-
Notifications
You must be signed in to change notification settings - Fork 15
/
Copy pathStocks_Crawl.py
444 lines (293 loc) · 19.6 KB
/
Stocks_Crawl.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
import MySQL_Database as MD
import requests
from io import StringIO
import pandas as pd
import time
class Stocks_Crawl(MD.MySQL_Database):
def __init__(self, timesleep=5, Crawl_flag = True, MySQL_flag = True,
Fetch_stock_statistics_flag = True, **kwargs):
super().__init__(**kwargs)
self.Crawl_flag = Crawl_flag
self.MySQL_flag = MySQL_flag
self.Fetch_stock_statistics_flag = Fetch_stock_statistics_flag
################# 上櫃公司價格資料
self.url_tpex_stock = "http://www.tpex.org.tw/web/stock/aftertrading/daily_close_quotes/stk_quote_download.php?l=zh-tw&d="
# self.tpex_df_stocks = pd.DataFrame( data = [],
# columns = ['Date', '證券代號', '證券名稱',
# '成交股數', '成交筆數',
# '成交金額', '開盤價',
# '最高價', '最低價',
# '收盤價', '漲跌(+/-)',
# '漲跌價差' ])
################# 上櫃公司法人買賣資料
self.url_tpex_df_institutional_investors = "https://www.tpex.org.tw/web/stock/3insti/daily_trade/3itrade_hedge_result.php?l=zh-tw&o=csv&se=EW&t=D&d="
# self.tpex_df_institutional_investors = pd.DataFrame( data = [],
# columns = ['證券代號', '證券名稱',
# '外陸資買進股數(不含外資自營商)',
# '外陸資賣出股數(不含外資自營商)',
# '外陸資買賣超股數(不含外資自營商)', '外資自營商買進股數',
# '外資自營商賣出股數', '外資自營商買賣超股數',
# '投信買進股數','投信賣出股數',
# '投信買賣超股數', '自營商買賣超股數',
# '自營商買進股數(自行買賣)', '自營商賣出股數(自行買賣)',
# '自營商買賣超股數(自行買賣)', '自營商買進股數(避險)',
# '自營商賣出股數(避險)', '自營商買賣超股數(避險)',
# '三大法人買賣超股數' ])
################# 上市公司價格資料
self.url_stock = 'https://www.twse.com.tw/exchangeReport/MI_INDEX?response=csv&date='
self.df_stocks = pd.DataFrame(data = [],
columns = ['Date', '證券代號', '證券名稱',
'成交股數', '成交筆數',
'成交金額', '開盤價',
'最高價', '最低價',
'收盤價', '漲跌(+/-)',
'漲跌價差' ])
################# 上市公司法人買賣資料
self.url_institutional_investors = 'http://www.tse.com.tw/fund/T86?response=csv&date='
self.df_institutional_investors = pd.DataFrame( data = [],
columns = ['證券代號', '證券名稱',
'外陸資買進股數(不含外資自營商)',
'外陸資賣出股數(不含外資自營商)',
'外陸資買賣超股數(不含外資自營商)', '外資自營商買進股數',
'外資自營商賣出股數', '外資自營商買賣超股數',
'投信買進股數','投信賣出股數',
'投信買賣超股數', '自營商買賣超股數',
'自營商買進股數(自行買賣)', '自營商賣出股數(自行買賣)',
'自營商買賣超股數(自行買賣)', '自營商買進股數(避險)',
'自營商賣出股數(避險)', '自營商買賣超股數(避險)',
'三大法人買賣超股數'])
################# 上市櫃公司股票本益比, 股價淨值比, 殖利率, 股利年度
self.df_statistics = pd.DataFrame( data = [],
columns = ["證券代號", "證券名稱", "本益比", "股價淨值比", "殖利率", "股利年度"])
self.timesleep = timesleep
if self.Crawl_flag:
self.Crawl()
elif self.Fetch_stock_statistics_flag:
self.Fetch_stock_statistics()
else:
print("The program is useless...END")
# 爬蟲完要不要存進MySQL資料庫
if self.MySQL_flag:
# 存進去Database
self.SaveIntoDatabase()
# 爬蟲完，也如果有將資料存進MySQL，將資料庫關起來
self.Close()
# Change the date
#############################################
def date_changer(self, date):
year = date[:4]
year = str(int(year)-1911)
month = date[4:6]
day = date[6:]
return year+"/"+month+"/"+day
# CRAWLING
#############################################
def Crawl(self):
