holerite.py 文件源码

def parse_entities(self, response):
        """
        A table is displayed with the data about the person
        who works at the Câmara
        """

        mesano = response.meta['mesano']

        self.log('Getting mesano: ' + mesano)

        # Check if the table is empty
        if not response.css('table tr td:nth-child(1)').extract_first():
            return self.log('Nenhum dado disponível')

        for tr in response.xpath('//table/tr').extract():
            selector = Selector(text=tr)
            entity_id = re.search("(javascript:pesquisa\()(\d*)(\);)", tr).group(2)

            request = scrapy.FormRequest(
                url=BASE_URL + 'holerite/consulta_beneficiario.html',
                formdata={
                    'hol_ben_id': entity_id,
                    'hol_mesano': mesano,
                    'hol_tipo': '1',
                    'hol_grupo': GRUPO,
                    'acao':''
                },
                callback=self.parse_salaries
            )

            request.meta['name'] = selector.xpath("//tr/td/text()").extract_first()
            request.meta['entity_id'] = entity_id
            request.meta['mesano'] = mesano

            yield request