有时在处理不规则数据时需要提取文本包含的时间日期。
dateutil.parser模块可以统一日期字符串格式。
datefinder模块可以在字符串中提取日期。
datefinder模块实现也是用正则，功能很全 但是对中文不友好。
但是这两个模块都不能支持中文及一些特殊的情况；所以我用正则写了段代码可进行中文日期及一些特殊的时间识别
例如：
'2012年12月12日','3小时前','在2012/12/13哈哈','时间2012-12-11 12:22:30','日期2012-13-11','测试2013.12.24','今天12:13'
import re
import chardet
from datetime import datetime,timedelta
# 匹配正则表达式
matchs = {
1:(r'\d{4}%s\d{1,2}%s\d{1,2}%s \d{1,2}%s\d{1,2}%s\d{1,2}%s','%%Y%s%%m%s%%d%s %%H%s%%M%s%%S%s'),
2:(r'\d{4}%s\d{1,2}%s\d{1,2}%s \d{1,2}%s\d{1,2}%s','%%Y%s%%m%s%%d%s %%H%s%%M%s'),
3:(r'\d{4}%s\d{1,2}%s\d{1,2}%s','%%Y%s%%m%s%%d%s'),
4:(r'\d{2}%s\d{1,2}%s\d{1,2}%s','%%y%s%%m%s%%d%s'),
# 没有年份
5:(r'\d{1,2}%s\d{1,2}%s \d{1,2}%s\d{1,2}%s\d{1,2}%s','%%m%s%%d%s %%H%s%%M%s%%S%s'),
6:(r'\d{1,2}%s\d{1,2}%s \d{1,2}%s\d{1,2}%s','%%m%s%%d%s %%H%s%%M%s'),
7:(r'\d{1,2}%s\d{1,2}%s','%%m%s%%d%s'),
# 没有年月日
8:(r'\d{1,2}%s\d{1,2}%s\d{1,2}%s','%%H%s%%M%s%%S%s'),
9:(r'\d{1,2}%s\d{1,2}%s','%%H%s%%M%s'),
}
# 正则中的%s分割
splits = [
{1:[('年','月','日','点','分','秒'),('-','-','',':',':',''),('\/','\/','',':',':',''),('\.','\.','',':',':','')]},
{2:[('年','月','日','点','分'),('-','-','',':',''),('\/','\/','',':',''),('\.','\.','',':','')]},
{3:[('年','月','日'),('-','-',''),('\/','\/',''),('\.','\.','')]},
{4:[('年','月','日'),('-','-',''),('\/','\/',''),('\.','\.','')]},
{5:[('月','日','点','分','秒'),('-','',':',':',''),('\/','',':',':',''),('\.','',':',':','')]},
{6:[('月','日','点','分'),('-','',':',''),('\/','',':',''),('\.','',':','')]},
{7:[('月','日'),('-',''),('\/',''),('\.','')]},
{8:[('点','分','秒'),(':',':','')]},
{9:[('点','分'),(':','')]},
]
def func(parten,tp):
re.search(parten,parten)
parten_other = '\d+天前|\d+分钟前|\d+小时前|\d+秒前'
class TimeFinder(object):
def __init__(self,base_date=None):
self.base_date = base_date
self.match_item = []
self.init_args()
self.init_match_item()
def init_args(self):
# 格式化基础时间
if not self.base_date:
self.base_date = datetime.now()
if self.base_date and not isinstance(self.base_date,datetime):
try:
self.base_date = datetime.strptime(self.base_date,'%Y-%m-%d %H:%M:%S')
except Exception as e:
raise 'type of base_date must be str of%Y-%m-%d %H:%M:%S or datetime'
def init_match_item(self):
