Linux cpanel.rrshost.in 5.15.0-25-generic #25-Ubuntu SMP Wed Mar 30 15:54:22 UTC 2022 x86_64
Apache
: 109.123.238.221 | : 172.69.130.109
128 Domain
8.2.28
aev999
Terminal
AUTO ROOT
Adminer
Backdoor Destroyer
Linux Exploit
Lock Shell
Lock File
Create User
CREATE RDP
PHP Mailer
BACKCONNECT
HASH IDENTIFIER
README
+ Create Folder
+ Create File
/
usr /
share /
doc /
python2.7 /
html /
_sources /
library /
[ HOME SHELL ]
Name
Size
Permission
Action
2to3.rst.txt
14.3
KB
-rw-r--r--
__builtin__.rst.txt
1.46
KB
-rw-r--r--
__future__.rst.txt
4.84
KB
-rw-r--r--
__main__.rst.txt
535
B
-rw-r--r--
_winreg.rst.txt
22.77
KB
-rw-r--r--
abc.rst.txt
7.05
KB
-rw-r--r--
aepack.rst.txt
4.16
KB
-rw-r--r--
aetools.rst.txt
3.45
KB
-rw-r--r--
aetypes.rst.txt
4.16
KB
-rw-r--r--
aifc.rst.txt
6.92
KB
-rw-r--r--
al.rst.txt
5.18
KB
-rw-r--r--
allos.rst.txt
695
B
-rw-r--r--
anydbm.rst.txt
4.01
KB
-rw-r--r--
archiving.rst.txt
424
B
-rw-r--r--
argparse.rst.txt
72.93
KB
-rw-r--r--
array.rst.txt
10.28
KB
-rw-r--r--
ast.rst.txt
10.23
KB
-rw-r--r--
asynchat.rst.txt
8.99
KB
-rw-r--r--
asyncore.rst.txt
12.63
KB
-rw-r--r--
atexit.rst.txt
3.82
KB
-rw-r--r--
audioop.rst.txt
10.15
KB
-rw-r--r--
autogil.rst.txt
1015
B
-rw-r--r--
base64.rst.txt
6.11
KB
-rw-r--r--
basehttpserver.rst.txt
10.16
KB
-rw-r--r--
bastion.rst.txt
2.55
KB
-rw-r--r--
bdb.rst.txt
12.16
KB
-rw-r--r--
binascii.rst.txt
6.36
KB
-rw-r--r--
binhex.rst.txt
1.87
KB
-rw-r--r--
bisect.rst.txt
5.29
KB
-rw-r--r--
bsddb.rst.txt
7.4
KB
-rw-r--r--
bz2.rst.txt
7.88
KB
-rw-r--r--
calendar.rst.txt
11.02
KB
-rw-r--r--
carbon.rst.txt
15.58
KB
-rw-r--r--
cd.rst.txt
11.69
KB
-rw-r--r--
cgi.rst.txt
22.32
KB
-rw-r--r--
cgihttpserver.rst.txt
2.72
KB
-rw-r--r--
cgitb.rst.txt
2.81
KB
-rw-r--r--
chunk.rst.txt
4.84
KB
-rw-r--r--
cmath.rst.txt
7.47
KB
-rw-r--r--
cmd.rst.txt
8.36
KB
-rw-r--r--
code.rst.txt
6.95
KB
-rw-r--r--
codecs.rst.txt
65.4
KB
-rw-r--r--
codeop.rst.txt
3.69
KB
-rw-r--r--
collections.rst.txt
40.48
KB
-rw-r--r--
colorpicker.rst.txt
913
B
-rw-r--r--
colorsys.rst.txt
1.78
KB
-rw-r--r--
commands.rst.txt
2.53
KB
-rw-r--r--
compileall.rst.txt
4.57
KB
-rw-r--r--
compiler.rst.txt
36.59
KB
-rw-r--r--
configparser.rst.txt
19.15
KB
-rw-r--r--
constants.rst.txt
2.27
KB
-rw-r--r--
contextlib.rst.txt
5.87
KB
-rw-r--r--
cookie.rst.txt
9.32
KB
-rw-r--r--
cookielib.rst.txt
27.22
KB
-rw-r--r--
copy.rst.txt
3.27
KB
-rw-r--r--
copy_reg.rst.txt
2.27
KB
-rw-r--r--
crypt.rst.txt
2.24
KB
-rw-r--r--
crypto.rst.txt
355
B
-rw-r--r--
