initiatives.py 文件源码

def parse(self, response):

        list_types = Selector(response).xpath('//div[@class="listado_1"]//ul/li/a')
        for types in list_types:
            href=  types.xpath("./@href").extract()
            text = types.xpath("./text()").extract()
            if Terms.filterBytype(text[0]):
                type = Terms.getType(text[0])
                initiative_url = Utils.createUrl(response.url,href[0])
                yield scrapy.Request(initiative_url,errback=self.errback_httpbin,callback=self.initiatives, meta={'type': type})
        """
        urlsa = ""
        urlsa = "http://www.congreso.es/portal/page/portal/Congreso/Congreso/Iniciativas/Indice%20de%20Iniciativas?_piref73_1335503_73_1335500_1335500.next_page=/wc/servidorCGI&CMD=VERLST&BASE=IW12&PIECE=IWC2&FMT=INITXD1S.fmt&FORM1=INITXLUS.fmt&DOCS=100-100&QUERY=%28I%29.ACIN1.+%26+%28161%29.SINI."


        yield scrapy.Request(urlsa, errback=self.errback_httpbin, callback=self.oneinitiative,
                             meta={'type': u"Proposición no de Ley en Comisión"})
        """