Patent.py 文件源码

def parsePatentDetail(self, response):
        sipo = response.meta['sipo']
        sipocrawler = response.meta['sipocrawler']
        detail = json.loads(response.body_as_unicode())
        sipocrawler['abstract'] = BeautifulSoup(detail.get('abstractInfoDTO').get('abIndexList')[0].get('value'),
                                                'lxml').text.replace('\n', '').strip()
        sipocrawler['invention_name'] = detail.get('abstractInfoDTO').get('tioIndex').get('value')
        for abitem in detail.get('abstractInfoDTO').get('abstractItemList'):
            ItemCollection.resolveData(sipocrawler, abitem.get('indexCnName'), abitem.get('value'))
        lawinfo = response.meta.get('lawinfo')
        formdata = url_config.relatedInfo.get('formdata')
        formdata.__setitem__('literaInfo.nrdAn', lawinfo.get('nrdAn'))
        formdata.__setitem__('literaInfo.nrdPn', lawinfo.get('nrdPn'))
        yield FormRequest(
            url=url_config.relatedInfo.get('url'),
            method='POST',
            dont_filter=True,  # ???????????????????????????
            formdata=formdata,
            callback=self.parseRelatedInfo,
            meta={'sipo': sipo, 'sipocrawler': sipocrawler}
        )

    # ??????