Python Event.extras['unique-id']方法代码示例

# 需要导入模块: from pupa.scrape import Event [as 别名]
# 或者: from pupa.scrape.Event import extras['unique-id'] [as 别名]
    def _parse_house_floor_xml_legislative_activity(self, xml):
        """
        Parses XML string of House floor updates and yields them in loop.

        @param xml: XML of field update
        @type xml: string
        @return: complete Event object
        @rtype: Event
        """
        tree = self._xml_parser(xml)

        congress = tree.xpath('.//legislative_congress')[0].get('congress')

        house_committees = self._get_current_house_committee_names()
        for fa in tree.xpath('.//floor_action'):
            fa_text = fa.xpath('.//action_description')[0].xpath('string()')

            eastern = pytz.timezone('US/Eastern')
            dt = datetime.datetime.strptime(fa.xpath('action_time')[0].get('for-search'), '%Y%m%dT%H:%M:%S')
            event = Event('House Floor Update on {0} at {1}.'.format(dt.strftime('%Y-%m-%d'), dt.strftime('%H:%M:%S')),
                          eastern.localize(dt).astimezone(pytz.utc),
                          'US/Eastern',
                          '',
                          description=fa_text,
                          classification='floor_update')

            event.set_location("East Capitol Street Northeast & First St SE, Washington, DC 20004",
                               note='House Floor', url='http://www.house.gov',
                               coordinates={'latitude': '38.889931', 'longitude': '-77.009003'})

            event.add_source(self._house_floor_src_url(date_str=tree.xpath('.//legislative_day')[0].get('date')),
                             note="Scraped from the Office of the Clerk, U.S. House of Representatives website.")

            event.extras['act-id'] = fa.get('act-id')
            event.extras['unique-id'] = fa.get('unique-id')

            # bills
            ai_b = event.add_agenda_item(description='Bills referenced by this update.')
            for bill in fa.xpath(".//a[@rel='bill']"):
                bill_name = bill.xpath('string()')
                ai_b.add_bill(bill_name, id=make_pseudo_id(identifier=bill_code_to_id(bill_name), congress=congress),
                              note="Bill was referenced on the House floor.")

            # publaws
            ai_p = event.add_agenda_item(description='Public laws referenced by this update.')
            for law in fa.xpath(".//a[@rel='publaw']"):
                detail_url = '/'.join(law.get('href').split('/')[0:-2]) + '/content-detail.html'
                ai_p.add_bill(law.xpath('string()'),
                              id=make_pseudo_id(**self._public_law_detail_scraper(url=detail_url)),
                              note='Law was referenced on the House floor.')

            # votes
            ai_v = event.add_agenda_item(description='Votes referenced by this update.')
            for vote in fa.xpath(".//a[@rel='vote']"):
                vote_name = vote.xpath('string()')
                ai_v.add_vote(vote_name,
                              id=make_pseudo_id(identifier=vote_code_to_id(vote_name), congress=congress),
                              note='Vote was referenced on the House floor.')

            # reports
            for report in fa.xpath(".//a[@rel='report']"):
                event.add_document('Document referenced by this update.', report.get('href'), media_type='text/html')

            for name in house_committees:
                if name.replace('House ', '') in fa_text:
                    event.add_committee(name, id=make_pseudo_id(name=name))

            # TODO identify legislators and add them as participants?


            yield event