HTTP GET - Download and Parse HTML

Downloads an HTML page from the Singapore Exchange and parses a row of options prices from an HTML table.

Download Chilkat Python Library

import sys
import chilkat

http = chilkat.CkHttp()

#  Any string unlocks the component for the 1st 30-days.
success = http.UnlockComponent("Anything for 30-day trial")
if (success != True):
    print http.lastErrorText()
    sys.exit()

#  Send the HTTP GET and return the content in a string.

html = http.quickGetStr("http://esite.sgx.com/live/dt/DTFuture.asp?JBFE")

#  Use the Chilkat HTML-to-XML component to convert
#  the HTML to parsable XML:
htmlToXml = chilkat.CkHtmlToXml()

#  Any string argument automatically begins the 30-day trial.
success = htmlToXml.UnlockComponent("30-day trial")
if (success != True):
    print "HtmlToXml component unlock failed"
    sys.exit()

#  Indicate the charset of the output XML we'll want.
htmlToXml.put_XmlCharset("utf-8")

#  Set the HTML:
htmlToXml.put_Html(html)

#  We won't need the scripts or images, so drop those tags...
htmlToXml.DropTagType("img")
htmlToXml.DropTagType("script")

#  Get the XML:

xmlStr = htmlToXml.toXml()

#  Load the XML into the Chilkat XML parser:
xml = chilkat.CkXml()
xml.LoadXml(xmlStr)

#  success = xml.SaveXml("out.xml");

#  Find a known point in the XML.  In this case we'll look for the text node
#  containing this string: "Chg From Prev Settle"
node = xml.SearchForContent(None,"text","Chg From Prev Settle")
if (node == None ):
    print "Did not find Chg From Prev Settle"
    sys.exit()

#  Move up to the TD node:
node.GetParent2()

#  Move up to the TR node:
node.GetParent2()

#  Move to the next row (i.e. next TR)
node.NextSibling2()

node.FirstChild2()
node.NextSibling2()

print "Expire Month/Year: " + node.getChildContent("text")
node.NextSibling2()

print "Last: " + node.getChildContent("text")
node.NextSibling2()

print "Change: " + node.getChildContent("text")
node.NextSibling2()

#  ...

success = node.SaveXml("row.xml")