Part 0: Import package¶

In [1]:

import requests as r
import json
import pandas as pd
from datetime import datetime, date

Part 1: Download 1 month data in TAIEX (台股加權股價指數)¶

In [2]:

url = "https://www.twse.com.tw/exchangeReport/FMTQIK?response=json&date=20200701"

In [3]:

r.get(url)

Out[3]:

<Response [200]>

In [4]:

res = r.get(url)

In [5]:

res.json()

Out[5]:

{'data': [['109/07/01',
   '5,812,063,202',
   '193,056,259,836',
   '1,471,747',
   '11,703.42',
   '82.18'],
  ['109/07/02',
   '6,091,006,206',
   '191,309,888,383',
   '1,487,513',
   '11,805.14',
   '101.72'],
  ['109/07/03',
   '6,484,752,215',
   '218,879,744,425',
   '1,666,680',
   '11,909.16',
   '104.02'],
  ['109/07/06',
   '7,916,423,089',
   '252,079,466,765',
   '1,951,316',
   '12,116.70',
   '207.54'],
  ['109/07/07',
   '7,651,045,729',
   '277,506,544,486',
   '1,994,922',
   '12,092.97',
   '-23.73'],
  ['109/07/08',
   '6,363,746,201',
   '242,676,395,267',
   '1,755,000',
   '12,170.19',
   '77.22'],
  ['109/07/09',
   '6,645,387,543',
   '252,727,573,213',
   '1,866,152',
   '12,192.69',
   '22.50'],
  ['109/07/10',
   '7,031,694,732',
   '261,020,496,174',
   '1,983,065',
   '12,073.68',
   '-119.01'],
  ['109/07/13',
   '6,140,389,276',
   '211,132,055,829',
   '1,586,140',
   '12,211.56',
   '137.88'],
  ['109/07/14',
   '6,197,831,696',
   '205,369,887,777',
   '1,561,071',
   '12,209.01',
   '-2.55'],
  ['109/07/15',
   '6,756,734,156',
   '240,427,292,308',
   '1,778,651',
   '12,202.85',
   '-6.16'],
  ['109/07/16',
   '5,770,300,669',
   '199,619,270,942',
   '1,466,907',
   '12,157.74',
   '-45.11'],
  ['109/07/17',
   '5,938,809,215',
   '200,271,062,950',
   '1,595,717',
   '12,181.56',
   '23.82'],
  ['109/07/20',
   '5,326,683,162',
   '176,439,351,236',
   '1,378,130',
   '12,174.54',
   '-7.02'],
  ['109/07/21',
   '6,781,208,219',
   '225,623,414,631',
   '1,684,747',
   '12,397.55',
   '223.01'],
  ['109/07/22',
   '6,475,848,930',
   '226,256,572,816',
   '1,619,267',
   '12,473.27',
   '75.72'],
  ['109/07/23',
   '6,566,842,345',
   '228,150,200,225',
   '1,573,096',
   '12,413.04',
   '-60.23'],
  ['109/07/24',
   '7,302,839,893',
   '268,423,485,119',
   '1,868,849',
   '12,304.04',
   '-109.00'],
  ['109/07/27',
   '6,497,324,062',
   '256,612,208,060',
   '1,698,001',
   '12,588.30',
   '284.26'],
  ['109/07/28',
   '7,749,667,366',
   '348,922,817,780',
   '2,066,032',
   '12,586.73',
   '-1.57'],
  ['109/07/29',
   '5,900,556,154',
   '221,220,518,609',
   '1,504,202',
   '12,540.97',
   '-45.76'],
  ['109/07/30',
   '5,882,978,873',
   '215,707,482,486',
   '1,489,304',
   '12,722.92',
   '181.95'],
  ['109/07/31',
   '5,953,761,412',
   '210,436,131,573',
   '1,422,266',
   '12,664.80',
   '-58.12']],
 'date': '20200718',
 'fields': ['日期', '成交股數', '成交金額', '成交筆數', '發行量加權股價指數', '漲跌點數'],
 'notes': ['當日統計資訊含大盤、零股、盤後定價及鉅額交易，不含拍賣、標購。',
  '外幣成交值係以本公司當日下午3時30分公告匯率換算後加入成交金額。<br>公告匯率請參考本公司首頁>產品與服務>交易系統>雙幣ETF專區>代號對應及每日公告匯率。'],
 'stat': 'OK',
 'title': '109年07月市場成交資訊'}

