From c53edcec68b17c859b5fbef6ec5038abd6caf591 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?=E6=9C=A8=E6=9C=A8?= Date: Fri, 23 Apr 2021 15:26:52 +0800 Subject: [PATCH] update weiboSpider/spider.py. --- weiboSpider/spider.py | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/weiboSpider/spider.py b/weiboSpider/spider.py index 417084e..f226ea3 100644 --- a/weiboSpider/spider.py +++ b/weiboSpider/spider.py @@ -31,7 +31,7 @@ import json # 数据采集 class data_spider: def __init__(self): - self.database = database_util() + # self.database = database_util() self.headers = { "User-Agent":"Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.181 Safari/537.36" } @@ -134,8 +134,13 @@ class data_spider: if wb: if wb['id'] in self.weibo_id_list: continue + # created_at = datetime.strptime( + # wb['created_at'], '%Y-%m-%d') + ### 格式变了,现在是 Fri Mar 26 03:27:41 +0800 2021 created_at = datetime.strptime( - wb['created_at'], '%Y-%m-%d') + wb['created_at'], '%a %b %d %H:%M:%S %z %Y') + created_at = created_at.replace(tzinfo=None) + ### since_date = datetime.strptime( self.since_date, '%Y-%m-%d') if created_at < since_date: -- Gitee