# Start crawling data
for date in self.dates:
print(date + " starts crawling")
try:
################ 爬上櫃公司 ################
if self.Flag_tpe_stocks:
ROC_era_date = self.date_changer(date)
# 股價資訊
self.Crawl_method(url = self.url_tpex_stock,
date = ROC_era_date,
Date = date,
url_suffix='&s=0,asc,0',
Flag_tpex_stocks=True,
Flag_tpex_insti_inv=False,
Flag_stocks=False,
Flag_insti_inv=False)
# 三大法人資訊
self.Crawl_method(url = self.url_tpex_df_institutional_investors,
date = ROC_era_date,
Date = date,
url_suffix='&s=0,asc',
Flag_tpex_stocks=False,
Flag_tpex_insti_inv=True,
Flag_stocks=False,
Flag_insti_inv=False)
# 本益比, 股價淨值比, 殖利率(%), 股利年度
self.Crawl_PB_and_PE(ROC_era_date)
################ 爬上市公司 ################
if self.Flag_tsw_stocks:
# 股價資訊
self.Crawl_method(url = self.url_stock,
date = date,
Date = date,
url_suffix='&type=ALL',
Flag_tpex_stocks=False,
Flag_tpex_insti_inv=False,
Flag_stocks=True,
Flag_insti_inv=False)
#爬上市公司三大法人資訊
self.Crawl_method(url = self.url_institutional_investors,
date = date,
Date = date,
url_suffix='&selectType=ALLBUT0999',
Flag_tpex_stocks=False,
Flag_tpex_insti_inv=False,
Flag_stocks=False,
Flag_insti_inv=True)
# 本益比, 股價淨值比, 殖利率(%), 股利年度
self.Crawl_PB_and_PE(date)
except Exception as err:
if type(err) == ValueError:
# print(err)
print(date +" is holiday")
elif type(err) == KeyError:
# print(err)
print(date +" is holiday")
else:
print("Error happens!! -> " + str(err))
break
time.sleep(self.timesleep)
# 把所有資料concatenate起來
self.ConcatData()
# 抓取特定股票(使用者要抓的那支股票)
#############################################
def Get_specific_stock(self, df):
if self.stock_name != '':
df = df[df["證券名稱"].apply(lambda x:x.replace(" ", "") ) == self.stock_name]
elif self.stock_num != '':
df["證券代號"] = df["證券代號"].apply(lambda x:x.replace("=", "").replace('"', '').replace(" ", ""))
df = df[df['證券代號'] == self.stock_num]
return df
# 重新命名col name, 確保一致
#############################################
def Rename_df_columns(self, df, Flag_tpex_stocks = False, Flag_tpex_insti_inv = False):
tpex_stocks_rename_columns = { "代號":"證券代號",
"名稱":"證券名稱",
"收盤 ":"收盤價",
"漲跌":"漲跌價差",
"開盤 ":"開盤價",
"最高 ":"最高價",
"最低":"最低價",
"成交股數 ":"成交股數",
"成交金額(元)":"成交金額",
"成交筆數 ":"成交筆數"}
tpex_insti_inv_rename_columns = { "代號":"證券代號",
"名稱":"證券名稱",
"外資及陸資(不含外資自營商)-買進股數":"外陸資買進股數(不含外資自營商)",
"外資及陸資(不含外資自營商)-賣出股數":"外陸資賣出股數(不含外資自營商)",
"外資及陸資(不含外資自營商)-買賣超股數":"外陸資買賣超股數(不含外資自營商)",
"外資自營商-買進股數":"外資自營商買進股數",
"外資自營商-賣出股數":"外資自營商賣出股數",
"外資自營商-買賣超股數":"外資自營商買賣超股數",
"投信-買進股數":"投信買進股數",
"投信-賣出股數":"投信賣出股數",
"投信-買賣超股數":"投信買賣超股數",
"自營商(自行買賣)-買進股數":"自營商買進股數(自行買賣)",
"自營商(自行買賣)-賣出股數":"自營商賣出股數(自行買賣)",
"自營商(自行買賣)-買賣超股數":"自營商買賣超股數(自行買賣)",
"自營商(避險)-買進股數":"自營商買進股數(避險)",
"自營商(避險)-賣出股數":"自營商賣出股數(避險)",
"自營商(避險)-買賣超股數":"自營商買賣超股數(避險)",
"自營商-買賣超股數":"自營商買賣超股數",
"三大法人買賣超股數合計":"三大法人買賣超股數" }
if Flag_tpex_stocks:
df.rename(columns=tpex_stocks_rename_columns, inplace = True)
elif Flag_tpex_insti_inv:
df.rename(columns=tpex_insti_inv_rename_columns, inplace = True)
else:
print("Error!!")
