt
99.8
KB
-rw-r--r--
unix.rst.txt
397
B
-rw-r--r--
urllib.error.rst.txt
2.15
KB
-rw-r--r--
urllib.parse.rst.txt
32.65
KB
-rw-r--r--
urllib.request.rst.txt
59.94
KB
-rw-r--r--
urllib.robotparser.rst.txt
3.19
KB
-rw-r--r--
urllib.rst.txt
466
B
-rw-r--r--
uu.rst.txt
2.67
KB
-rw-r--r--
uuid.rst.txt
9.95
KB
-rw-r--r--
venv.rst.txt
25.52
KB
-rw-r--r--
warnings.rst.txt
23.71
KB
-rw-r--r--
wave.rst.txt
6.68
KB
-rw-r--r--
weakref.rst.txt
21.22
KB
-rw-r--r--
webbrowser.rst.txt
9.83
KB
-rw-r--r--
windows.rst.txt
258
B
-rw-r--r--
winreg.rst.txt
25.18
KB
-rw-r--r--
winsound.rst.txt
5.01
KB
-rw-r--r--
wsgiref.rst.txt
32.61
KB
-rw-r--r--
xdrlib.rst.txt
8.02
KB
-rw-r--r--
xml.dom.minidom.rst.txt
11
KB
-rw-r--r--
xml.dom.pulldom.rst.txt
5.16
KB
-rw-r--r--
xml.dom.rst.txt
38.62
KB
-rw-r--r--
xml.etree.elementtree.rst.txt
56.91
KB
-rw-r--r--
xml.rst.txt
5.79
KB
-rw-r--r--
xml.sax.handler.rst.txt
16.43
KB
-rw-r--r--
xml.sax.reader.rst.txt
11.97
KB
-rw-r--r--
xml.sax.rst.txt
7.09
KB
-rw-r--r--
xml.sax.utils.rst.txt
3.81
KB
-rw-r--r--
xmlrpc.client.rst.txt
22.52
KB
-rw-r--r--
xmlrpc.rst.txt
475
B
-rw-r--r--
xmlrpc.server.rst.txt
16.25
KB
-rw-r--r--
zipapp.rst.txt
17.85
KB
-rw-r--r--
zipfile.rst.txt
29.76
KB
-rw-r--r--
zipimport.rst.txt
6.79
KB
-rw-r--r--
zlib.rst.txt
13.83
KB
-rw-r--r--
zoneinfo.rst.txt
15.66
KB
-rw-r--r--
Delete
Unzip
Zip
${this.title}
Close
Code Editor : html.parser.rst.txt
: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 tag of an element (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. ``>``), 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. ``<!--comment-->``). For example, the comment ``<!-- 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 ``<!--[if IE 9]>IE9-specific content<![endif]-->``, 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('<!-- a comment -->' ... '<!--[if IE 9]>IE-specific content<![endif]-->') 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('>>>') 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
Close