Python Bill.add_sponsor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 add_sponsor [as 别名]
    def scrape(self):
        self.session = '2011'

        for i, page in enumerate(self.searchLegislation()) :
            for legislation_summary in self.parseSearchResults(page) :
                title = legislation_summary['Title'].strip()
                if title == "":
                    continue

                bill = Bill(name=legislation_summary['Record #'],
                            session=self.session,
                            title=title,
                            type=[legislation_summary['Type'].lower()],
                            organization=self.jurisdiction.name)

                bill.add_source(legislation_summary['URL'])

                legislation_details = self.expandLegislationSummary(legislation_summary)

                for related_bill in legislation_details.get('Related files', []) :
                    bill.add_related_bill(name = related_bill,
                                          session = self.session,
                                          relation='other-session',
                                          chamber=None)

                for i, sponsor in enumerate(legislation_details.get('Sponsors', [])) :
                    if i == 0 :
                        primary = True
                        sponsorship_type = "Primary"
                    else :
                        primary = False
                        sponsorship_type = "Regular"

                    bill.add_sponsor(sponsor, sponsorship_type,
                                     'person', primary)

                for subject in legislation_details.get(u'Topics', []) :
                    bill.add_subject(subject)

                for attachment in legislation_details.get(u'Attachments', []) :
                    bill.add_version_link('PDF',
                                          attachment['url'],
                                          mimetype="application/pdf")


                yield bill

# 需要导入模块: from pupa.scrape import Bill [as 别名]
# 或者: from pupa.scrape.Bill import add_sponsor [as 别名]
    def old_scrape(self, session=None):
        status_report_url = "https://www.legislature.ohio.gov/legislation/status-reports"

        # ssl verification off due Ohio not correctly implementing SSL
        if not session:
            session = self.latest_session()
            self.info('no session, using %s', session)

        doc = self.get(status_report_url).text
        doc = lxml.html.fromstring(doc)
        doc.make_links_absolute(status_report_url)
        xpath = "//div[contains(text(),'{}')]/following-sibling::table"
        status_table = doc.xpath(xpath.format(session))[0]
        status_links = status_table.xpath(".//a[contains(text(),'Excel')]/@href")

        for url in status_links:

            try:
                fname, resp = self.urlretrieve(url)
            except scrapelib.HTTPError as report:
                self.logger.warning("Missing report {}".format(report))
                continue

            sh = xlrd.open_workbook(fname).sheet_by_index(0)

            # once workbook is open, we can remove tempfile
            os.remove(fname)
            for rownum in range(1, sh.nrows):
                bill_id = sh.cell(rownum, 0).value

                bill_type = "resolution" if "R" in bill_id else "bill"
                chamber = "lower" if "H" in bill_id else "upper"

                bill_title = str(sh.cell(rownum, 3).value)

                bill = Bill(
                            bill_id,
                            legislative_session=session,
                            chamber=chamber,
                            title=bill_title,
                            classification=bill_type
                       )
                bill.add_source(url)
                bill.add_sponsor('primary', str(sh.cell(rownum, 1).value))

                # add cosponsor
                if sh.cell(rownum, 2).value:
                    bill.add_sponsor('cosponsor',
                                     str(sh.cell(rownum, 2).value))

                actor = ""

                # Actions start column after bill title
                for colnum in range(4, sh.ncols - 1):
                    action = str(sh.cell(0, colnum).value)
                    cell = sh.cell(rownum, colnum)
                    date = cell.value

                    if len(action) != 0:
                        if action.split()[0] == 'House':
                            actor = "lower"
                        elif action.split()[0] == 'Senate':
                            actor = "upper"
                        elif action.split()[-1] == 'Governor':
                            actor = "executive"
                        elif action.split()[0] == 'Gov.':
                            actor = "executive"
                        elif action.split()[-1] == 'Gov.':
                            actor = "executive"

