元号年を見つけるためだけの正規表現
大化の改新以降の日本元号にヒットすると思う
import re
re_gengo = re.compile("(令和|平[成治]|昭和|大[正永治同宝化]|明[治和暦応徳]|慶[応安長雲]|元[治文禄和亀中弘徳亨応仁久暦永慶]|文[久政化禄亀明正安和中保永応暦治]|万[延治寿]|安[政永貞元和]|嘉[永吉慶暦元禎禄応承保祥]|弘[化治和安長仁]|天[保明和正文授福養承治永仁喜元延禄徳暦慶安長応(?:平神護)(?:平宝字)(?:平勝宝)(?:平感宝)平]|享[和保禄徳]|寛[政延保文永正元喜治徳仁弘和平]|宝[暦永徳治亀]|延[享宝徳文元慶応久長喜暦]|正[徳保長平慶中和安応元嘉治暦]|貞[享治和永応元観]|承[応久元安徳暦保平和]|永[禄正享徳和仁万暦治久長保承祚延観]|長[享禄寛承治久暦元和保徳]|応[仁永安長保徳和]|康[正応暦安永元治和平保]|至徳|観応|暦[応仁]|建[徳武治長保暦永仁久]|興国|徳治|乾元|仁[治安平和寿]|寿永|養[和老]|治[承暦安]|保[元延安]|久[寿安]|昌泰|斉衡|神[(?:護景雲)亀]|霊亀|和銅|朱鳥|白雉)\s*([\d元〇一二三四五六七八九十壱弐参０-９]+\s*年)?")
wikipedia より各元号の開始年月日をPython dictにしたもの
諸説あり開始年月日が仮説の場合もあった。。
g2d = {
'令和': datetime(2019, 5, 1),
'平成': datetime(1989, 1, 8),
'昭和': datetime(1926, 12, 25),
'大正': datetime(1912, 7, 30),
'明治': datetime(1868, 10, 23),
'慶応': datetime(1865, 5, 1), '元治': datetime(1864, 3, 27), '文久': datetime(1861, 3, 29), '万延': datetime(1860, 4, 8), '安政': datetime(1855, 1, 15), '嘉永': datetime(1848, 4, 1), '弘化': datetime(1845, 1, 9), '天保': datetime(1831, 1, 23), '文政': datetime(1818, 5, 26), '文化': datetime(1804, 3, 22), '享和': datetime(1801, 3, 19), '寛政': datetime(1789, 2, 19), '天明': datetime(1781, 4, 25), '安永': datetime(1772, 12, 10), '明和': datetime(1764, 6, 30), '宝暦': datetime(1751, 12, 14), '寛延': datetime(1748, 8, 5), '延享': datetime(1744, 4, 3), '寛保': datetime(1741, 4, 12), '元文': datetime(1736, 6, 7), '享保': datetime(1716, 8, 9), '正徳': datetime(1711, 6, 11), '宝永': datetime(1704, 4, 16), '元禄': datetime(1688, 10, 23), '貞享': datetime(1684, 4, 5), '天和': datetime(1681, 11, 9), '延宝': datetime(1673, 10, 30), '寛文': datetime(1661, 5, 23), '万治': datetime(1658, 8, 21), '明暦': datetime(1655, 5, 18), '承応': datetime(1652, 10, 20), '慶安': datetime(1648, 4, 7), '正保': datetime(1645, 1, 13), '寛永': datetime(1624, 4, 17), '元和': datetime(1615, 9, 5), '慶長': datetime(1596, 12, 16), '文禄': datetime(1593, 1, 10), '天正': datetime(1573, 8, 25), '元亀': datetime(1570, 5, 27), '永禄': datetime(1558, 3, 18), '弘治': datetime(1555, 11, 7), '天文': datetime(1532, 8, 29), '享禄': datetime(1528, 9, 3), '大永': datetime(1521, 9, 23), '永正': datetime(1504, 3, 16), '文亀': datetime(1501, 3, 18), '明応': datetime(1492, 8, 12), '延徳': datetime(1489, 9, 16), '長享': datetime(1487, 8, 9), '文明': datetime(1469, 6, 8), '応仁': datetime(1467, 4, 9), '文正': datetime(1466, 3, 14),