csv.rst.txt
22.22
KB
-rw-r--r--
ctypes.rst.txt
88.39
KB
-rw-r--r--
curses.ascii.rst.txt
8.83
KB
-rw-r--r--
curses.panel.rst.txt
2.68
KB
-rw-r--r--
curses.rst.txt
73.12
KB
-rw-r--r--
custominterp.rst.txt
570
B
-rw-r--r--
datatypes.rst.txt
864
B
-rw-r--r--
datetime.rst.txt
72.93
KB
-rw-r--r--
dbhash.rst.txt
3.77
KB
-rw-r--r--
dbm.rst.txt
3.04
KB
-rw-r--r--
debug.rst.txt
446
B
-rw-r--r--
decimal.rst.txt
69.26
KB
-rw-r--r--
development.rst.txt
640
B
-rw-r--r--
difflib.rst.txt
30
KB
-rw-r--r--
dircache.rst.txt
1.77
KB
-rw-r--r--
dis.rst.txt
22.7
KB
-rw-r--r--
distribution.rst.txt
426
B
-rw-r--r--
distutils.rst.txt
1.91
KB
-rw-r--r--
dl.rst.txt
3.31
KB
-rw-r--r--
doctest.rst.txt
72.25
KB
-rw-r--r--
docxmlrpcserver.rst.txt
3.71
KB
-rw-r--r--
dumbdbm.rst.txt
2.77
KB
-rw-r--r--
dummy_thread.rst.txt
1.03
KB
-rw-r--r--
dummy_threading.rst.txt
799
B
-rw-r--r--
easydialogs.rst.txt
10.1
KB
-rw-r--r--
email-examples.rst.txt
1.24
KB
-rw-r--r--
email.charset.rst.txt
9.43
KB
-rw-r--r--
email.encoders.rst.txt
2.32
KB
-rw-r--r--
email.errors.rst.txt
3.91
KB
-rw-r--r--
email.generator.rst.txt
5.99
KB
-rw-r--r--
email.header.rst.txt
7.35
KB
-rw-r--r--
email.iterators.rst.txt
2.36
KB
-rw-r--r--
email.message.rst.txt
24.63
KB
-rw-r--r--
email.mime.rst.txt
9.68
KB
-rw-r--r--
email.parser.rst.txt
10.08
KB
-rw-r--r--
email.rst.txt
15.73
KB
-rw-r--r--
email.utils.rst.txt
6.32
KB
-rw-r--r--
ensurepip.rst.txt
4.9
KB
-rw-r--r--
errno.rst.txt
6.55
KB
-rw-r--r--
exceptions.rst.txt
18.03
KB
-rw-r--r--
fcntl.rst.txt
7.19
KB
-rw-r--r--
filecmp.rst.txt
5.22
KB
-rw-r--r--
fileformats.rst.txt
302
B
-rw-r--r--
fileinput.rst.txt
7.24
KB
-rw-r--r--
filesys.rst.txt
806
B
-rw-r--r--
fl.rst.txt
17.23
KB
-rw-r--r--
fm.rst.txt
2.64
KB
-rw-r--r--
fnmatch.rst.txt
3.03
KB
-rw-r--r--
formatter.rst.txt
12.93
KB
-rw-r--r--
fpectl.rst.txt
4.07
KB
-rw-r--r--
fpformat.rst.txt
1.71
KB
-rw-r--r--
fractions.rst.txt
5.17
KB
-rw-r--r--
framework.rst.txt
11.18
KB
-rw-r--r--
frameworks.rst.txt
378
B
-rw-r--r--
ftplib.rst.txt
15.35
KB
-rw-r--r--
functions.rst.txt
73.75
KB
-rw-r--r--
functools.rst.txt
7.27
KB
-rw-r--r--
future_builtins.rst.txt
1.96
KB
-rw-r--r--
gc.rst.txt
8.8
KB
-rw-r--r--
gdbm.rst.txt
4.77
KB
-rw-r--r--
gensuitemodule.rst.txt
3.04
KB
-rw-r--r--
getopt.rst.txt
6.51
KB
-rw-r--r--
getpass.rst.txt
1.83
KB
-rw-r--r--
gettext.rst.txt
28.36
KB
-rw-r--r--
gl.rst.txt
5.87
KB
-rw-r--r--
glob.rst.txt
2.36
KB
-rw-r--r--
grp.rst.txt
2.2
KB
-rw-r--r--
gzip.rst.txt
4.71
KB
-rw-r--r--