                    if action in ('House Intro. Date', 'Senate Intro. Date'):
                        atype = ['bill:introduced']
                        action = action.replace('Intro. Date', 'Introduced')
                    elif action == '3rd Consideration':
                        atype = ['bill:reading:3', 'bill:passed']
                    elif action == 'Sent to Gov.':
                        atype = ['governor:received']
                    elif action == 'Signed By Governor':
                        atype = ['governor:signed']
                    else:
                        atype = ['other']

                    if type(date) == float:
                        date = str(xlrd.xldate_as_tuple(date, 0))
                        date = datetime.datetime.strptime(
                            date, "(%Y, %m, %d, %H, %M, %S)")
                        date = self._tz.localize(date)
                        date = "{:%Y-%m-%d}".format(date)
                        bill.add_action(actor, action, date, type=atype)

                for idx, char in enumerate(bill_id):
                    try:
                        int(char)
                    except ValueError:
                        continue

                    underscore_bill = bill_id[:idx]+"_"+bill_id[idx:]
                    break

                yield from self.scrape_votes_old(bill, underscore_bill, session)
#.........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 add_sponsor [as 别名]

#.........这里部分代码省略.........

                #dc has no chambers. calling it all upper
                # bill = Bill(session,"upper", bill_id, title, type=bill_type)
                # bill = Bill(bill_id, legislative_session=session, chamber=chamber, title=title, classification=bill_type)
                bill = Bill(bill_id, legislative_session=session, title=title, classification=bill_type)

                #sponsors and cosponsors
                if "Introducer" in legislation_info:
                    introducers = legislation_info["Introducer"]
                    intro_date = self.date_format(legislation_info["IntroductionDate"])
                    # bill.add_action("upper",
                    #                "Introduced",
                    #               intro_date,
                    #                type="introduction")
                    bill.add_action("Introduced", intro_date, chamber="upper", classification="introduction")
                else:
                    #sometimes there are introducers, sometimes not.
                    # Set Introducers to empty array to avoid downstream breakage, but log bills without introducers
                    self.logger.warning("No Introducer: {0} {1}: {2}".format(bill['chamber'], bill['session'], bill['bill_id']))
                    introducers = []

                try:
                    #sometimes there are cosponsors, sometimes not.
                    cosponsors = legislation_info["CoSponsor"]
                except KeyError:
                    cosponsors = []

                for i in introducers:
                    name = i["Name"]
                    #they messed up Phil Mendelson's name
                    if name == "Phil Pmendelson":
                        name = "Phil Mendelson"
                    # bill.add_sponsor(name=sponsor_name,type="primary")
                    bill.add_sponsorship(name, classification=cosponsors, entity_type='person', primary=True)

                for s in cosponsors:
                    name = s["Name"]
                    if name == "Phil Pmendelson":
                        name = "Phil Mendelson"
                    bill.add_sponsor(name=name,type="cosponsor")


                #if it's become law, add the law number as an alternate title
                if "LawNumber" in legislation_info:
                    law_num = legislation_info["LawNumber"]
                    if law_num:
                        bill.add_title(law_num)

                #also sometimes it's got an act number
                if "ActNumber" in legislation_info:
                    act_num = legislation_info["ActNumber"]
                    if act_num:
                        bill.add_title(act_num)

                #sometimes AdditionalInformation has a previous bill name
                if "AdditionalInformation" in legislation_info:
                    add_info = legislation_info["AdditionalInformation"]
                    if "previously" in add_info.lower():
                        prev_title = add_info.lower().replace("previously","").strip().replace(" ","")
                        bill.add_title(prev_title.upper())
                    elif add_info:
                        bill["additional_information"] = add_info

                if "WithDrawnDate" in legislation_info:
                    withdrawn_date = self.date_format(legislation_info["WithDrawnDate"])
                    withdrawn_by = legislation_info["WithdrawnBy"][0]["Name"].strip()