Python Bill.legislative_session方法代码示例

# 需要导入模块: from pupa.scrape import Bill [as 别名]
# 或者: from pupa.scrape.Bill import legislative_session [as 别名]
    def scrape(self):
        for leg_summary in self.legislation(created_after=datetime.datetime(2014, 1, 1)) :
            leg_type = BILL_TYPES[leg_summary['Type']]
            
            bill = Bill(identifier=leg_summary['File\xa0#'],
                        title=leg_summary['Title'],
                        legislative_session=None,
                        classification=leg_type,
                        from_organization={"name":"New York City Council"})
            bill.add_source(leg_summary['url'])

            leg_details = self.legDetails(leg_summary['url'])
            history = self.history(leg_summary['url'])

            bill.add_title(leg_details['Name'], 
                           note='created by administrative staff')

            if 'Summary' in leg_details :
                bill.add_abstract(leg_details['Summary'], note='')

            if leg_details['Law number'] :
                bill.add_identifier(leg_details['Law number'], 
                                    note='law number')

            for sponsorship in self._sponsors(leg_details.get('Sponsors', [])) :
                sponsor, sponsorship_type, primary = sponsorship
                bill.add_sponsorship(sponsor, sponsorship_type,
                                     'person', primary, 
                                     entity_id = make_pseudo_id(name=sponsor))

            
            for attachment in leg_details.get('Attachments', []) :
                bill.add_document_link(attachment['label'],
                                       attachment['url'],
                                       media_type="application/pdf")

            history = list(history)

            if history :
                earliest_action = min(self.toTime(action['Date']) 
                                      for action in history)

                bill.legislative_session = self.sessions(earliest_action)
            else :
                bill.legislative_session = str(self.SESSION_STARTS[0])

            for action in history :
                action_description = action['Action']
                if not action_description :
                    continue
                    
                action_class = ACTION_CLASSIFICATION[action_description]

                action_date = self.toDate(action['Date'])
                responsible_org = action['Action\xa0By']
                if responsible_org == 'City Council' :
                    responsible_org = 'New York City Council'
                elif responsible_org == 'Administration' :
                    responsible_org = 'Mayor'
                   
                if responsible_org == 'Town Hall Meeting' :
                    continue
                else :
                    act = bill.add_action(action_description,
                                          action_date,
                                          organization={'name': responsible_org},
                                          classification=action_class)

                if 'url' in action['Action\xa0Details'] :
                    action_detail_url = action['Action\xa0Details']['url']
                    if action_class == 'committee-referral' :
                        action_details = self.actionDetails(action_detail_url)
                        referred_committee = action_details['Action text'].rsplit(' to the ', 1)[-1]
                        act.add_related_entity(referred_committee,
                                               'organization',
                                               entity_id = make_pseudo_id(name=referred_committee))
                    result, votes = self.extractVotes(action_detail_url)
                    if votes :
                        action_vote = VoteEvent(legislative_session=bill.legislative_session, 
                                           motion_text=action_description,
                                           organization={'name': responsible_org},
                                           classification=action_class,
                                           start_date=action_date,
                                           result=result,
                                           bill=bill)
                        action_vote.add_source(action_detail_url)

                        for option, voter in votes :
                            action_vote.vote(option, voter)


                        yield action_vote
            
            text = self.text(leg_summary['url'])

            if text :
                bill.extras = {'local_classification' : leg_summary['Type'],
                               'full_text' : text}
            else :
                bill.extras = {'local_classification' : leg_summary['Type']}
#.........这里部分代码省略.........

# 需要导入模块: from pupa.scrape import Bill [as 别名]
# 或者: from pupa.scrape.Bill import legislative_session [as 别名]
    def scrape(self):
        for agenda_item in self.agendaItems(date_from=self.start_date, date_to=self.end_date):
            # TODO: Add agenda_item type to OCD
            leg_type = "bill"

            title = agenda_item["Title"].replace("\n", " ")
            title_re = re.compile(
                "^(.+?)(?: - (?:by )?((?:Deputy )?Mayor|Councillor) (.+), seconded by ((?:Deputy )?Mayor|Councillor) (.+))?$"
            )
            title, primary_role, primary_sponsor, secondary_role, secondary_sponsor = re.match(title_re, title).groups()

            b = Bill(
                identifier=agenda_item["Item No."],
                title=title,
                legislative_session=None,
                classification=leg_type,
                from_organization={"name": self.jurisdiction.name},
            )
            b.add_source(agenda_item["url"], note="web")

            if primary_sponsor and secondary_sponsor:
                b.add_sponsorship(primary_sponsor, "mover", "person", True)
                b.add_sponsorship(secondary_sponsor, "seconder", "person", False)

            # TODO: Fake session for now
            b.legislative_session = "2014-2018"

            agenda_item_versions = self.agendaItemVersions(agenda_item["url"])

            # Use one version's full_text (will be most recent)
            b.extras["full_text"] = agenda_item_versions[0]["full_text"]

            for version in agenda_item_versions:
                action_date = self.toDate(version["date"])

                if "Summary" in version["sections"]:
                    # TODO: Investigate whether these vary between versions, as
                    # we perhaps don't need to add one for each
                    b.add_abstract(version["sections"]["Summary"], note="", date=action_date)

                if not version["action"]:
                    continue
                if re.match(r"\d+:\d+ [A|P]M", version["action"]):
                    continue

                action_description = version["action"]
                responsible_org = version["responsible_org"]
                action_class = ACTION_CLASSIFICATION.get(version["action"])

                def is_recommendation(version):
                    return any("Recommendations" in s for s in version["sections"].keys())

                if responsible_org == "City Council":
                    responsible_org = self.jurisdiction.name
                else:
                    if action_class == "passage":
                        action_class = "committee-passage"

                        if is_recommendation(version):
                            action_class = "committee-passage-favorable"

                b.add_action(
                    action_description, action_date, organization={"name": responsible_org}, classification=action_class
                )

            yield b