# 构建穷举正则匹配公式 及提取的字符串转datetime格式映射
for item in splits:
for num,value in item.items():
match = matchs[num]
for sp in value:
tmp = []
for m in match:
tmp.append(m%sp)
self.match_item.append(tuple(tmp))
def get_time_other(self,text):
m = re.search('\d+',text)
if not m:
return None
num = int(m.group())
if '天' in text:
return self.base_date - timedelta(days=num)
elif '小时' in text:
return self.base_date - timedelta(hours=num)
elif '分钟' in text:
return self.base_date - timedelta(minutes=num)
elif '秒' in text:
return self.base_date - timedelta(seconds=num)
return None
def find_time(self,text):
# 格式化text为str类型
if isinstance(text,bytes):
encoding =chardet.detect(text)['encoding']
text = text.decode(encoding)
res = []
parten = '|'.join([x[0] for x in self.match_item])
parten = parten+ '|' +parten_other
match_list = re.findall(parten,text)
if not match_list:
return None
for match in match_list:
for item in self.match_item:
try:
date = datetime.strptime(match,item[1].replace('\\',''))
if date.year==1900:
date = date.replace(year=self.base_date.year)
if date.month==1:
date = date.replace(month=self.base_date.month)
if date.day==1:
date = date.replace(day=self.base_date.day)
res.append(datetime.strftime(date,'%Y-%m-%d %H:%M:%S'))
break
except Exception as e:
date = self.get_time_other(match)
if date:
res.append(datetime.strftime(date,'%Y-%m-%d %H:%M:%S'))
break
if not res:
return None
return res
def test():
timefinder =TimeFinder(base_date='2020-04-23 00:00:00')
for text in ['2012年12月12日','3小时前','在2012/12/13哈哈','时间2012-12-11 12:22:30','日期2012-13-11','测试2013.12.24','今天12:13']:
res = timefinder.find_time(text)
print('text----',text)
print('res---',res)
if __name__ == '__main__':
test()
测试运行结果如下
text---- 2012年12月12日
res--- ['2012-12-12 00:00:00']
text---- 3小时前
res--- ['2020-04-22 21:00:00']
text---- 在2012/12/13哈哈
res--- ['2012-12-13 00:00:00']
text---- 时间2012-12-11 12:22:30
res--- ['2012-12-11 12:22:30']
text---- 日期2012-13-11
res--- None
text---- 测试2013.12.24
res--- ['2013-12-24 00:00:00']
text---- 今天12:13
res--- ['2020-04-23 12:13:00']
到此这篇关于python自动提取文本中的时间(包含中文日期)的文章就介绍到这了,更多相关python自动提取时间内容请搜索龙方网络以前的文章或继续浏览下面的相关文章希望大家以后多多支持龙方网络！

