Open Safari front window NYT article with the paywall removed.

opennyt.py

#!/usr/bin/env python

## opennyt.py
##
## Given a NYT article on the front page this reopens it without the paywall


import sys, os
import time, string, re
import urllib, json
from subprocess import PIPE, Popen


def  getsource():
    """
    Gets the html source of the front document in safariopen
    """
    applescript = """'
        tell application "Safari"
            get the source of the front document
        end tell
        '"""        
    cmd = "osascript -e " + applescript
    (out, err) = Popen(cmd, stdin=PIPE, stdout=PIPE, stderr=PIPE, close_fds=True, shell=True).communicate(None)
    print err
    return out
    
def scansource():
    """
    Scans source of NYT article for title
    """
    
    source = getsource().split("\n")
    for s in source:
            if "NYT_HEADLINE" in s:
                print s
                mobj = re.search(r"([\s\w]+)</NYT_", s)
                if mobj:
                    print mobj.group(1)
                    return mobj.group(1)
                else:
                    print "***"
                    
def safariopen(url):
    """
    Opens an url in the current tab in Safari
    """

    applescript = """'
        tell application "Safari" 
                set the URL of the front document to "http://%s"
            end tell
        '"""%url

    cmd = "osascript -e " + applescript
    print applescript
    
    (out, err) = Popen(cmd, stdin=PIPE, stdout=PIPE, stderr=PIPE, close_fds=True, shell=True).communicate(None)
    print err
    return out
    
def parsenewsdiffs(url):
    """
    Given a newsdiff's url gets the original nyts url
    """
    
    if "newsdiffs.org" in url:
        mobj = re.search(r"(www.nytimes.com.*)", url)
        if mobj:
            return mobj.group(1)
    else:
        return None 
    
def google(query):
    """  
    Gets a Google search result for the term, returning the url from newsdiffs 
    """
    
    if (query == None or query == "" or query == " "):
        return None
    
    searchurl = urllib.urlencode({'q':query})
    url = 'http://ajax.googleapis.com/ajax/services/search/web?v=1.0&%s' % searchurl
    
    response= urllib.urlopen(url).read()
    data = json.loads(response)
    results = data['responseData']['results']

    found_url = None   
    for r in results:
        print r['url']
        if "http://www.newsdiffs.org" in r['url']:
            found_url = parsenewsdiffs(r['url'])
            
    return found_url

def test():    
    result = google("to save a man's life a muddy tug of war with the earth itself")
    print result
    print safariopen( result )
    
def main():
    title =  scansource()
    result = google( title )
    safariopen( result )
    
if __name__ == '__main__':
        main()