hashlib.rst.txt
7.21
KB
-rw-r--r--
heapq.rst.txt
12.88
KB
-rw-r--r--
hmac.rst.txt
3
KB
-rw-r--r--
hotshot.rst.txt
4.19
KB
-rw-r--r--
htmllib.rst.txt
7.21
KB
-rw-r--r--
htmlparser.rst.txt
11.37
KB
-rw-r--r--
httplib.rst.txt
36.58
KB
-rw-r--r--
i18n.rst.txt
409
B
-rw-r--r--
ic.rst.txt
4.89
KB
-rw-r--r--
idle.rst.txt
21.66
KB
-rw-r--r--
imageop.rst.txt
3.91
KB
-rw-r--r--
imaplib.rst.txt
16.82
KB
-rw-r--r--
imgfile.rst.txt
2.7
KB
-rw-r--r--
imghdr.rst.txt
2.57
KB
-rw-r--r--
imp.rst.txt
12.3
KB
-rw-r--r--
importlib.rst.txt
1.1
KB
-rw-r--r--
imputil.rst.txt
6.86
KB
-rw-r--r--
index.rst.txt
2.23
KB
-rw-r--r--
inspect.rst.txt
27.49
KB
-rw-r--r--
internet.rst.txt
950
B
-rw-r--r--
intro.rst.txt
2.74
KB
-rw-r--r--
io.rst.txt
38.11
KB
-rw-r--r--
ipc.rst.txt
630
B
-rw-r--r--
itertools.rst.txt
35.67
KB
-rw-r--r--
jpeg.rst.txt
3.77
KB
-rw-r--r--
json.rst.txt
24.95
KB
-rw-r--r--
keyword.rst.txt
617
B
-rw-r--r--
language.rst.txt
523
B
-rw-r--r--
linecache.rst.txt
1.84
KB
-rw-r--r--
locale.rst.txt
24.39
KB
-rw-r--r--
logging.config.rst.txt
30.82
KB
-rw-r--r--
logging.handlers.rst.txt
27.49
KB
-rw-r--r--
logging.rst.txt
45.78
KB
-rw-r--r--
mac.rst.txt
791
B
-rw-r--r--
macos.rst.txt
3.73
KB
-rw-r--r--
macosa.rst.txt
3.87
KB
-rw-r--r--
macostools.rst.txt
3.92
KB
-rw-r--r--
macpath.rst.txt
650
B
-rw-r--r--
mailbox.rst.txt
66.53
KB
-rw-r--r--
mailcap.rst.txt
3.59
KB
-rw-r--r--
markup.rst.txt
1.22
KB
-rw-r--r--
marshal.rst.txt
5.56
KB
-rw-r--r--
math.rst.txt
10.66
KB
-rw-r--r--
md5.rst.txt
2.75
KB
-rw-r--r--
mhlib.rst.txt
3.87
KB
-rw-r--r--
mimetools.rst.txt
4.4
KB
-rw-r--r--
mimetypes.rst.txt
9.61
KB
-rw-r--r--
mimewriter.rst.txt
3.28
KB
-rw-r--r--
mimify.rst.txt
3.44
KB
-rw-r--r--
miniaeframe.rst.txt
2.5
KB
-rw-r--r--
misc.rst.txt
248
B
-rw-r--r--
mm.rst.txt
447
B
-rw-r--r--
mmap.rst.txt
10.24
KB
-rw-r--r--
modulefinder.rst.txt
3.3
KB
-rw-r--r--
modules.rst.txt
382
B
-rw-r--r--
msilib.rst.txt
18.62
KB
-rw-r--r--
msvcrt.rst.txt
4.24
KB
-rw-r--r--
multifile.rst.txt
6.46
KB
-rw-r--r--
multiprocessing.rst.txt
90.45
KB
-rw-r--r--
mutex.rst.txt
1.89
KB
-rw-r--r--
netdata.rst.txt
432
B
-rw-r--r--
netrc.rst.txt
3.05
KB
-rw-r--r--
new.rst.txt
2.59
KB
-rw-r--r--
nis.rst.txt
2.06
KB
-rw-r--r--
nntplib.rst.txt
14.19
KB
-rw-r--r--
numbers.rst.txt
7.82
KB
-rw-r--r--
numeric.rst.txt
751
B
-rw-r--r--
operator.rst.txt
21.57
KB
-rw-r--r--
optparse.rst.txt
75.29
KB
-rw-r--r--
os.path.rst.txt
12.79
KB
-rw-r--r--
os.rst.txt
80.64
KB
-rw-r--r--
ossaudiodev.rst.txt
16.9