在美国，2017 年圣诞节的表示是“12/25/17”，而在欧洲，同一个日子却表示为“25/12/17”。这里构造的日期和时间提取器尝试适配上面两种日/月的表示顺序，并检查以确保是有效的日期
import re
from datetime import date
import datetime

# 美国日期的正则表达式
us = r'((([01]?\d)[-/]([0123]?\d))([-/]([0123]\d)\d\d)?)'
mdy = re.findall(us, 'Santa came 12/25/2017. An elf appeared 12/12.')
print(mdy)

# 结构化提取的日期
# lstrip() 方法用于截掉字符串左边的空格或指定字符
dates = [{'mdy': x[0], 'md': x[1], 'm': int(x[2]), 'd': int(x[3]),
             'y': int(x[4].lstrip('/') or 0), 'c': int(x[5] or 0)} for x in mdy]
print(dates)

# 基本的上下文管理
# 使用在内存的结构化数据的上下文中最近读取到的年份来
# 填充任何缺失的数字字段
for i, d in enumerate(dates):
    for k, v in d.items():
        if not v:
            d[k] = dates[max(i - 1, 0)][k]

print(dates)
datetimes = [date(d['y'], d['m'], d['d']) for d in dates]
print(datetimes)


# 欧洲日期的正则表达式
eu = r'((([0123]?\d)[-/]([01]?\d))([-/]([0123]\d)?\d\d)?)'
dmy = re.findall(eu, 'Alan Mathison Turing OBE FRS (23/6/1912-7/6/1954) was an English computer scientist.')
print(dmy)
dmy = re.findall(eu, 'Alan Mathison Turing OBE FRS (23/6/12-7/6/54) was an English computer scientist.')
print(dmy)

