| Server IP : 109.234.164.53 / Your IP : 216.73.216.110 Web Server : Apache System : Linux cervelle.o2switch.net 4.18.0-553.32.1.lve.el8.x86_64 #1 SMP Thu Dec 19 13:14:03 UTC 2024 x86_64 User : computer3 ( 1098) PHP Version : 7.1.33 Disable Function : NONE MySQL : OFF | cURL : ON | WGET : ON | Perl : ON | Python : ON | Sudo : OFF | Pkexec : OFF Directory : /opt/alt/python37/share/doc/alt-python37-pyparsing-doc/examples/ |
Upload File : |
#
# htmlStripper.py
#
# Sample code for stripping HTML markup tags and scripts from
# HTML source files.
#
# Copyright (c) 2006, 2016, Paul McGuire
#
from urllib.request import urlopen
from pyparsing import (
makeHTMLTags,
commonHTMLEntity,
replaceHTMLEntity,
htmlComment,
anyOpenTag,
anyCloseTag,
LineEnd,
replaceWith,
)
scriptOpen, scriptClose = makeHTMLTags("script")
scriptBody = scriptOpen + scriptOpen.tag_body + scriptClose
commonHTMLEntity.setParseAction(replaceHTMLEntity)
# get some HTML
targetURL = "https://wiki.python.org/moin/PythonDecoratorLibrary"
with urlopen(targetURL) as targetPage:
targetHTML = targetPage.read().decode("UTF-8")
# first pass, strip out tags and translate entities
firstPass = (
(htmlComment | scriptBody | commonHTMLEntity | anyOpenTag | anyCloseTag)
.suppress()
.transformString(targetHTML)
)
# first pass leaves many blank lines, collapse these down
repeatedNewlines = LineEnd() * (2,)
repeatedNewlines.setParseAction(replaceWith("\n\n"))
secondPass = repeatedNewlines.transformString(firstPass)
print(secondPass)