ScrapyJS - 如何正确等待页面加载？

Question

我正在使用ScrapyJS和Splash模拟表单提交按钮单击

def start_requests(self):
        script = """
        function main(splash)
            assert(splash:autoload("https://ajax.googleapis.com/ajax/libs/jquery/2.1.3/jquery.min.js"))
            assert(splash:go(splash.args.url))

            local js = [[
                var $j = jQuery.noConflict();
                $j('#USER').val('frankcastle');
                $j('#password').val('punisher');
                $j('.button-oblong-orange.button-orange a').click();
            ]]

            assert(splash:runjs(js))

            local resumeJs = [[
                function main(splash) {
                    var $j = jQuery.noConflict();
                    $j(document).ready(function(){
                        splash.resume();
                    })
                }
            ]]

        assert(splash:wait_for_resume(resumeJs))

            return {
                html = splash:html()
            }
        end
        """
        splash_meta = {'splash': {'endpoint': 'execute', 'args': {'wait': 0.5, 'lua_source': script}}}

        for url in self.start_urls:
            yield scrapy.Request(url, self.after_login, meta=splash_meta)

def after_login(self, response):
        print response.body
        return

在做完之后splash:runjs(js),我splash:wait(5)试图splash:wait_for_resume获得结果.这可能并不总是有效(网络延迟),那么有更好的方法吗？

Answer 1

事实证明,唯一的方法是使用splash:wait()它,但在循环中执行并检查某些元素的可用性(如页脚).

def start_requests(self):
        script = """
        function main(splash)
            assert(splash:autoload("https://ajax.googleapis.com/ajax/libs/jquery/2.1.3/jquery.min.js"))
            assert(splash:go(splash.args.url))

            local js = [[
                var $j = jQuery.noConflict();
                $j('#USER').val('frankcastle');
                $j('#password').val('punisher');
                $j('.button-oblong-orange.button-orange a').click();
                $j('body').empty() // clear body, otherwise the wait_for footer will always be true
            ]]

            assert(splash:runjs(js))

            function wait_for(splash, condition)
                while not condition() do
                    splash:wait(0.05)
                end
            end

            wait_for(splash, function()
                return splash:evaljs("document.querySelector('#footer') != null")
            end)

            return {
                html = splash:html()
            }
        end
        """
        splash_meta = {'splash': {'endpoint': 'execute', 'args': {'wait': 0.5, 'lua_source': script}}}

        for url in self.start_urls:
            yield scrapy.Request(url, self.after_login, meta=splash_meta)