initiatives.py 文件源码

def fragmenttxt(self, response,number):
        pages = Selector(response).xpath('//p/a/@name').extract()
        text = Selector(response).xpath('//div[@class="texto_completo"]').extract()
        result = []
        control = False


        try:
            firstopage = Utils.getnumber(pages[0])
        except:
            firstopage= "1"
            control = True

        # selecciona del texto solo la pagina que nos resulta útil
        splittext = text[0].split("<br><br>")
        for i in splittext:
            if Utils.checkPage(i,number):
                control = True
                continue
            elif int(number) < int(firstopage):
                control = True
            if control  and Utils.checkPage(i,str(int(number)+1)):
                break
            if control:
                result.append(i)


        return Utils.concatlist(result)