Extract multi-line javascript content from <script> tag using Scrapy

If you don't want to play around with regular expressions, there's js2xml, which parses Javascript code and converts it to an lxml document. Then you can use XPath to query things from the Javascript statements. (disclaimer: I wrote and maintain js2xml)

Here's sample code on how to get those data.bundles assignments:

import scrapy

selector = scrapy.Selector(text="""<script>
        var hardwareTemplateFunctions;
        var storefrontContextUrl = '';

        jq(function() {
            var data = new Object();
            data.hardwareProductCode = '9054832';
            data.offeringCode = 'SMART_BASIC.TLF12PLEAS';
            data.defaultTab = '';
            data.categoryId = 10001;

            data.bundles = new Object();
                            data.bundles['SMART_SUPERX.TLF12PLEAS'] = {
                    signupFee: parsePrice('0'),
                    newMsisdnFee: parsePrice('199'),
                    upfrontPrice: parsePrice('1099'),
                    monthlyPrice: parsePrice('499'),
                    commitmentTime: parsePrice('12'),
                    offeringTitle: 'SMART Super',
                    offeringType: 'VOICE',
                    monthlyPrice: parsePrice('499'),
                    commitmentTime: 12
                };
                            data.bundles['SMART_PLUSS.TLF12PLEAS'] = {
                    signupFee: parsePrice('0'),
                    newMsisdnFee: parsePrice('199'),
                    upfrontPrice: parsePrice('1599'),
                    monthlyPrice: parsePrice('399'),
                    commitmentTime: parsePrice('12'),
                    offeringTitle: 'SMART Pluss',
                    offeringType: 'VOICE',
                    monthlyPrice: parsePrice('399'),
                    commitmentTime: 12
                };
                            data.bundles['SMART_BASIC.TLF12PLEAS'] = {
                    signupFee: parsePrice('0'),
                    newMsisdnFee: parsePrice('199'),
                    upfrontPrice: parsePrice('2199'),
                    monthlyPrice: parsePrice('299'),
                    commitmentTime: parsePrice('12'),
                    offeringTitle: 'SMART Basis',
                    offeringType: 'VOICE',
                    monthlyPrice: parsePrice('299'),
                    commitmentTime: 12
                };
                            data.bundles['SMART_MINI.TLF12PLEAS'] = {
                    signupFee: parsePrice('0'),
                    newMsisdnFee: parsePrice('199'),
                    upfrontPrice: parsePrice('2999'),
                    monthlyPrice: parsePrice('199'),
                    commitmentTime: parsePrice('12'),
                    offeringTitle: 'SMART Mini',
                    offeringType: 'VOICE',
                    monthlyPrice: parsePrice('199'),
                    commitmentTime: 12
                };
                            data.bundles['KONTANT_KOMPLETT.REGULAR'] = {
                    signupFee: parsePrice('0'),
                    newMsisdnFee: parsePrice('0'),
                    upfrontPrice: parsePrice('3499'),
                    monthlyPrice: parsePrice('0'),
                    commitmentTime: parsePrice('0'),
                    offeringTitle: 'SMART Kontant',
                    offeringType: 'PREPAID',
                    monthlyPrice: parsePrice('0'),
                    commitmentTime: 0
                };

            data.reviewJson = new Object();


            hardwareTemplateFunctions = hardwareTemplateFunctions(data);
            hardwareTemplateFunctions.init();

            data.reviewSummaryBox = hardwareTemplateFunctions.reviewSummaryBox;

            accessoryFunctions(data).init();
            additionalServiceFunctions(data).init();
        });

        function parsePrice(str) {
            var price = parseFloat(str);
            return isNaN(price) ? 0 : price;
        }

        var offerings = {};
    </script>""")

(this first part is to get the HTML input in a Scrapy Selector)

import js2xml
import pprint

data_bundles = {}
for script in selector.xpath('//script/text()').extract():
    # this is how you turn Javascript code into an XML document (lxml document in fact)
    jstree = js2xml.parse(script)

    # then, we're interested in assignments of data.bundles object
    for a in jstree.xpath('//assign[left//property/identifier/@name="bundles" and right/object]'):
        # the assigned property is give by a <string> property from a <bracketaccessor>
        bundle_prop = a.xpath('./left/bracketaccessor/property/string/text()')
        if bundle_prop is not None:
            curr_prop = bundle_prop[0]

        data_bundles[curr_prop] = {}

        # the left object is assigned an object (inside a <right> element)
        # let's loop on the <property> elements)
        # the values are either numbers or string arguments of a function call
        for prop in a.xpath('./right/object/property'):
            data_bundles[curr_prop][prop.xpath('@name')[0]] = prop.xpath('.//number/@value | .//string/text()')[0]

pprint.pprint(data_bundles)