In [6]:

stock_json = res.json()

In [7]:

stock_json['data']

Out[7]:

[['109/07/01',
  '5,812,063,202',
  '193,056,259,836',
  '1,471,747',
  '11,703.42',
  '82.18'],
 ['109/07/02',
  '6,091,006,206',
  '191,309,888,383',
  '1,487,513',
  '11,805.14',
  '101.72'],
 ['109/07/03',
  '6,484,752,215',
  '218,879,744,425',
  '1,666,680',
  '11,909.16',
  '104.02'],
 ['109/07/06',
  '7,916,423,089',
  '252,079,466,765',
  '1,951,316',
  '12,116.70',
  '207.54'],
 ['109/07/07',
  '7,651,045,729',
  '277,506,544,486',
  '1,994,922',
  '12,092.97',
  '-23.73'],
 ['109/07/08',
  '6,363,746,201',
  '242,676,395,267',
  '1,755,000',
  '12,170.19',
  '77.22'],
 ['109/07/09',
  '6,645,387,543',
  '252,727,573,213',
  '1,866,152',
  '12,192.69',
  '22.50'],
 ['109/07/10',
  '7,031,694,732',
  '261,020,496,174',
  '1,983,065',
  '12,073.68',
  '-119.01'],
 ['109/07/13',
  '6,140,389,276',
  '211,132,055,829',
  '1,586,140',
  '12,211.56',
  '137.88'],
 ['109/07/14',
  '6,197,831,696',
  '205,369,887,777',
  '1,561,071',
  '12,209.01',
  '-2.55'],
 ['109/07/15',
  '6,756,734,156',
  '240,427,292,308',
  '1,778,651',
  '12,202.85',
  '-6.16'],
 ['109/07/16',
  '5,770,300,669',
  '199,619,270,942',
  '1,466,907',
  '12,157.74',
  '-45.11'],
 ['109/07/17',
  '5,938,809,215',
  '200,271,062,950',
  '1,595,717',
  '12,181.56',
  '23.82'],
 ['109/07/20',
  '5,326,683,162',
  '176,439,351,236',
  '1,378,130',
  '12,174.54',
  '-7.02'],
 ['109/07/21',
  '6,781,208,219',
  '225,623,414,631',
  '1,684,747',
  '12,397.55',
  '223.01'],
 ['109/07/22',
  '6,475,848,930',
  '226,256,572,816',
  '1,619,267',
  '12,473.27',
  '75.72'],
 ['109/07/23',
  '6,566,842,345',
  '228,150,200,225',
  '1,573,096',
  '12,413.04',
  '-60.23'],
 ['109/07/24',
  '7,302,839,893',
  '268,423,485,119',
  '1,868,849',
  '12,304.04',
  '-109.00'],
 ['109/07/27',
  '6,497,324,062',
  '256,612,208,060',
  '1,698,001',
  '12,588.30',
  '284.26'],
 ['109/07/28',
  '7,749,667,366',
  '348,922,817,780',
  '2,066,032',
  '12,586.73',
  '-1.57'],
 ['109/07/29',
  '5,900,556,154',
  '221,220,518,609',
  '1,504,202',
  '12,540.97',
  '-45.76'],
 ['109/07/30',
  '5,882,978,873',
  '215,707,482,486',
  '1,489,304',
  '12,722.92',
  '181.95'],
 ['109/07/31',
  '5,953,761,412',
  '210,436,131,573',
  '1,422,266',
  '12,664.80',
  '-58.12']]

In [8]:

pd.DataFrame.from_dict(stock_json['data'])

Out[8]:

	0	1	2	3	4	5
0	109/07/01	5,812,063,202	193,056,259,836	1,471,747	11,703.42	82.18
1	109/07/02	6,091,006,206	191,309,888,383	1,487,513	11,805.14	101.72
2	109/07/03	6,484,752,215	218,879,744,425	1,666,680	11,909.16	104.02
3	109/07/06	7,916,423,089	252,079,466,765	1,951,316	12,116.70	207.54
4	109/07/07	7,651,045,729	277,506,544,486	1,994,922	12,092.97	-23.73
5	109/07/08	6,363,746,201	242,676,395,267	1,755,000	12,170.19	77.22
6	109/07/09	6,645,387,543	252,727,573,213	1,866,152	12,192.69	22.50
7	109/07/10	7,031,694,732	261,020,496,174	1,983,065	12,073.68	-119.01
8	109/07/13	6,140,389,276	211,132,055,829	1,586,140	12,211.56	137.88
9	109/07/14	6,197,831,696	205,369,887,777	1,561,071	12,209.01	-2.55
10	109/07/15	6,756,734,156	240,427,292,308	1,778,651	12,202.85	-6.16
11	109/07/16	5,770,300,669	199,619,270,942	1,466,907	12,157.74	-45.11
12	109/07/17	5,938,809,215	200,271,062,950	1,595,717	12,181.56	23.82
13	109/07/20	5,326,683,162	176,439,351,236	1,378,130	12,174.54	-7.02
14	109/07/21	6,781,208,219	225,623,414,631	1,684,747	12,397.55	223.01
15	109/07/22	6,475,848,930	226,256,572,816	1,619,267	12,473.27	75.72
16	109/07/23	6,566,842,345	228,150,200,225	1,573,096	12,413.04	-60.23
17	109/07/24	7,302,839,893	268,423,485,119	1,868,849	12,304.04	-109.00
18	109/07/27	6,497,324,062	256,612,208,060	1,698,001	12,588.30	284.26
19	109/07/28	7,749,667,366	348,922,817,780	2,066,032	12,586.73	-1.57
20	109/07/29	5,900,556,154	221,220,518,609	1,504,202	12,540.97	-45.76
21	109/07/30	5,882,978,873	215,707,482,486	1,489,304	12,722.92	181.95
22	109/07/31	5,953,761,412	210,436,131,573	1,422,266	12,664.80	-58.12

In [9]:

stock_df = pd.DataFrame.from_dict(stock_json['data'])
stock_df.head()

Out[9]:

	0	1	2	3	4	5
0	109/07/01	5,812,063,202	193,056,259,836	1,471,747	11,703.42	82.18
1	109/07/02	6,091,006,206	191,309,888,383	1,487,513	11,805.14	101.72
2	109/07/03	6,484,752,215	218,879,744,425	1,666,680	11,909.16	104.02
3	109/07/06	7,916,423,089	252,079,466,765	1,951,316	12,116.70	207.54
4	109/07/07	7,651,045,729	277,506,544,486	1,994,922	12,092.97	-23.73

In [10]:

stock_json['fields']

Out[10]:

['日期', '成交股數', '成交金額', '成交筆數', '發行量加權股價指數', '漲跌點數']

In [11]:

stock_df.columns = stock_json['fields']

In [12]:

stock_df.head()

Out[12]:

	日期	成交股數	成交金額	成交筆數	發行量加權股價指數	漲跌點數
0	109/07/01	5,812,063,202	193,056,259,836	1,471,747	11,703.42	82.18
1	109/07/02	6,091,006,206	191,309,888,383	1,487,513	11,805.14	101.72
2	109/07/03	6,484,752,215	218,879,744,425	1,666,680	11,909.16	104.02
3	109/07/06	7,916,423,089	252,079,466,765	1,951,316	12,116.70	207.54
4	109/07/07	7,651,045,729	277,506,544,486	1,994,922	12,092.97	-23.73

Part 2: Download multi months data in TAIEX (台股加權股價指數)¶

In [13]:

url = "https://www.twse.com.tw/exchangeReport/FMTQIK?response=json&date=20200701"

In [14]:

month_list = pd.date_range('2020-06-01','2020-08-01', freq='MS').strftime("%Y%m%d").tolist()    

In [15]:

for month in month_list:
    print(month) 

20200601
20200701
20200801

In [16]:

df = pd.DataFrame()
df

Out[16]:

In [17]:

for month in month_list:
    url = "https://www.twse.com.tw/exchangeReport/FMTQIK?response=json&date=" + month
    res = r.get(url)
    stock_json = res.json()
    stock_df = pd.DataFrame.from_dict(stock_json['data'])
    df = df.append(stock_df, ignore_index = True)

In [18]:

df.columns = ['日期', '成交股數', '成交金額', '成交筆數', '發行量加權股價指數', '漲跌點數']

In [19]:

df.head()

Out[19]:

	日期	成交股數	成交金額	成交筆數	發行量加權股價指數	漲跌點數
0	109/06/01	4,975,164,301	169,563,746,947	1,350,613	11,079.02	136.86
1	109/06/02	4,974,734,421	182,409,278,902	1,399,684	11,127.93	48.91
2	109/06/03	6,431,206,610	214,594,995,112	1,670,723	11,320.16	192.23
3	109/06/04	5,944,102,520	203,655,766,408	1,550,402	11,393.23	73.07
4	109/06/05	5,782,637,500	181,156,372,573	1,522,634	11,479.40	86.17

In [20]:

def get_stock_data(start_year, start_month, end_year, end_month):
    start_date = str(date(start_year, start_month, 1))
    end_date = str(date(end_year, end_month, 1))
    month_list = pd.date_range(start_date, end_date, freq='MS').strftime("%Y%m%d").tolist()
    
    df = pd.DataFrame()
    for month in month_list:
        url = "https://www.twse.com.tw/exchangeReport/FMTQIK?response=json&date=" + month
        res = r.get(url)
        stock_json = res.json()
        stock_df = pd.DataFrame.from_dict(stock_json['data'])
        df = df.append(stock_df, ignore_index = True)
    
    df.columns = ['日期', '成交股數', '成交金額', '成交筆數', '發行量加權股價指數', '漲跌點數']
    return df

Part 3: Save the dataframe as csv file¶

In [21]:

get_stock_data(start_year = 2019, start_month = 7, end_year = 2019, end_month = 9)

Out[21]:

	日期	成交股數	成交金額	成交筆數	發行量加權股價指數	漲跌點數
0	108/07/01	4,985,631,880	145,664,096,932	1,089,572	10,895.46	164.63
1	108/07/02	4,295,548,703	120,716,164,596	991,072	10,865.12	-30.34
2	108/07/03	4,246,162,907	112,714,237,324	938,659	10,743.77	-121.35
3	108/07/04	3,797,646,624	98,158,438,333	828,014	10,775.90	32.13
4	108/07/05	3,400,302,424	86,511,212,135	752,681	10,785.73	9.83
5	108/07/08	3,738,945,153	97,082,027,949	815,372	10,751.22	-34.51
6	108/07/09	3,474,464,386	94,204,036,152	836,475	10,702.78	-48.44
7	108/07/10	4,044,852,809	104,197,474,125	932,562	10,798.48	95.70
8	108/07/11	4,997,530,807	132,057,394,072	1,071,497	10,843.42	44.94
9	108/07/12	4,559,013,456	122,217,270,421	1,031,495	10,824.35	-19.07
10	108/07/15	4,625,135,650	120,541,529,871	1,005,175	10,876.43	52.08
11	108/07/16	4,451,418,488	119,695,164,249	1,037,335	10,886.05	9.62
12	108/07/17	4,588,257,766	116,341,167,900	1,048,002	10,828.48	-57.57
13	108/07/18	4,212,328,479	106,205,765,697	961,380	10,799.28	-29.20
14	108/07/19	4,502,161,924	123,566,684,603	982,410	10,873.19	73.91
15	108/07/22	4,435,604,953	118,654,132,818	977,980	10,944.53	71.34
16	108/07/23	4,564,947,566	127,879,150,427	1,077,697	10,947.26	2.73
17	108/07/24	4,789,346,753	133,129,096,409	1,132,545	10,935.76	-11.50
18	108/07/25	5,034,848,310	133,885,703,398	1,131,686	10,941.41	5.65
19	108/07/26	4,227,775,498	111,794,836,905	1,002,794	10,891.98	-49.43
20	108/07/29	3,873,144,739	105,524,746,606	945,531	10,885.73	-6.25
21	108/07/30	4,493,608,915	131,409,613,891	1,099,181	10,830.90	-54.83
22	108/07/31	4,476,398,294	131,643,019,317	1,046,160	10,823.81	-7.09
23	108/08/01	4,521,619,307	131,058,984,590	1,098,159	10,731.75	-92.06
24	108/08/02	5,675,601,956	159,939,135,883	1,300,394	10,549.04	-182.71
25	108/08/05	4,911,728,030	129,390,816,837	1,107,939	10,423.41	-125.63
26	108/08/06	6,008,242,875	146,038,029,501	1,232,634	10,394.75	-28.66
27	108/08/07	4,468,033,535	121,765,614,143	1,059,318	10,386.18	-8.57
28	108/08/08	4,470,132,577	124,081,823,011	998,888	10,494.49	108.31
29	108/08/12	4,517,408,511	126,685,737,957	1,065,930	10,472.36	-22.13
...	...	...	...	...	...	...
33	108/08/16	4,700,960,825	120,048,343,262	1,133,574	10,420.89	93.76
34	108/08/19	4,574,050,378	120,476,924,084	1,068,019	10,488.75	67.86
35	108/08/20	4,542,661,753	121,491,792,456	1,070,480	10,522.50	33.75
36	108/08/21	3,932,448,282	111,080,424,760	1,006,299	10,525.80	3.30
37	108/08/22	4,396,250,909	123,271,367,108	1,072,360	10,529.78	3.98
38	108/08/23	3,942,656,466	110,007,554,049	947,669	10,538.11	8.33
39	108/08/26	4,862,207,637	117,049,586,345	1,016,154	10,354.57	-183.54
40	108/08/27	4,120,194,542	123,691,150,076	894,549	10,387.23	32.66
41	108/08/28	3,597,431,879	102,092,710,347	878,572	10,434.29	47.06
42	108/08/29	3,866,814,680	104,248,701,178	937,813	10,462.43	28.14
43	108/08/30	5,323,560,006	148,217,313,012	1,199,598	10,618.05	155.62
44	108/09/02	4,333,278,342	105,848,766,031	981,744	10,634.85	16.80
45	108/09/03	4,043,809,186	105,576,630,318	949,727	10,558.21	-76.64
46	108/09/04	4,338,123,349	107,093,494,944	972,295	10,657.31	99.10
47	108/09/05	6,013,120,362	154,662,076,294	1,261,814	10,756.93	99.62
48	108/09/06	4,827,692,321	131,307,111,626	1,107,361	10,780.64	23.71
49	108/09/09	4,543,925,038	116,733,239,498	1,027,773	10,801.14	20.50
50	108/09/10	4,475,712,468	121,338,149,239	986,052	10,753.58	-47.56
51	108/09/11	4,310,865,154	119,937,917,952	974,736	10,790.35	36.77
52	108/09/12	4,330,422,356	120,872,609,647	962,901	10,827.55	37.20
53	108/09/16	4,390,073,832	119,576,475,670	1,005,025	10,898.13	70.58
54	108/09/17	4,238,580,734	117,546,611,937	1,001,017	10,874.50	-23.63
55	108/09/18	4,380,465,735	130,465,246,047	1,113,809	10,929.45	54.95
56	108/09/19	4,094,709,966	114,671,100,910	922,567	10,894.70	-34.75
57	108/09/20	4,712,806,256	147,979,569,707	1,015,743	10,929.69	34.99
58	108/09/23	3,976,565,745	106,841,123,621	978,964	10,919.02	-10.67
59	108/09/24	3,872,481,764	109,707,784,147	1,013,261	10,918.01	-1.01
60	108/09/25	3,880,868,893	106,259,302,170	954,407	10,873.69	-44.32
61	108/09/26	3,878,756,606	116,018,960,126	945,745	10,871.99	-1.70
62	108/09/27	4,211,145,537	124,771,598,230	1,031,089	10,829.68	-42.31

63 rows × 6 columns

In [22]:

stock = get_stock_data(start_year = 2019, start_month = 7, end_year = 2019, end_month = 9)
stock.head()

Out[22]:

	日期	成交股數	成交金額	成交筆數	發行量加權股價指數	漲跌點數
0	108/07/01	4,985,631,880	145,664,096,932	1,089,572	10,895.46	164.63
1	108/07/02	4,295,548,703	120,716,164,596	991,072	10,865.12	-30.34
2	108/07/03	4,246,162,907	112,714,237,324	938,659	10,743.77	-121.35
3	108/07/04	3,797,646,624	98,158,438,333	828,014	10,775.90	32.13
4	108/07/05	3,400,302,424	86,511,212,135	752,681	10,785.73	9.83

In [23]:

stock.to_csv("TAIEX.csv")

In [ ]:

Part 0: Import package¶

Part 1: Download 1 month data in TAIEX (台股 加權股價指數)¶

Part 2: Download multi months data in TAIEX (台股 加權股價指數)¶

Part 3: Save the dataframe as csv file¶

Part 1: Download 1 month data in TAIEX (台股加權股價指數)¶

Part 2: Download multi months data in TAIEX (台股加權股價指數)¶