'寛正': datetime(1461, 2, 1), '長禄': datetime(1457, 10, 16), '康正': datetime(1455, 9, 6), '享徳': datetime(1452, 8, 10), '宝徳': datetime(1449, 8, 16), '文安': datetime(1444, 2, 23), '嘉吉': datetime(1441, 3, 10), '永享': datetime(1429, 10, 3), '正長': datetime(1428, 6, 10), '応永': datetime(1394, 8, 2), '明徳': datetime(1390, 4, 12), '康応': datetime(1389, 3, 7), '嘉慶': datetime(1387, 10, 5), '至徳': datetime(1384, 3, 19), '永徳': datetime(1381, 3, 20), '康暦': datetime(1379, 4, 9), '永和': datetime(1375, 3, 29), '応安': datetime(1368, 3, 7), '貞治': datetime(1362, 10, 11), '康安': datetime(1361, 5, 4), '延文': datetime(1356, 4, 29), '文和': datetime(1352, 11, 4), '観応': datetime(1350, 4, 4), '貞和': datetime(1345, 11, 15), '康永': datetime(1342, 6, 1), '暦応': datetime(1338, 10, 11), '元中': datetime(1384, 5, 18), '弘和': datetime(1381, 3, 6), '天授': datetime(1375, 6, 26), '文中': datetime(1372, 5, 1), '建徳': datetime(1370, 8, 16), '正平': datetime(1347, 1, 20), '興国': datetime(1340, 5, 25), '延元': datetime(1336, 4, 11), '建武': datetime(1334, 3, 5), '正慶': datetime(1332, 5, 23), '元弘': datetime(1331, 9, 11), '元徳': datetime(1329, 9, 22), '嘉暦': datetime(1326, 5, 28), '正中': datetime(1324, 12, 25), '元亨': datetime(1321, 3, 22), '元応': datetime(1319, 5, 18), '文保': datetime(1317, 3, 16), '正和': datetime(1312, 4, 27), '応長': datetime(1311, 5, 17), '延慶': datetime(1308, 11, 22), '徳治': datetime(1307, 1, 18), '嘉元': datetime(1303, 9, 16), '乾元': datetime(1302, 12, 10), '正安': datetime(1299, 5, 25), '永仁': datetime(1293, 9, 6), '正応': datetime(1288, 5, 29), '弘安': datetime(1278, 3, 23), '建治': datetime(1275, 5, 22), '文永': datetime(1264, 3, 27), '弘長': datetime(1261, 3, 22), '文応': datetime(1260, 5, 24), '正元': datetime(1259, 4, 20), '正嘉': datetime(1257, 3, 31), '康元': datetime(1256, 10, 24), '建長': datetime(1249, 5, 2), '宝治': datetime(1247, 4, 5), '寛元': datetime(1243, 3, 18), '仁治': datetime(1240, 8, 5), '延応': datetime(1239, 3, 13), '暦仁': datetime(1238, 12, 30), '嘉禎': datetime(1235, 11, 1), '文暦': datetime(1234, 11, 27), '天福': datetime(1233, 5, 25), '貞永': datetime(1232, 4, 23), '寛喜': datetime(1229, 3, 31), '安貞': datetime(1228, 1, 18), '嘉禄': datetime(1225, 5, 28), '元仁': datetime(1224, 12, 31), '貞応': datetime(1222, 5, 25), '承久': datetime(1219, 5, 27), '建保': datetime(1214, 1, 18), '建暦': datetime(1211, 4, 23), '承元': datetime(1207, 11, 16), '建永': datetime(1206, 6, 5), '元久': datetime(1204, 3, 23), '建仁': datetime(1201, 3, 19), '正治': datetime(1199, 5, 23), '建久': datetime(1190, 5, 16), '文治': datetime(1185, 9, 9), '元暦': datetime(1184, 5, 27), '寿永': datetime(1182, 6, 29), '養和': datetime(1181, 8, 25), '治承': datetime(1177, 8, 29), '安元': datetime(1175, 8, 16), '承安': datetime(1171, 5, 27), '嘉応': datetime(1169, 5, 6), '仁安': datetime(1166, 9, 23), '永万': datetime(1165, 7, 14), '長寛': datetime(1163, 5, 4), '応保': datetime(1161, 9, 24), '永暦': datetime(1160, 2, 18),