KB
-rw-r--r--
othergui.rst.txt
2.66
KB
-rw-r--r--
parser.rst.txt
15.02
KB
-rw-r--r--
pdb.rst.txt
15.67
KB
-rw-r--r--
persistence.rst.txt
826
B
-rw-r--r--
pickle.rst.txt
36.39
KB
-rw-r--r--
pickletools.rst.txt
1.95
KB
-rw-r--r--
pipes.rst.txt
3.7
KB
-rw-r--r--
pkgutil.rst.txt
7.53
KB
-rw-r--r--
platform.rst.txt
9.33
KB
-rw-r--r--
plistlib.rst.txt
4.04
KB
-rw-r--r--
popen2.rst.txt
6.86
KB
-rw-r--r--
poplib.rst.txt
6.07
KB
-rw-r--r--
posix.rst.txt
3.54
KB
-rw-r--r--
posixfile.rst.txt
7.03
KB
-rw-r--r--
pprint.rst.txt
8.86
KB
-rw-r--r--
profile.rst.txt
27.99
KB
-rw-r--r--
pty.rst.txt
1.72
KB
-rw-r--r--
pwd.rst.txt
2.66
KB
-rw-r--r--
py_compile.rst.txt
2.42
KB
-rw-r--r--
pyclbr.rst.txt
3.22
KB
-rw-r--r--
pydoc.rst.txt
3.99
KB
-rw-r--r--
pyexpat.rst.txt
28.21
KB
-rw-r--r--
python.rst.txt
514
B
-rw-r--r--
queue.rst.txt
6.87
KB
-rw-r--r--
quopri.rst.txt
2.61
KB
-rw-r--r--
random.rst.txt
13.01
KB
-rw-r--r--
re.rst.txt
53.81
KB
-rw-r--r--
readline.rst.txt
10.27
KB
-rw-r--r--
repr.rst.txt
4.61
KB
-rw-r--r--
resource.rst.txt
9.37
KB
-rw-r--r--
restricted.rst.txt
3.25
KB
-rw-r--r--
rexec.rst.txt
11.47
KB
-rw-r--r--
rfc822.rst.txt
13.71
KB
-rw-r--r--
rlcompleter.rst.txt
2.44
KB
-rw-r--r--
robotparser.rst.txt
2.14
KB
-rw-r--r--
runpy.rst.txt
6.78
KB
-rw-r--r--
sched.rst.txt
4.54
KB
-rw-r--r--
scrolledtext.rst.txt
1.35
KB
-rw-r--r--
select.rst.txt
20.26
KB
-rw-r--r--
sets.rst.txt
14.62
KB
-rw-r--r--
sgi.rst.txt
322
B
-rw-r--r--
sgmllib.rst.txt
10.41
KB
-rw-r--r--
sha.rst.txt
2.74
KB
-rw-r--r--
shelve.rst.txt
8.12
KB
-rw-r--r--
shlex.rst.txt
11.05
KB
-rw-r--r--
shutil.rst.txt
13.17
KB
-rw-r--r--
signal.rst.txt
10.47
KB
-rw-r--r--
simplehttpserver.rst.txt
4.45
KB
-rw-r--r--
simplexmlrpcserver.rst.txt
10.63
KB
-rw-r--r--
site.rst.txt
7.7
KB
-rw-r--r--
smtpd.rst.txt
2.41
KB
-rw-r--r--
smtplib.rst.txt
14.56
KB
-rw-r--r--
sndhdr.rst.txt
1.72
KB
-rw-r--r--
socket.rst.txt
39.81
KB
-rw-r--r--
socketserver.rst.txt
21.98
KB
-rw-r--r--
someos.rst.txt
599
B
-rw-r--r--
spwd.rst.txt
2.76
KB
-rw-r--r--
sqlite3.rst.txt
34.62
KB
-rw-r--r--
ssl.rst.txt
74.91
KB
-rw-r--r--
stat.rst.txt
7.6
KB
-rw-r--r--
statvfs.rst.txt
1.27
KB
-rw-r--r--
stdtypes.rst.txt
119.78
KB
-rw-r--r--
string.rst.txt
43.05
KB
-rw-r--r--
stringio.rst.txt
4.07
KB
-rw-r--r--
stringprep.rst.txt
4.14
KB
-rw-r--r--
strings.rst.txt
746
B
-rw-r--r--
struct.rst.txt
16.7
KB
-rw-r--r--
subprocess.rst.txt
32.86
KB
-rw-r--r--
sun.rst.txt
249
B
-rw-r--r--
sunau.rst.txt
6.96
KB
-rw-r--r--
sunaudio.rst.txt
