From e1411313422e807b51e418ff22a4839b7903ad14 Mon Sep 17 00:00:00 2001 From: gwen Date: Wed, 20 Sep 2023 18:47:32 +0200 Subject: [PATCH] preparation for real datetime objects --- actes-princiers/src/actesdataset.py | 11 ++++++++++- 1 file changed, 10 insertions(+), 1 deletion(-) diff --git a/actes-princiers/src/actesdataset.py b/actes-princiers/src/actesdataset.py index 2040f3d..472cfe6 100644 --- a/actes-princiers/src/actesdataset.py +++ b/actes-princiers/src/actesdataset.py @@ -107,7 +107,7 @@ class BsXMLDataSet(XMLDataSet): def extract_prince_code_from_filestem(self, filestem): """ builds prince code - + :param: filestem sample: "anj_isa_i_1441_08_05a" :return: prince code, sample: "isa_i" @@ -123,6 +123,15 @@ class BsXMLDataSet(XMLDataSet): # 1.1/ Get all data from XML (9). counter is the id (= numb_acte) numb = self.soup.TEI["xml:id"] # /TEI[@xml:id] is always the acte's ID date_time = self.soup.msItem.docDate["when"] # YYYY-MM-DD or YYYY-MM date + #from datetime import datetime + #if not len(date_time.split('-')) == 2: + # # time format '%Y-%m-%d' + # isotime = datetime.strptime(date_time,'%Y-%m-%d') + # date_time = isotime.isoformat() + #else: + # # time format '%Y-%m' + # isotime = datetime.strptime(date_time,'%Y-%m') + # date_time = isotime.isoformat() date = self.soup.msItem.docDate.text # verbose date analyse = self.soup.abstract.p.text # acte's short analysis ref = self.soup.msIdentifier.find_all("idno", {"n": "2"})