简介
用爬虫获取目标网站数据后可能会遇见时间为处理刚刚,分钟,小时,天前等时间格式,如图
解决问题:
写了一个工具类来处理该问题,其中封装了两个函数
1. 将时间中的中文数字转换成阿拉伯数字
def exchange_num(date):
'''
将输入字符串中的中文数字转换成阿拉伯数字
'''
zh_num = '零一二三四五六七八九'
for num in range(len(zh_num)):
date = date.replace(zh_num[num], str(num))
return date
2.将时间按照刚刚,分钟,小时,天前等时间格式进行判定跟转换对应时间
def deal_time(zh_time):
'''
对时间进行分类处理,对不同情况进行判断
'''
zh_time = exchange_num(zh_time.strip())
time_list = [
"小时前",
"分钟前",
"刚刚",
"天前"
]
now_time = datetime.strftime(datetime.today(), '%Y-%m-%d')
time_key_dict = {}
[time_key_dict.update({key: operator.contains(zh_time, key)}) for key in time_list]
if time_key_dict['刚刚'] or time_key_dict['分钟前']:
return now_time
elif time_key_dict['小时前']:
now_hour = datetime.strftime(datetime.today(), "%H")
pattern = re.search(r"(\d+)", zh_time)
if pattern.group(1) <= now_hour:
# 小于24小时转换成当日时间
return now_time
else:
return datetime.strftime(datetime.today() + timedelta(days=-1), '%Y-%m-%d') # 获取前1天日期
elif time_key_dict['天前']:
try:
pattern = re.search(r"(\d+)", zh_time)
zh_time = datetime.strftime(datetime.today() + timedelta(days=(int(pattern.group(1))) * -1),'%Y-%m-%d')
return zh_time
except Exception:
return f"转换失败 当前时间{now_time},网站中的时间{zh_time}"
else:
return zh_time
完整代码如下
import operator
from datetime import datetime, timedelta
import re
class DealTime:
'''
处理刚刚,分钟,小时,天前等时间
'''
def exchange_num(self, date):
'''
将输入字符串中的中文数字转换成阿拉伯数字
'''
zh_num = '零一二三四五六七八九'
for num in range(len(zh_num)):
date = date.replace(zh_num[num], str(num))
return date
def deal_time(self, zh_time):
'''
对时间进行分类处理,对不同情况进行判断
'''
zh_time = self.exchange_num(zh_time.strip())
time_list = [
"小时前",
"分钟前",
"刚刚",
"天前"
]
now_time = datetime.strftime(datetime.today(), '%Y-%m-%d')
time_key_dict = {}
[time_key_dict.update({key: operator.contains(zh_time, key)}) for key in time_list]
if time_key_dict['刚刚'] or time_key_dict['分钟前']:
return now_time
elif time_key_dict['小时前']:
now_hour = datetime.strftime(datetime.today(), "%H")
pattern = re.search(r"(\d+)", zh_time)
if pattern.group(1) <= now_hour:
# 小于24小时转换成当日时间
return now_time
else:
return datetime.strftime(datetime.today() + timedelta(days=-1), '%Y-%m-%d') # 获取前1天日期
elif time_key_dict['天前']:
try:
pattern = re.search(r"(\d+)", zh_time)
zh_time = datetime.strftime(datetime.today() + timedelta(days=(int(pattern.group(1))) * -1), '%Y-%m-%d')
return zh_time
except Exception:
return f"转换失败 当前时间{now_time},网站中的时间{zh_time}"
else:
return zh_time
if __name__ == '__main__':
print(DealTime().deal_time("刚刚"))
print(DealTime().deal_time("一天前"))
print(DealTime().deal_time("1天前"))
print(DealTime().deal_time("5分钟前"))
标签:zh,Python,分钟,num,天前,key,time,dict,datetime
From: https://www.cnblogs.com/Red-Sun/p/16851559.html