This is what you get out of this:

{'KONTANT_KOMPLETT.REGULAR': {'commitmentTime': '0',
                              'monthlyPrice': '0',
                              'newMsisdnFee': '0',
                              'offeringTitle': 'SMART Kontant',
                              'offeringType': 'PREPAID',
                              'signupFee': '0',
                              'upfrontPrice': '3499'},
 'SMART_BASIC.TLF12PLEAS': {'commitmentTime': '12',
                            'monthlyPrice': '299',
                            'newMsisdnFee': '199',
                            'offeringTitle': 'SMART Basis',
                            'offeringType': 'VOICE',
                            'signupFee': '0',
                            'upfrontPrice': '2199'},
 'SMART_MINI.TLF12PLEAS': {'commitmentTime': '12',
                           'monthlyPrice': '199',
                           'newMsisdnFee': '199',
                           'offeringTitle': 'SMART Mini',
                           'offeringType': 'VOICE',
                           'signupFee': '0',
                           'upfrontPrice': '2999'},
 'SMART_PLUSS.TLF12PLEAS': {'commitmentTime': '12',
                            'monthlyPrice': '399',
                            'newMsisdnFee': '199',
                            'offeringTitle': 'SMART Pluss',
                            'offeringType': 'VOICE',
                            'signupFee': '0',
                            'upfrontPrice': '1599'},
 'SMART_SUPERX.TLF12PLEAS': {'commitmentTime': '12',
                             'monthlyPrice': '499',
                             'newMsisdnFee': '199',
                             'offeringTitle': 'SMART Super',
                             'offeringType': 'VOICE',
                             'signupFee': '0',
                             'upfrontPrice': '1099'}}

For more info on the XML schema you get with js2xml.parse(), you can check https://github.com/redapple/js2xml/blob/master/SCHEMA.rst

This script requires Mozilla Firefox and python-selenium installed, also I made the tests using a file called script.txt, which contains the script surrounded by tag. Here's the code:

from selenium import webdriver

script_content = open("script.txt").read()

#Removing script tags
exec_script = script_content.replace("<script>", "").replace("</script>", "")

#Removing jq function call
exec_script = exec_script.replace("jq(function() {", "").replace("});", "")

#Setting some helper functions to avoid javascript errors
helper_functions = """function hardwareTemplateFunctions(){
                     return {init: function(){}};};  
                     accessoryFunctions = additionalServiceFunctions = 
                     hardwareTemplateFunctions;"""

#Returning data variable
return_statement = "return data;"

wd = webdriver.Firefox()

#Getting data variable in result
result = wd.execute_script(helper_functions + exec_script +  return_statement)

The result variable looks like this:

{u'bundles': {u'KONTANT_KOMPLETT.REGULAR': {u'commitmentTime': 0,
   u'monthlyPrice': 0,
   u'newMsisdnFee': 0,
   u'offeringTitle': u'SMART Kontant',
   u'offeringType': u'PREPAID',
   u'signupFee': 0,
   u'upfrontPrice': 3499},
  u'SMART_BASIC.TLF12PLEAS': {u'commitmentTime': 12,
   u'monthlyPrice': 299,
   u'newMsisdnFee': 199,
   u'offeringTitle': u'SMART Basis',
   u'offeringType': u'VOICE',
   u'signupFee': 0,
   u'upfrontPrice': 2199},
  u'SMART_MINI.TLF12PLEAS': {u'commitmentTime': 12,
   u'monthlyPrice': 199,
   u'newMsisdnFee': 199,
   u'offeringTitle': u'SMART Mini',
   u'offeringType': u'VOICE',
   u'signupFee': 0,
   u'upfrontPrice': 2999},
  u'SMART_PLUSS.TLF12PLEAS': {u'commitmentTime': 12,
   u'monthlyPrice': 399,
   u'newMsisdnFee': 199,
   u'offeringTitle': u'SMART Pluss',
   u'offeringType': u'VOICE',
   u'signupFee': 0,
   u'upfrontPrice': 1599},
  u'SMART_SUPERX.TLF12PLEAS': {u'commitmentTime': 12,
   u'monthlyPrice': 499,
   u'newMsisdnFee': 199,
   u'offeringTitle': u'SMART Super',
   u'offeringType': u'VOICE',
   u'signupFee': 0,
   u'upfrontPrice': 1099}},
 u'categoryId': 10001,
 u'defaultTab': u'',
 u'hardwareProductCode': u'9054832',
 u'offeringCode': u'SMART_BASIC.TLF12PLEAS',
 u'reviewJson': {},
 u'reviewSummaryBox': None}