5.71
KB
-rw-r--r--
symbol.rst.txt
975
B
-rw-r--r--
symtable.rst.txt
4.95
KB
-rw-r--r--
sys.rst.txt
46.4
KB
-rw-r--r--
sysconfig.rst.txt
7.46
KB
-rw-r--r--
syslog.rst.txt
3.84
KB
-rw-r--r--
tabnanny.rst.txt
1.95
KB
-rw-r--r--
tarfile.rst.txt
27.55
KB
-rw-r--r--
telnetlib.rst.txt
7.31
KB
-rw-r--r--
tempfile.rst.txt
10.26
KB
-rw-r--r--
termios.rst.txt
3.65
KB
-rw-r--r--
test.rst.txt
17.34
KB
-rw-r--r--
textwrap.rst.txt
8.47
KB
-rw-r--r--
thread.rst.txt
6.43
KB
-rw-r--r--
threading.rst.txt
31.77
KB
-rw-r--r--
time.rst.txt
25.41
KB
-rw-r--r--
timeit.rst.txt
11.33
KB
-rw-r--r--
tix.rst.txt
22.16
KB
-rw-r--r--
tk.rst.txt
1.57
KB
-rw-r--r--
tkinter.rst.txt
32.72
KB
-rw-r--r--
token.rst.txt
2.39
KB
-rw-r--r--
tokenize.rst.txt
5.44
KB
-rw-r--r--
trace.rst.txt
6.57
KB
-rw-r--r--
traceback.rst.txt
10.46
KB
-rw-r--r--
ttk.rst.txt
56.07
KB
-rw-r--r--
tty.rst.txt
1011
B
-rw-r--r--
turtle.rst.txt
62.59
KB
-rw-r--r--
types.rst.txt
6.05
KB
-rw-r--r--
undoc.rst.txt
6.4
KB
-rw-r--r--
unicodedata.rst.txt
5.59
KB
-rw-r--r--
unittest.rst.txt
81.01
KB
-rw-r--r--
unix.rst.txt
490
B
-rw-r--r--
urllib.rst.txt
24.38
KB
-rw-r--r--
urllib2.rst.txt
34.39
KB
-rw-r--r--
urlparse.rst.txt
16.56
KB
-rw-r--r--
user.rst.txt
2.68
KB
-rw-r--r--
userdict.rst.txt
9.07
KB
-rw-r--r--
uu.rst.txt
2.31
KB
-rw-r--r--
uuid.rst.txt
8.18
KB
-rw-r--r--
warnings.rst.txt
19.6
KB
-rw-r--r--
wave.rst.txt
4.93
KB
-rw-r--r--
weakref.rst.txt
12.62
KB
-rw-r--r--
webbrowser.rst.txt
9.63
KB
-rw-r--r--
whichdb.rst.txt
931
B
-rw-r--r--
windows.rst.txt
273
B
-rw-r--r--
winsound.rst.txt
4.95
KB
-rw-r--r--
wsgiref.rst.txt
29.85
KB
-rw-r--r--
xdrlib.rst.txt
7.89
KB
-rw-r--r--
xml.dom.minidom.rst.txt
10.95
KB
-rw-r--r--
xml.dom.pulldom.rst.txt
1.53
KB
-rw-r--r--
xml.dom.rst.txt
39.24
KB
-rw-r--r--
xml.etree.elementtree.rst.txt
34.87
KB
-rw-r--r--
xml.rst.txt
5.95
KB
-rw-r--r--
xml.sax.handler.rst.txt
15.01
KB
-rw-r--r--
xml.sax.reader.rst.txt
11.97
KB
-rw-r--r--
xml.sax.rst.txt
6.31
KB
-rw-r--r--
xml.sax.utils.rst.txt
3.48
KB
-rw-r--r--
xmlrpclib.rst.txt
22.03
KB
-rw-r--r--
zipfile.rst.txt
18.43
KB
-rw-r--r--
zipimport.rst.txt
5.82
KB
-rw-r--r--
zlib.rst.txt
12.47
KB
-rw-r--r--
Delete
Unzip
Zip
${this.title}
Close
Code Editor : htmlparser.rst.txt