# 综合提取
# 识别年份
# 两位数表示的年份，30-99 = 1930-1999
yr_19xx = (r'\b(?P<yr_19xx>' +
           '|'.join('{}'.format(i) for i in range(30, 100)) +
           r')\b')
# 一位或者两位数表示的年份，01-30 = 2001-2030
# 02d 格式一个整数（ d ）到最小宽度2（ 2 ）的字段，左侧填充零（前导 0 ）
yr_20xx = (r'\b(?P<yr_20xx>' +
           '|'.join('{:02d}'.format(i) for i in range(10)) + '|' +
           '|'.join('{}'.format(i) for i in range(10, 30)) +
           r')\b')
# 3 位数或者 4 位数表示的年份的前几位数字，如“123 A.D.”中的“1”
# 或者“2018”中的“20”
yr_cent = r'\b(?P<yr_cent>' + '|'.join('{}'.format(i) for i in range(1, 40)) + r')'
# 位数或者 4 位数表示的年份的后两位数字，如“123 A.D.”中的“23”
# 或者“2018”中的“18”
yr_ccxx = r'(?P<yr_ccxx>' + '|'.join('{:02d}'.format(i) for i in range(0, 100)) + r')\b'
yr_xxxx = r'\b(?P<yr_xxxx>(' + yr_cent + ')(' + yr_ccxx + r'))\b'
yr = (r'\b(?P<yr>' +
      yr_19xx + '|' + yr_20xx + '|' + yr_xxxx +
      r')\b')
# finditer()函数实现每次只返回一个，并且返回所在的位置
groups = list(re.finditer(yr, "0, 17, 2000, 01, '08, 99, 1984, 2030/1970 85 47 `66"))
full_years = [g['yr'] for g in groups]
print(full_years)

# 用正则表达式识别月份名称
mon_words = 'January February March April May June July August September October November December'
mon = (r'\b(?P<mon>' + '|'.join('{}|{}|{}|{}|{:02d}'.format(m, m[:4], m[:3], i + 1, i + 1) for i, m in enumerate(mon_words.split())) + r')\b')
print(re.findall(mon, 'January has 31 days, February the 2nd month of 12, has 28, except in a Leap Year.'))

# 组合信息提取正则表达式
day = r'(?P<day>' + '|'.join('{:02d}|{}'.format(i, i) for i in range(1, 32)) + r')\b'
eu = (r'\b(' + day.replace('<day', '<eu_day') + r')\b[-,/ ]{0,2}\b(' + mon.replace('<mon', '<eu_mon') + r')\b[-,/ ]{0,2}\b(' + yr.replace('<yr', '<eu_yr') + r')\b')
us = (r'\b(' + mon.replace('<mon', '<us_mon') + r')\b[-,/ ]{0,2}\b(' + day.replace('<day', '<us_day') + r')\b[-,/ ]{0,2}\b(' + yr.replace('<yr', '<us_yr') + r')\b')
date_pattern = r'\b(' + eu + '|' + us + r')\b'
print(list(re.finditer(date_pattern, '31 Oct, 1970 25/12/2017')))

# 验证日期
dates = []
es_groups = list(re.finditer(date_pattern, "0, 12/25/2017, 2000, 01, '08, 99, 1984, 31/10/1970, 85 47 `66"))
for g in es_groups:
    month_num = (g['us_mon'] or g['eu_mon']).strip()
    try:
        month_num = int(month_num)
    except ValueError:
        month_num = [w[:len(month_num)] for w in mon_words].index(month_num) + 1
    date = datetime.date(int(g['us_yr'] or g['eu_yr']), month_num, int(g['us_day'] or g['eu_day']))
    dates.append(date)
print("dates:", dates)

