| Server IP : 88.222.222.18 / Your IP : 216.73.216.254 Web Server : LiteSpeed System : Linux id-dci-web1986.main-hosting.eu 5.14.0-611.26.1.el9_7.x86_64 #1 SMP PREEMPT_DYNAMIC Thu Jan 29 05:24:47 EST 2026 x86_64 User : u686484674 ( 686484674) PHP Version : 8.0.30 Disable Function : system, exec, shell_exec, passthru, mysql_list_dbs, ini_alter, dl, symlink, link, chgrp, leak, popen, apache_child_terminate, virtual, mb_send_mail MySQL : OFF | cURL : ON | WGET : ON | Perl : OFF | Python : OFF | Sudo : OFF | Pkexec : OFF Directory : /opt/gsutil/third_party/pyparsing/examples/ |
Upload File : |
# URL extractor
# Copyright 2004, Paul McGuire
from pyparsing import makeHTMLTags, pyparsing_common as ppc
from urllib.request import urlopen
import pprint
linkOpenTag, linkCloseTag = makeHTMLTags("a")
linkBody = linkOpenTag.tag_body
linkBody.setParseAction(ppc.stripHTMLTags)
linkBody.addParseAction(lambda toks: " ".join(toks[0].strip().split()))
link = linkOpenTag + linkBody("body") + linkCloseTag.suppress()
# Go get some HTML with some links in it.
with urlopen("https://www.cnn.com/") as serverListPage:
htmlText = serverListPage.read().decode("UTF-8")
# scanString is a generator that loops through the input htmlText, and for each
# match yields the tokens and start and end locations (for this application, we are
# not interested in the start and end values).
for toks, strt, end in link.scanString(htmlText):
print(toks.asList())
# Create dictionary from list comprehension, assembled from each pair of tokens returned
# from a matched URL.
pprint.pprint({toks.body: toks.href for toks, strt, end in link.scanString(htmlText)})