Created
January 2, 2013 23:59
-
-
Save gordonmeyer/4439532 to your computer and use it in GitHub Desktop.
This script is for use with Keyboard Maestro, as described at: http://www.gordonmeyer.com/2013/01/keyboard-maestro-make-link-with-title-from-clipboard.html It outputs the title of a webpage. The URL is passed via a Keyboard Maestro variable. This is a rather crude, but reliable, method of getting the title and does not require the installation o…
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#! /usr/bin/python | |
""" | |
brute force get title of web page | |
usage: getTitle.py url | |
Gordon Meyer January 1, 2013 | |
www.gordonmeyer.com | |
""" | |
# modules used | |
import urllib2, urlparse, string, os | |
def getPage(theURL): | |
## returns the HTML text of the URL | |
req = urllib2.Request(theURL) | |
thePage = urllib2.urlopen(req) | |
theHTML = thePage.read() | |
return theHTML | |
## | |
def extractTitle(theLine): | |
## finds and returns contents of <title> tag | |
titleStart = theLine.find("<title>") | |
if titleStart > -1: #make sure we found the tag, -1 will mean we did not | |
titleStart = titleStart + 7 #skip to end of tag | |
titleEnd = theLine.find("</title>") | |
theTitle = theLine[titleStart:titleEnd] | |
theTitle = theTitle.strip() # remove whitespace | |
else: | |
theTitle = "" | |
return(theTitle) | |
## MAIN | |
# get URL from Keyboard Maestro variable | |
theURL = os.getenv('KMVAR_theURL') | |
thePageHTML = getPage(theURL) | |
theTitle = extractTitle(thePageHTML) | |
print theTitle |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment