Python CleanText.split方法代码示例

# 需要导入模块: from weboob.browser.filters.standard import CleanText [as 别名]
# 或者: from weboob.browser.filters.standard.CleanText import split [as 别名]
 def obj_size(self):
     rawsize = CleanText('./div[has-class("poid")]')(self)
     rawsize = rawsize.replace(',','.').strip()
     nsize = float(rawsize.split()[0])
     usize = rawsize.split()[-1].upper().replace('O','B')
     size = get_bytes_size(nsize,usize)
     return size

# 需要导入模块: from weboob.browser.filters.standard import CleanText [as 别名]
# 或者: from weboob.browser.filters.standard.CleanText import split [as 别名]
            def obj_label(self):
                raw_label = CleanText(TableCell('label'))(self)
                label = CleanText(TableCell('label')(self)[0].xpath('./br/following-sibling::text()'))(self)

                if (label and label.split()[0] != raw_label.split()[0]) or not label:
                    label = raw_label

                return CleanText(TableCell('label')(self)[0].xpath('./noscript'))(self) or label

# 需要导入模块: from weboob.browser.filters.standard import CleanText [as 别名]
# 或者: from weboob.browser.filters.standard.CleanText import split [as 别名]
        def obj_details(self):
            details = {}

            details["creationDate"] = Date(
                Regexp(
                    CleanText(
                        '//p[@class="offer-description-notes"]|//p[has-class("darkergrey")]'
                    ),
                    u'.*Mis en ligne : (\d{2}/\d{2}/\d{4}).*'
                ),
                dayfirst=True
            )(self)

            honoraires = CleanText(
                (
                    '//div[has-class("offer-price")]/span[has-class("lbl-agencyfees")]'
                ),
                default=None
            )(self)
            if honoraires:
                details["Honoraires"] = (
                    "{} (TTC, en sus)".format(
                        honoraires.split(":")[1].strip()
                    )
                )

            for li in XPath('//ul[@itemprop="description"]/li')(self):
                label = CleanText('./div[has-class("criteria-label")]')(li)
                value = CleanText('./div[has-class("criteria-value")]')(li)
                details[label] = value

            return details

# 需要导入模块: from weboob.browser.filters.standard import CleanText [as 别名]
# 或者: from weboob.browser.filters.standard.CleanText import split [as 别名]
 def get_author(self):
     try:
         author = CleanText('.')(self.get_element_author())
         if author.startswith('Par '):
             return author.split('Par ', 1)[1]
         else:
             return author
     except AttributeError:
         return ''

# 需要导入模块: from weboob.browser.filters.standard import CleanText [as 别名]
# 或者: from weboob.browser.filters.standard.CleanText import split [as 别名]
 def next_page(self):
     js_datas = CleanText('//div[@id="js-data"]/@data-rest-search-request')(self)
     total_page = self.page.browser.get_total_page(js_datas.split("?")[-1])
     m = re.match(".*page=(\d?)(?:&.*)?", self.page.url)
     if m:
         current_page = int(m.group(1))
         next_page = current_page + 1
         if next_page <= total_page:
             return self.page.url.replace("page=%d" % current_page, "page=%d" % next_page)

# 需要导入模块: from weboob.browser.filters.standard import CleanText [as 别名]
# 或者: from weboob.browser.filters.standard.CleanText import split [as 别名]
    def check_errors(self):
        # check if user can add new recipient
        errors_id = ('popinClientNonEligible', 'popinClientNonEligibleBis')

        for error_id in errors_id:
            if self.doc.xpath('//script[contains(text(), "showDivJQInfo(\'%s\')")]' % error_id):
                msg = CleanText('//div[@id="%s"]//p' % error_id)(self.doc)
                # get the first sentence of information message
                # beacause the message is too long and contains unnecessary recommendations
                raise AddRecipientBankError(message=msg.split('.')[0])

# 需要导入模块: from weboob.browser.filters.standard import CleanText [as 别名]
# 或者: from weboob.browser.filters.standard.CleanText import split [as 别名]
            def obj_code(self):
                # We try to get the code from <a> div. If we didn't find code in url,
                # we try to find it in the cell text

                tablecell = TableCell('label', colspan=True)(self)[0]
                # url find try
                url = tablecell.xpath('./following-sibling::td[position()=1]/div/a')[0].attrib['href']
                code_match = re.search(r'sico=([A-Z0-9]*)', url)

                if code_match:
                    if is_isin_valid(code_match.group(1)):
                        return code_match.group(1)

                # cell text find try
                text = CleanText(tablecell.xpath('./following-sibling::td[position()=1]/div')[0])(self)

                for code in text.split(' '):
                    if is_isin_valid(code):
                        return code
                return NotAvailable

# 需要导入模块: from weboob.browser.filters.standard import CleanText [as 别名]
# 或者: from weboob.browser.filters.standard.CleanText import split [as 别名]
 def obj_id(self):
     try:
         _id = CleanText('.//td/a/@id')(self)
         if not _id:
             ac_details_page = self.page.browser.open(Link('.//td/a')(self)).page
         else:
             if '-' in _id:
                 split = _id.split('-')
                 ac_details_page = self.page.browser.open('/outil/UWVI/AssuranceVie/accesDetail?ID_CONTRAT=%s&PRODUCTEUR=%s' % (split[0], split[1])).page
             else:
                 ac_details_page = self.page.browser.open('/outil/UWVI/AssuranceVie/accesDetail?ID_CONTRAT=%s' % (_id)).page
         return CleanText('(//tr[3])/td[2]')(ac_details_page.doc)
     except ServerError:
         self.logger.debug("link didn't work, trying with the form instead")
         # the above server error can cause the form to fail, so we may have to go back on the accounts list before submitting
         self.page.browser.open(self.page.url)
         # redirection to lifeinsurances accounts and comeback on Lcl original website
         page = self.obj__form().submit().page
         account_id = page.get_account_id()
         page.come_back()
         return account_id

