Fixed dict structure in makeHTMLTags expressions, and added tag_body attribute to the generated start expression giving easy access to a SkipTo(closeTag) that will parse the tag's body text; some code cleanup and removed duplication among examples

1 files changed, 36 insertions, 35 deletions

diff --git a/examples/getNTPserversNew.py b/examples/getNTPserversNew.py
index c87c0ae..c86e756 100644
--- a/examples/getNTPserversNew.py
+++ b/examples/getNTPserversNew.py
@@ -1,35 +1,36 @@
-# getNTPserversNew.py

-#

-# Demonstration of the parsing module, implementing a HTML page scanner,

-# to extract a list of NTP time servers from the NIST web site.

-#

-# Copyright 2004-2010, by Paul McGuire

-# September, 2010 - updated to more current use of setResultsName, new NIST URL

-#

-from pyparsing import (Word, Combine, SkipTo, nums, makeHTMLTags,

-                        delimitedList, alphas, alphanums)

-try:

-    import urllib.request

-    urlopen = urllib.request.urlopen

-except ImportError:

-    import urllib

-    urlopen = urllib.urlopen

-

-integer = Word(nums)

-ipAddress = Combine( integer + "." + integer + "." + integer + "." + integer )

-hostname = delimitedList(Word(alphas,alphanums+"-_"),".",combine=True)

-tdStart,tdEnd = makeHTMLTags("td")

-timeServerPattern =  (tdStart + hostname("hostname") + tdEnd +

-                      tdStart + ipAddress("ipAddr") + tdEnd +

-                      tdStart + SkipTo(tdEnd)("loc") + tdEnd)

-

-# get list of time servers

-nistTimeServerURL = "https://tf.nist.gov/tf-cgi/servers.cgi#"

-serverListPage = urlopen( nistTimeServerURL )

-serverListHTML = serverListPage.read().decode("UTF-8")

-serverListPage.close()

-

-addrs = {}

-for srvr,startloc,endloc in timeServerPattern.scanString( serverListHTML ):

-    print("{0} ({1}) - {2}".format(srvr.ipAddr, srvr.hostname.strip(), srvr.loc.strip()))

-    addrs[srvr.ipAddr] = srvr.loc

+# getNTPserversNew.py
+#
+# Demonstration of the parsing module, implementing a HTML page scanner,
+# to extract a list of NTP time servers from the NIST web site.
+#
+# Copyright 2004-2010, by Paul McGuire
+# September, 2010 - updated to more current use of setResultsName, new NIST URL
+#
+import pyparsing as pp
+ppc = pp.pyparsing_common
+from contextlib import closing
+
+try:
+    import urllib.request
+    urlopen = urllib.request.urlopen
+except ImportError:
+    import urllib
+    urlopen = urllib.urlopen
+
+integer = pp.Word(pp.nums)
+ipAddress = ppc.ipv4_address()
+hostname = pp.delimitedList(pp.Word(pp.alphas, pp.alphanums+"-_"), ".", combine=True)
+tdStart, tdEnd = pp.makeHTMLTags("td")
+timeServerPattern = (tdStart + hostname("hostname") + tdEnd
+                     + tdStart + ipAddress("ipAddr") + tdEnd
+                     + tdStart + tdStart.tag_body("loc") + tdEnd)
+
+# get list of time servers
+nistTimeServerURL = "https://tf.nist.gov/tf-cgi/servers.cgi#"
+with closing(urlopen(nistTimeServerURL)) as serverListPage:
+    serverListHTML = serverListPage.read().decode("UTF-8")
+
+addrs = {}
+for srvr, startloc, endloc in timeServerPattern.scanString(serverListHTML):
+    print("{0} ({1}) - {2}".format(srvr.ipAddr, srvr.hostname.strip(), srvr.loc.strip()))
+    addrs[srvr.ipAddr] = srvr.loc