From 49746b779ba7695c93d70f247de4583ffb53f509 Mon Sep 17 00:00:00 2001 From: ldy <1913292237@qq.com> Date: Tue, 8 Aug 2023 13:24:51 +0800 Subject: [PATCH] handled 2 typos in month while formatting date --- 01_EJDE_spider/ejde_main.py | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/01_EJDE_spider/ejde_main.py b/01_EJDE_spider/ejde_main.py index 905f9eb..4f8cf0e 100644 --- a/01_EJDE_spider/ejde_main.py +++ b/01_EJDE_spider/ejde_main.py @@ -18,8 +18,18 @@ from concurrent.futures import ThreadPoolExecutor, as_completed def datetime_transform(date): - input_date = datetime.strptime(date, "%B %d, %Y") - return input_date.strftime("%Y-%m-%d") + try: + input_date = datetime.strptime(date, "%B %d, %Y") + return input_date.strftime("%Y-%m-%d") + # handle two month-typos + except ValueError as vale: + if "Match 7, 2012" in date: + return "2012-03-07" + elif "Janaury 15, 2021" in date: + return "2021-01-15" + else: + print("Month typo:", str(vale)) + return date # Article and author detail