# 需要导入模块: from weboob.browser.filters.standard import CleanText [as 别名]
# 或者: from weboob.browser.filters.standard.CleanText import split [as 别名]
 def obj_date(self):
     time = CleanText(u'//span[@id="refresh_time"]')(self)
     time = [int(t) for t in time.split(":")]
     now = datetime.datetime.now()
     now.replace(hour=time[0], minute=time[1])
     return now

# 需要导入模块: from weboob.browser.filters.standard import CleanText [as 别名]
# 或者: from weboob.browser.filters.standard.CleanText import split [as 别名]
    def get_history(self, account):
        # checking if the card is still valid
        if self.doc.xpath('//div[@id="errorbox"]'):
            return

        # adding a time delta because amex have hard time to put the date in a good interval
        beginning_date = self.get_beginning_debit_date() - datetime.timedelta(days=360)
        end_date = self.get_end_debit_date()

        guesser = ChaoticDateGuesser(beginning_date, end_date)

        # Since the site doesn't provide the debit_date,
        # we just use the date of beginning of the previous period.
        # If this date + 1 month is greater than today's date,
        # then the transaction is coming
        end_of_period = None
        previous_date = CleanText('//td[@id="colStatementBalance"]/div[3]', default=None)(self.doc)
        if previous_date:
            end_of_period = (parse_french_date(' '.join(previous_date.split()[1:4])) + relativedelta(months=1)).date()
        else:
            previous_date = CleanText('//select[@id="viewPeriod"]/option[@selected]', default=None)(self.doc)
            if previous_date:
                end_of_period = parse_french_date(' '.join(previous_date.split()[:3])) + relativedelta(days=-1) + relativedelta(months=1)
                end_of_period = end_of_period.date()

        _id = str(int(account._idforold))
        for tr in reversed(self.doc.xpath('//div[@id="txnsSection"]//tbody[@id="tableBody-txnsCard%s"]/tr[@class="tableStandardText"]' % _id)):
            cols = tr.findall('td')

            t = Transaction()

            day, month = CleanText().filter(cols[self.COL_DATE]).split(' ', 1)
            day = int(day)
            month = self.parse_month(month)
            date = guesser.guess_date(day, month)

            vdate = None
            try:
                detail = cols[self.COL_TEXT].xpath('./div[has-class("hiddenROC")]')[0]
            except IndexError:
                pass
            else:
                m = re.search(r' (\d{2} \D{3,4})', (' '.join([txt.strip() for txt in detail.itertext()])).strip())
                if m:
                    vday, vmonth = m.group(1).strip().split(' ')
                    vday = int(vday)
                    vmonth = self.parse_month(vmonth)
                    vdate = guesser.guess_date(vday, vmonth)
                detail.drop_tree()

            raw = (' '.join([txt.strip() for txt in cols[self.COL_TEXT].itertext()])).strip()
            credit = CleanText().filter(cols[self.COL_CREDIT])
            debit = CleanText().filter(cols[self.COL_DEBIT])
            if end_of_period is not None and datetime.date.today() < end_of_period:
                t._is_coming = True
            else:
                t._is_coming = False

            t.date = t.rdate = date
            t.vdate = vdate
            t.raw = re.sub(r'[ ]+', ' ', raw)
            t.label = re.sub('(.*?)( \d+)?  .*', r'\1', raw).strip()
            t.amount = parse_decimal(credit or debit) * (1 if credit else -1)
            if t.raw in self.browser.SUMMARY_CARD_LABEL:
                t.type = t.TYPE_CARD_SUMMARY
            elif t.amount > 0:
                t.type = t.TYPE_ORDER
            else:
                t.date = end_of_period
                t.type = t.TYPE_DEFERRED_CARD

            yield t

# 需要导入模块: from weboob.browser.filters.standard import CleanText [as 别名]
# 或者: from weboob.browser.filters.standard.CleanText import split [as 别名]
 def obj__invest_account_id(self):
     invest_account_id = CleanText(Dict(
         'holdingSummaryInformation/0/accountNumber'
     ))(self)
     return invest_account_id.split(' ')[0]

# 需要导入模块: from weboob.browser.filters.standard import CleanText [as 别名]
# 或者: from weboob.browser.filters.standard.CleanText import split [as 别名]
 def obj_publication_date(self):
     content = CleanText('./div[2]')(self)
     split_date = content.split('|')[0].split('/')
     if len(split_date) == 3:
         return date(int(split_date[2]) + 2000, int(split_date[1]), int(split_date[0]))
     return ''

# 需要导入模块: from weboob.browser.filters.standard import CleanText [as 别名]
# 或者: from weboob.browser.filters.standard.CleanText import split [as 别名]
 def obj_id(self):
     acc_id = CleanText(Dict('accountNumber'))(self)
     return acc_id.split(' ')[0]

# 需要导入模块: from weboob.browser.filters.standard import CleanText [as 别名]
# 或者: from weboob.browser.filters.standard.CleanText import split [as 别名]
 def obj_size(self):
     rawsize = CleanText('//div[@class="accordion"]//tr[th="Taille totale"]/td')(self)
     nsize = float(rawsize.split()[0])
     usize = rawsize.split()[-1].upper()
     size = get_bytes_size(nsize, usize)
     return size

# 需要导入模块: from weboob.browser.filters.standard import CleanText [as 别名]
# 或者: from weboob.browser.filters.standard.CleanText import split [as 别名]
 def obj_place(self):
     content = CleanText('./div[2]')(self)
     if len(content.split('|')) > 1:
         return content.split('|')[1]
     return ''