:mod:`HTMLParser` --- Simple HTML and XHTML parser ================================================== .. module:: HTMLParser :synopsis: A simple parser that can handle HTML and XHTML. .. note:: The :mod:`HTMLParser` module has been renamed to :mod:`html.parser` in Python 3. The :term:`2to3` tool will automatically adapt imports when converting your sources to Python 3. .. versionadded:: 2.2 .. index:: single: HTML single: XHTML **Source code:** :source:`Lib/HTMLParser.py` -------------- 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. Unlike the parser in :mod:`htmllib`, this parser is not based on the SGML parser in :mod:`sgmllib`. .. class:: HTMLParser() 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. The :class:`.HTMLParser` class is instantiated without arguments. Unlike the parser in :mod:`htmllib`, 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. An exception is defined as well: .. exception:: HTMLParseError :class:`.HTMLParser` is able to handle broken markup, but in some cases it might raise this exception when it encounters an error while parsing. This exception provides three attributes: :attr:`msg` is a brief message explaining the error, :attr:`lineno` is the number of the line on which the broken construct was detected, and :attr:`offset` is the number of characters into the line at which the construct starts. 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 HTMLParser import HTMLParser # create a subclass and override the handler methods 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 # instantiate the parser and fed it some HTML 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* can be either :class:`unicode` or :class:`str`, but passing :class:`unicode` is advised. .. 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/')])``. .. versionchanged:: 2.6 All entity references from :mod:`htmlentitydefs` are now 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'``). .. 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'``. .. 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) This method is 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'")``. .. 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. .. _htmlparser-examples: Examples -------- The following class implements a parser that will be used to illustrate more examples:: from HTMLParser import HTMLParser from htmlentitydefs 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 = unichr(name2codepoint[name]) print "Named ent:", c def handle_charref(self, name): if name.startswith('x'): c = unichr(int(name[1:], 16)) else: c = unichr(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:: >>> 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
