用正则表达式提取文本中的日期

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)