有时在处理不规则数据时需要提取文本包含的时间日期。
dateutil.parser模块可以统一日期字符串格式。
datefinder模块可以在字符串中提取日期。
datefinder模块实现也是用正则，功能很全 但是对中文不友好。
但是这两个模块都不能支持中文及一些特殊的情况；所以我用正则写了段代码可进行中文日期及一些特殊的时间识别
例如：
"2012年12月12日","3小时前","在2012/12/13哈哈","时间2012-12-11 12:22:30","日期2012-13-11","测试2013.12.24","今天12:13"
import re
import chardet
from datetime import datetime,timedelta
# 匹配正则表达式
matchs = {
1:(r"d{4}%sd{1,2}%sd{1,2}%s d{1,2}%sd{1,2}%sd{1,2}%s","%%Y%s%%m%s%%d%s %%H%s%%M%s%%S%s"),
2:(r"d{4}%sd{1,2}%sd{1,2}%s d{1,2}%sd{1,2}%s","%%Y%s%%m%s%%d%s %%H%s%%M%s"),
3:(r"d{4}%sd{1,2}%sd{1,2}%s","%%Y%s%%m%s%%d%s"),
4:(r"d{2}%sd{1,2}%sd{1,2}%s","%%y%s%%m%s%%d%s"),
# 没有年份
5:(r"d{1,2}%sd{1,2}%s d{1,2}%sd{1,2}%sd{1,2}%s","%%m%s%%d%s %%H%s%%M%s%%S%s"),
6:(r"d{1,2}%sd{1,2}%s d{1,2}%sd{1,2}%s","%%m%s%%d%s %%H%s%%M%s"),
7:(r"d{1,2}%sd{1,2}%s","%%m%s%%d%s"),
# 没有年月日
8:(r"d{1,2}%sd{1,2}%sd{1,2}%s","%%H%s%%M%s%%S%s"),
9:(r"d{1,2}%sd{1,2}%s","%%H%s%%M%s"),
}
# 正则中的%s分割
splits = [
{1:[("年","月","日","点","分","秒"),("-","-","",":",":",""),("/","/","",":",":",""),(".",".","",":",":","")]},
{2:[("年","月","日","点","分"),("-","-","",":",""),("/","/","",":",""),(".",".","",":","")]},
{3:[("年","月","日"),("-","-",""),("/","/",""),(".",".","")]},
{4:[("年","月","日"),("-","-",""),("/","/",""),(".",".","")]},
{5:[("月","日","点","分","秒"),("-","",":",":",""),("/","",":",":",""),(".","",":",":","")]},
{6:[("月","日","点","分"),("-","",":",""),("/","",":",""),(".","",":","")]},
{7:[("月","日"),("-",""),("/",""),(".","")]},
{8:[("点","分","秒"),(":",":","")]},
{9:[("点","分"),(":","")]},
]
def func(parten,tp):
re.search(parten,parten)
parten_other = "d+天前|d+分钟前|d+小时前|d+秒前"
class TimeFinder(object):
def __init__(self,base_date=None):
self.base_date = base_date
self.match_item = []
self.init_args()
self.init_match_item()
def init_args(self):
# 格式化基础时间
if not self.base_date:
self.base_date = datetime.now()
if self.base_date and not isinstance(self.base_date,datetime):
try:
self.base_date = datetime.strptime(self.base_date,"%Y-%m-%d %H:%M:%S")
except Exception as e:
raise "type of base_date must be str of%Y-%m-%d %H:%M:%S or datetime"
def init_match_item(self):
# 构建穷举正则匹配公式 及提取的字符串转datetime格式映射
for item in splits:
for num,value in item.items():
match = matchs[num]
for sp in value:
tmp = []
for m in match:
tmp.append(m%sp)
self.match_item.append(tuple(tmp))
def get_time_other(self,text):
m = re.search("d+",text)
if not m:
return None
num = int(m.group())
if "天" in text:
return self.base_date - timedelta(days=num)
elif "小时" in text:
return self.base_date - timedelta(hours=num)
elif "分钟" in text:
return self.base_date - timedelta(minutes=num)
elif "秒" in text:
return self.base_date - timedelta(seconds=num)
return None
def find_time(self,text):
# 格式化text为str类型
if isinstance(text,bytes):
encoding =chardet.detect(text)["encoding"]
text = text.decode(encoding)
res = []
parten = "|".join([x[0] for x in self.match_item])
parten = parten+ "|" +parten_other
match_list = re.findall(parten,text)
if not match_list:
return None
for match in match_list:
for item in self.match_item:
try:
date = datetime.strptime(match,item[1].replace("\",""))
if date.year==1900:
date = date.replace(year=self.base_date.year)
if date.month==1:
date = date.replace(month=self.base_date.month)
if date.day==1:
date = date.replace(day=self.base_date.day)
res.append(datetime.strftime(date,"%Y-%m-%d %H:%M:%S"))
break
except Exception as e:
date = self.get_time_other(match)
if date:
res.append(datetime.strftime(date,"%Y-%m-%d %H:%M:%S"))
break
if not res:
return None
return res
def test():
timefinder =TimeFinder(base_date="2020-04-23 00:00:00")
for text in ["2012年12月12日","3小时前","在2012/12/13哈哈","时间2012-12-11 12:22:30","日期2012-13-11","测试2013.12.24","今天12:13"]:
res = timefinder.find_time(text)
print("text----",text)
print("res---",res)
if __name__ == "__main__":
test()
测试运行结果如下
text---- 2012年12月12日
res--- ["2012-12-12 00:00:00"]
text---- 3小时前
res--- ["2020-04-22 21:00:00"]
text---- 在2012/12/13哈哈
res--- ["2012-12-13 00:00:00"]
text---- 时间2012-12-11 12:22:30
res--- ["2012-12-11 12:22:30"]
text---- 日期2012-13-11
res--- None
text---- 测试2013.12.24
res--- ["2013-12-24 00:00:00"]
text---- 今天12:13
res--- ["2020-04-23 12:13:00"]
到此这篇关于python自动提取文本中的时间(包含中文日期)的文章就介绍到这了,更多相关python自动提取时间内容请搜索云海天教程以前的文章或继续浏览下面的相关文章希望大家以后多多支持云海天教程！
原文链接：https://www.cnblogs.com/i-love-python/p/12763063.html

