forked from susumOyaji/phytonsample
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathstockPriceDataCollection.py
149 lines (126 loc) · 5.46 KB
/
stockPriceDataCollection.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
#BM Pythonで作る株価予測SlackBot
#import vital tools
from selenium import webdriver
import pandas as pd
import numpy as np
from matplotlib import pyplot as plt
#%matplotlib inline
#browser open (chrome)
browser=webdriver.Chrome()
#ready for scraping
columnNames=[]
ETFComparisonsTable=[]
for num in range(0,48):
browser.get("https://kabuoji3.com/stock/")
stockSearch=browser.find_element_by_class_name("form_inputs")
stockSearchForm=stockSearch.find_element_by_class_name("form_txt")
stockSearchForm.send_keys("ETF")
btnClick=browser.find_element_by_class_name("btn_submit")
btnClick.click()
#choose a stock out of list
stockClick=browser.find_elements_by_class_name("clickable")
stockClick[num].find_element_by_tag_name("a").click()
stockTable=browser.find_element_by_class_name("table_wrap")
stockLine=stockTable.find_elements_by_tag_name("tr")
#price scraping with calculation
if len(stockLine)==302:
ETFComparisons=[]
for i in range(2,152):
stockETFPriceAfter=stockLine[i-1].find_elements_by_tag_name("td")
stockETFPriceBefore=stockLine[i].find_elements_by_tag_name("td")
ETFComparison=float(stockETFPriceAfter[6].text)-float(stockETFPriceBefore[6].text)
ETFComparisons.append(ETFComparison)
stockETFPriceAfter=stockLine[151].find_elements_by_tag_name("td")
stockETFPriceBefore=stockLine[153].find_elements_by_tag_name("td")
ETFComparison=float(stockETFPriceAfter[6].text)-float(stockETFPriceBefore[6].text)
ETFComparisons.append(ETFComparison)
for i in range(154,302):
stockETFPriceAfter=stockLine[i-1].find_elements_by_tag_name("td")
stockETFPriceBefore=stockLine[i].find_elements_by_tag_name("td")
ETFComparison=float(stockETFPriceAfter[6].text)-float(stockETFPriceBefore[6].text)
ETFComparisons.append(ETFComparison)
ETFComparisonsTable.append(ETFComparisons)
#pick up title
stockTitleBox=browser.find_element_by_class_name("base_box_ttl")
stockTitle=stockTitleBox.find_element_by_class_name("jp").text
columnNames.append(stockTitle)
#making ETF table
ETFTable=pd.DataFrame(ETFComparisonsTable)
ETFTable=ETFTable.T
ETFTable.columns=columnNames
#checking ETF table
ETF.head()
#date scraping
browser.get("https://kabuoji3.com/stock/{}/".format(4307))
stockTable=browser.find_element_by_class_name("table_wrap")
stockLine=stockTable.find_elements_by_tag_name("tr")
dates=[]
for i in range(1,152):
stockDate=stockLine[i].find_elements_by_tag_name("td")
stockDate=stockDate[0].text
dates.append(stockDate)
for i in range(153,302):
stockDate=stockLine[i].find_elements_by_tag_name("td")
stockDate=stockDate[0].text
dates.append(stockDate)
df_date=pd.DataFrame()
df_date["date"]=dates
df_date["year"]=df_date["date"].apply(lambda x:int(x.split("-")[0]))
df_date["month"]=df_date["date"].apply(lambda x:int(x.split("-")[1]))
df_date["day"]=df_date["date"].apply(lambda x:int(x.split("-")[2]))
df_date.head()
#stock scraping (comparison with yesterday)
browser.get("https://kabuoji3.com/stock/{}/".format(4307))
stockTable=browser.find_element_by_class_name("table_wrap")
stockLine=stockTable.find_elements_by_tag_name("tr")
targetStockComparisons=[]
for i in range(2,152):
targetStockPriceAfter=stockLine[i-1].find_elements_by_tag_name("td")
targetStockPriceBefore=stockLine[i].find_elements_by_tag_name("td")
targetStockComparison=float(targetStockPriceAfter[6].text)-float(targetStockPriceBefore[6].text)
targetStockComparisons.append(targetStockComparison)
targetStockPriceAfter=stockLine[151].find_elements_by_tag_name("td")
targetStockPriceBefore=stockLine[153].find_elements_by_tag_name("td")
targetStockComparison=float(targetStockPriceAfter[6].text)-float(targetStockPriceBefore[6].text)
targetStockComparisons.append(targetStockComparison)
for i in range(154,302):
targetStockPriceAfter=stockLine[i-1].find_elements_by_tag_name("td")
targetStockPriceBefore=stockLine[i].find_elements_by_tag_name("td")
targetStockComparison=float(targetStockPriceAfter[6].text)-float(targetStockPriceBefore[6].text)
targetStockComparisons.append(targetStockComparison)
df=pd.DataFrame(targetStockComparisons)
df.columns=["(株)野村総合研究所：前日比"]
df.head()
#add table
stockPriceTable=pd.concat([df_date,ETFTable],axis=1)
stockPriceTable=pd.concat([stockPriceTable,df],axis=1)
stockPriceTable.head()
#prepare for making target values
df_next=df.copy()
df_next.columns=["(株)野村総合研究所：翌日比"]
#date scraping for target values
browser.get("https://kabuoji3.com/stock/{}/".format(4307))
stockTable=browser.find_element_by_class_name("table_wrap")
stockLine=stockTable.find_elements_by_tag_name("tr")
dates=[]
for i in range(2,152):
stockDate=stockLine[i].find_elements_by_tag_name("td")
stockDate=stockDate[0].text
dates.append(stockDate)
for i in range(153,302):
stockDate=stockLine[i].find_elements_by_tag_name("td")
stockDate=stockDate[0].text
dates.append(stockDate)
df_date2=pd.DataFrame()
df_date2["date"]=dates
#making target values table
df_next=pd.concat([df_date2,df_next],axis=1)
df_next.index=df_date2["date"]
#prepare for complete table
table=stockPriceTable[1:299].copy()
table.index=table["date"]
#making complete table
table["(株)野村総合研究所：翌日比"]=df_next["(株)野村総合研究所：翌日比"]
table.tail()
#making csv file
table.to_csv("stockPriceData.csv", index=False)