使用Scrapy </script>从<script>标签中提取多行javascript内容

时间：2015-01-03 12:17:11

标签： javascript python regex scrapy

我尝试使用Scrapy从此脚本标记中提取数据：

<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>

我想从每个部分获得如下所示的数据：

 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
            };

然后从每个字段中获取数据并从例如upfrontPrice获取最终数据（例如，在此示例中为1099）。

我尝试使用此方法获取每个对象：

items = response.xpath('//script/text()').re("data.bundles\[.*\](.*)")

然而，这只给我第一行数据。 （= {）。那我该怎么做呢？有没有更好的方法从脚本标记中提取此数据？

修改：当我使用items = response.xpath('//script/text()').re("data.bundles\[.*\] = {((?s).*) };")时，我似乎只获得了最后一个块（data.bundles['KONTANT_KOMPLETT.REGULAR']

）

我如何获得所有这些的列表？

3 个答案:

答案 0 :(得分：5)

如果您不想使用正则表达式，可以使用js2xml来解析Javascript代码并将其转换为lxml文档。 然后，您可以使用XPath从Javascript语句中查询事物。 （免责声明：我编写并维护js2xml）

以下是有关如何获取data.bundles作业的示例代码：

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>""")

（第一部分是在Scrapy选择器中获取HTML输入）

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)

这是你从中得到的：

{'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'}}

有关js2xml.parse()获得的XML架构的详细信息，请查看https://github.com/redapple/js2xml/blob/master/SCHEMA.rst

答案 1 :(得分：4)

以下正则表达式似乎是正确的：

r"data\.bundles\[[^\]]*\] = {([^}]*)}"
正则表达式中的

*是贪婪的 - 它会尽可能地匹配，所以我使用[^\]]来确保我匹配最接近的]。我用{}括号做同样的事情。另外，我不必担心.不匹配换行符。

答案 2 :(得分：3)

此脚本需要安装Mozilla Firefox和python-selenium，我还使用名为script.txt的文件进行测试，该文件包含由标记包围的脚本。这是代码：

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)

结果变量如下所示：

{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}
相关问题
最新问题