有时在处理不规则数据时需要提取文本包含的时间日期。
dateutil.parser模块可以统一日期字符串格式。
datefinder模块可以在字符串中提取日期。
datefinder模块实现也是用正则，功能很全 但是对中文不友好。
但是这两个模块都不能支持中文及一些特殊的情况；所以我用正则写了段代码可进行中文日期及一些特殊的时间识别
例如：
'2012年12月12日','3小时前','在2012/12/13哈哈','时间2012-12-11 12:22:30','日期2012-13-11','测试2013.12.24','今天12:13'
import re
import chardet
from datetime import datetime,timedelta
# 匹配正则表达式
matchs = {
1:(r'\d{4}%s\d{1,2}%s\d{1,2}%s \d{1,2}%s\d{1,2}%s\d{1,2}%s','%%Y%s%%m%s%%d%s %%H%s%%M%s%%S%s'),
2:(r'\d{4}%s\d{1,2}%s\d{1,2}%s \d{1,2}%s\d{1,2}%s','%%Y%s%%m%s%%d%s %%H%s%%M%s'),
3:(r'\d{4}%s\d{1,2}%s\d{1,2}%s','%%Y%s%%m%s%%d%s'),
4:(r'\d{2}%s\d{1,2}%s\d{1,2}%s','%%y%s%%m%s%%d%s'),
# 没有年份
5:(r'\d{1,2}%s\d{1,2}%s \d{1,2}%s\d{1,2}%s\d{1,2}%s','%%m%s%%d%s %%H%s%%M%s%%S%s'),
6:(r'\d{1,2}%s\d{1,2}%s \d{1,2}%s\d{1,2}%s','%%m%s%%d%s %%H%s%%M%s'),
7:(r'\d{1,2}%s\d{1,2}%s','%%m%s%%d%s'),
# 没有年月日
8:(r'\d{1,2}%s\d{1,2}%s\d{1,2}%s','%%H%s%%M%s%%S%s'),
9:(r'\d{1,2}%s\d{1,2}%s','%%H%s%%M%s'),
}
# 正则中的%s分割
splits = [
{1:[('年','月','日','点','分','秒'),('-','-','',':',':',''),('\/','\/','',':',':',''),('\.','\.','',':',':','')]},
{2:[('年','月','日','点','分'),('-','-','',':',''),('\/','\/','',':',''),('\.','\.','',':','')]},
{3:[('年','月','日'),('-','-',''),('\/','\/',''),('\.','\.','')]},
{4:[('年','月','日'),('-','-',''),('\/','\/',''),('\.','\.','')]},
{5:[('月','日','点','分','秒'),('-','',':',':',''),('\/','',':',':',''),('\.','',':',':','')]},
{6:[('月','日','点','分'),('-','',':',''),('\/','',':',''),('\.','',':','')]},
{7:[('月','日'),('-',''),('\/',''),('\.','')]},
{8:[('点','分','秒'),(':',':','')]},
{9:[('点','分'),(':','')]},
]
def func(parten,tp):
re.search(parten,parten)
parten_other = '\d+天前|\d+分钟前|\d+小时前|\d+秒前'
class TimeFinder(object):
def __init__(self,base_date=None):
self.base_date = base_date
self.match_item = []
self.init_args()
self.init_match_item()
def init_args(self):
# 格式化基础时间
if not self.base_date:
self.base_date = datetime.now()
if self.base_date and not isinstance(self.base_date,datetime):
try:
self.base_date = datetime.strptime(self.base_date,'%Y-%m-%d %H:%M:%S')
except Exception as e:
raise 'type of base_date must be str of%Y-%m-%d %H:%M:%S or datetime'
def init_match_item(self):
# 构建穷举正则匹配公式 及提取的字符串转datetime格式映射
for item in splits:
for num,value in item.items():
match = matchs[num]
for sp in value:
tmp = []
for m in match:
tmp.append(m%sp)
self.match_item.append(tuple(tmp))
def get_time_other(self,text):
m = re.search('\d+',text)
if not m:
return None
num = int(m.group())
if '天' in text:
return self.base_date - timedelta(days=num)
elif '小时' in text:
return self.base_date - timedelta(hours=num)
elif '分钟' in text:
return self.base_date - timedelta(minutes=num)
elif '秒' in text:
return self.base_date - timedelta(seconds=num)
return None
def find_time(self,text):
# 格式化text为str类型
if isinstance(text,bytes):
encoding =chardet.detect(text)['encoding']
text = text.decode(encoding)
res = []
parten = '|'.join([x[0] for x in self.match_item])
parten = parten+ '|' +parten_other
match_list = re.findall(parten,text)
if not match_list:
return None
for match in match_list:
for item in self.match_item:
try:
date = datetime.strptime(match,item[1].replace('\\',''))
if date.year==1900:
date = date.replace(year=self.base_date.year)
if date.month==1:
date = date.replace(month=self.base_date.month)
if date.day==1:
date = date.replace(day=self.base_date.day)
res.append(datetime.strftime(date,'%Y-%m-%d %H:%M:%S'))
break
except Exception as e:
date = self.get_time_other(match)
if date:
res.append(datetime.strftime(date,'%Y-%m-%d %H:%M:%S'))
break
if not res:
return None
return res
def test():
timefinder =TimeFinder(base_date='2020-04-23 00:00:00')
for text in ['2012年12月12日','3小时前','在2012/12/13哈哈','时间2012-12-11 12:22:30','日期2012-13-11','测试2013.12.24','今天12:13']:
res = timefinder.find_time(text)
print('text----',text)
print('res---',res)
if __name__ == '__main__':
test()
测试运行结果如下
text---- 2012年12月12日
res--- ['2012-12-12 00:00:00']
text---- 3小时前
res--- ['2020-04-22 21:00:00']
text---- 在2012/12/13哈哈
res--- ['2012-12-13 00:00:00']
text---- 时间2012-12-11 12:22:30
res--- ['2012-12-11 12:22:30']
text---- 日期2012-13-11
res--- None
text---- 测试2013.12.24
res--- ['2013-12-24 00:00:00']
text---- 今天12:13
res--- ['2020-04-23 12:13:00']
到此这篇关于python自动提取文本中的时间(包含中文日期)的文章就介绍到这了,更多相关python自动提取时间内容请搜索脚本之家以前的文章或继续浏览下面的相关文章希望大家以后多多支持脚本之家！