#!/usr/bin/env python
import os
import sys
import signal
from optparse import OptionParser
from PyQt4.QtCore import *
from PyQt4.QtGui import *
from PyQt4.QtWebKit import QWebPage

JQUERY_URL  = "http://jquery.com/src/jquery-latest.js"
JQUERY_FILE = "jquery.js"
JQUERY_PATH = os.path.join(os.path.dirname(__file__), JQUERY_FILE)

class WebPage(QWebPage):
    "print javascript errors to stderr"
    def javaScriptConsoleMessage(self, message, line_number, source_id):
        sys.stdout.write(message)
        sys.stdout.write("\n")

class Crawler(WebPage):
    def __init__(self, url, file):
        WebPage.__init__(self)
        self._url = url
        self._file = file
 
    def crawl(self):
        signal.signal(signal.SIGINT, signal.SIG_DFL)
        self.connect(self, SIGNAL("loadFinished(bool)"), self._finished_loading)
        self.mainFrame().load(QUrl(self._url))
 
    def _finished_loading(self, status):
        #inject jquery
        jq_file_handler = open(JQUERY_PATH, "r")
        jquery = jq_file_handler.read()
        jq_file_handler.close()
        self.mainFrame().evaluateJavaScript(jquery)
        
        #pass it on
        self.scraper()

    def scraper(self):
        #file = open(self._file, "w")
        #file.write(self.mainFrame().toHtml())
        #file.close()

        print "main tag name: " + self.mainFrame().documentElement().tagName()
        print "current document title is: " + self.mainFrame().title()

        #this is how you handle a hash
        print "result is: " + str(self.mainFrame().evaluateJavaScript("x={'key': 'value', 'key2': 'value2'};x").toMap().keys())

        #let's test console output
        self.mainFrame().evaluateJavaScript("console.log(\"this message indicates that console.log() is working.\")")

        #how about something more complicated?
        self.mainFrame().evaluateJavaScript("function thinker() { return 55; }")
        result = self.mainFrame().evaluateJavaScript("thinker").toString()
        print "result is: " + result
        
        #self.mainFrame().evaluateJavaScript("function changer() { document.title = 'billy bob'; }")
        #changer = self.globalObject().property("changer")
        sys.exit(0)
 
def main():
    app = QApplication(sys.argv)
    options = get_cmd_options()
    crawler = Crawler(options.url, options.file)
    crawler.crawl()
    sys.exit(app.exec_())
 
def get_cmd_options():
    """
        gets and validates the input from the command line
    """
    usage = "usage: %prog [options] args"
    parser = OptionParser(usage)
    parser.add_option("-u", "--url", dest = "url", help = "URL to fetch data from")
    parser.add_option("-f", "--file", dest = "file", help = "Local file path to save data to")
 
    (options,args) = parser.parse_args()
 
    if not options.url:
        print "You must specify an URL.", sys.argv[0], "--help for more details"
        exit(1)
    if not options.file:
        print "You must specify a destination file.", sys.argv[0], "--help for more details"
        exit(1)
 
    return options
 
if __name__ == '__main__':
    main()