return df
# 開始爬蟲
#############################################
def Crawl_method(self, url, date, Date, url_suffix='', Flag_tpex_stocks=False, Flag_tpex_insti_inv=False,
Flag_stocks=False, Flag_insti_inv=False):
# 下載股價
r = requests.post( url + date + url_suffix)
# 整理資料，變成表格
if not Flag_tpex_stocks and not Flag_tpex_insti_inv and not Flag_stocks and not Flag_insti_inv:
print("Error...Crawling nothing, please set the flags right")
return 0
######### 爬上櫃公司 #########
if Flag_tpex_stocks:
df = pd.read_csv(StringIO(r.text), header=2).dropna(how='all', axis=1).dropna(how='any')
df = df.iloc[:, :11]
df = self.Rename_df_columns(df, Flag_tpex_stocks = True, Flag_tpex_insti_inv = False)
df = self.Get_specific_stock(df)
df.insert(0, "Date", Date)
df.drop("均價 ", axis = "columns", inplace = True)
df["漲跌(+/-)"] = df["漲跌價差"].values[0][0] if df["漲跌價差"].values[0][0] != "0" else "X"
self.df_stocks = self.df_stocks.append(df, ignore_index=True)
if Flag_tpex_insti_inv:
df = pd.read_csv(StringIO(r.text.replace("=", "")), header = 1 ).dropna(how='all', axis=1).dropna(how='any')
df.insert(0, "Date", Date)
df.drop(columns=[ "自營商-買進股數",
"自營商-賣出股數",
"外資及陸資-買進股數",
"外資及陸資-賣出股數",
"外資及陸資-買賣超股數"], inplace = True)
df = self.Rename_df_columns(df, Flag_tpex_stocks = False, Flag_tpex_insti_inv = True)
df = self.Get_specific_stock(df)
self.df_institutional_investors = self.df_institutional_investors.append(df, ignore_index = True)
######### 爬上市公司 #########
if Flag_stocks:
df = pd.read_csv(StringIO(r.text.replace("=", "")),
header = ["證券代號" in l for l in r.text.split("\n")].index(True)-1 )
df.insert(0, "Date", date)
df = df.iloc[:, :12]
df = self.Get_specific_stock(df)
self.df_stocks = self.df_stocks.append(df, ignore_index=True)
if Flag_insti_inv:
df = pd.read_csv(StringIO(r.text.replace("=", "")),
header = 1 ).dropna(how='all', axis=1).dropna(how='any')
df.insert(0, "Date", date)
df = self.Get_specific_stock(df)
self.df_institutional_investors = self.df_institutional_investors.append(df, ignore_index = True)
# 合併Date
#############################################
def ConcatData(self):
# 將index reset 以免concat出現NaN值
self.df_stocks.reset_index(drop=True, inplace=True)
self.df_institutional_investors.reset_index(drop=True, inplace=True)
self.df_statistics.reset_index(drop=True, inplace=True)
self.df_stocks = pd.concat([self.df_stocks, self.df_institutional_investors.drop(columns=["Date", "證券代號", "證券名稱"]),
self.df_statistics.drop(columns=["證券代號", "證券名稱"])], axis = 1)
# 將Date存進資料庫
#############################################
def SaveIntoDatabase(self):
# creating column list for insertion
cols = "`,`".join([str(i) for i in self.df_stocks.columns.tolist()])
# Insert DataFrame recrds one by one.
for i, row in self.df_stocks.iterrows():
try:
sql = "INSERT INTO `{}` (`".format(self.table_name) +cols + "`) VALUES (" + "%s,"*(len(row)-1) + "%s)"
self.cursor.execute(sql, tuple(row))
# the connection is not autocommitted by default, so we must commit to save our changes
self.db.commit()
except Exception as err:
# print(err)
print("This data already exists in this table, jumping...")
continue
# 抓取PB, PE
#############################################
def Crawl_PB_and_PE(self, date):
"""
This function is for crwaling the PB, PE and Dividend yield statistics.
"""
# 上櫃公司
if self.Flag_tpe_stocks:
url = "https://www.tpex.org.tw/web/stock/aftertrading/peratio_analysis/pera_download.php?l=zh-tw&d="+date+"&s=0,asc,0"
r = requests.get(url)
r = r.text.split("\n")
df = pd.read_csv(StringIO("\n".join(r[3:-1]))).fillna(0)
columns_title = ["股票代號", "名稱", "本益比", "股價淨值比", "殖利率(%)", "股利年度" ]
df = df[columns_title]
df.rename(columns = {"殖利率(%)":"殖利率", "股票代號":"證券代號", "名稱":"證券名稱"}, inplace = True)
df = self.Get_specific_stock(df)
self.df_statistics = self.df_statistics.append(df, ignore_index=True)
# 上市公司
if self.Flag_tsw_stocks:
url = "https://www.twse.com.tw/exchangeReport/BWIBBU_d?response=csv&date="+date+"&selectType=ALL"
r = requests.get(url)
r = r.text.split("\r\n")[:-13]
df = pd.read_csv(StringIO("\n".join(r)), header=1).dropna(how="all", axis=1).apply(lambda x:x.replace("-", 0))
columns_title = ["證券代號", "證券名稱", "本益比", "股價淨值比", "殖利率(%)", "股利年度" ]
df = df[columns_title]
df.rename(columns = {"殖利率(%)":"殖利率"}, inplace = True)
df = self.Get_specific_stock(df)
self.df_statistics = self.df_statistics.append(df, ignore_index=True)