如果您不想使用正則表達式,那么有js2xml ,它解析Javascript代碼並將其轉換為lxml文檔。 然后,您可以使用XPath從Javascript語句中查詢事物。 (免責聲明:我編寫並維護js2xml)
以下是有關如何獲取這些data.bundles
分配的示例代碼:
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選擇器中獲取HTML輸入)
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)
這就是你從中得到的:
{'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'}}
有關使用js2xml.parse()
獲得的XML模式的更多信息,可以查看https://github.com/redapple/js2xml/blob/master/SCHEMA.rst