'平治': datetime(1159, 5, 9), '保元': datetime(1156, 5, 18), '久寿': datetime(1154, 12, 4), '仁平': datetime(1151, 2, 14), '久安': datetime(1145, 8, 12), '天養': datetime(1144, 3, 28), '康治': datetime(1142, 5, 25), '永治': datetime(1141, 8, 13), '保延': datetime(1135, 6, 10), '長承': datetime(1132, 9, 21), '天承': datetime(1131, 2, 28), '大治': datetime(1126, 2, 15), '天治': datetime(1124, 5, 18), '保安': datetime(1120, 5, 9), '元永': datetime(1118, 4, 25), '永久': datetime(1113, 8, 25), '天永': datetime(1110, 7, 31), '天仁': datetime(1108, 9, 9), '嘉承': datetime(1106, 5, 13), '長治': datetime(1104, 3, 8), '康和': datetime(1099, 9, 15), '承徳': datetime(1097, 12, 27), '永長': datetime(1097, 1, 3), '嘉保': datetime(1095, 1, 23), '寛治': datetime(1087, 5, 11), '応徳': datetime(1084, 3, 15), '永保': datetime(1081, 3, 22), '承暦': datetime(1077, 12, 5), '承保': datetime(1074, 9, 16), '延久': datetime(1069, 5, 6), '治暦': datetime(1065, 9, 4), '康平': datetime(1058, 9, 19), '天喜': datetime(1053, 2, 2), '永承': datetime(1046, 5, 22), '寛徳': datetime(1044, 12, 16), '長久': datetime(1040, 12, 16), '長暦': datetime(1037, 5, 9), '長元': datetime(1028, 8, 18), '万寿': datetime(1024, 8, 19), '治安': datetime(1021, 3, 17), '寛仁': datetime(1017, 5, 21), '長和': datetime(1013, 2, 8), '寛弘': datetime(1004, 8, 8), '長保': datetime(999, 2, 1), '長徳': datetime(995, 3, 25), '正暦': datetime(990, 11, 26), '永祚': datetime(989, 9, 10), '永延': datetime(987, 5, 5), '寛和': datetime(985, 5, 19), '永観': datetime(983, 5, 29), '天元': datetime(978, 12, 31), '貞元': datetime(976, 8, 11), '天延': datetime(974, 1, 16), '天禄': datetime(970, 5, 3), '安和': datetime(968, 9, 8), '康保': datetime(964, 8, 19), '応和': datetime(961, 3, 5), '天徳': datetime(957, 11, 21), '天暦': datetime(947, 5, 15), '天慶': datetime(938, 6, 22), '承平': datetime(931, 5, 16), '延長': datetime(923, 5, 29), '延喜': datetime(901, 8, 31), '昌泰': datetime(898, 5, 20), '寛平': datetime(889, 5, 30), '仁和': datetime(885, 3, 11), '元慶': datetime(877, 6, 1), '貞観': datetime(859, 5, 20), '天安': datetime(857, 3, 20), '斉衡': datetime(854, 12, 23), '仁寿': datetime(851, 6, 1), '嘉祥': datetime(848, 7, 16), '承和': datetime(834, 2, 14), '天長': datetime(824, 2, 8), '弘仁': datetime(810, 10, 20), '大同': datetime(806, 6, 8), '延暦': datetime(782, 9, 30), '天応': datetime(781, 1, 30), '宝亀': datetime(770, 10, 23), '神護景雲': datetime(767, 9, 13), '天平神護': datetime(765, 2, 1), '天平宝字': datetime(757, 9, 6), '天平勝宝': datetime(749, 8, 19), '天平感宝': datetime(749, 5, 4), '天平': datetime(729, 9, 2), '神亀': datetime(724, 3, 3), '養老': datetime(717, 12, 24), '霊亀': datetime(715, 10, 3), '和銅': datetime(708, 2, 7), '慶雲': datetime(704, 6, 16), '大宝': datetime(701, 5, 3), '朱鳥': datetime(686, 8, 14), '白雉': datetime(650, 3, 22),
'大化': datetime(645, 7, 17)
}