質問編集履歴
1
ソースコードを載せました。人気の本（文庫、新書、漫画・・・）のデータを抽出しています。
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -24,25 +24,187 @@
|
|
|
24
24
|
|
|
25
25
|
```Python
|
|
26
26
|
|
|
27
|
+
|
|
28
|
+
|
|
29
|
+
import requests
|
|
30
|
+
|
|
31
|
+
from bs4 import BeautifulSoup
|
|
32
|
+
|
|
27
33
|
import pandas as pd
|
|
28
34
|
|
|
29
35
|
import xlsxwriter
|
|
30
36
|
|
|
31
|
-
|
|
32
|
-
|
|
33
|
-
|
|
34
|
-
|
|
35
|
-
pa
|
|
36
|
-
|
|
37
|
-
|
|
38
|
-
|
|
39
|
-
|
|
40
|
-
|
|
41
|
-
|
|
42
|
-
|
|
43
|
-
|
|
44
|
-
|
|
45
|
-
|
|
37
|
+
import openpyxl as opx
|
|
38
|
+
|
|
39
|
+
|
|
40
|
+
|
|
41
|
+
pages = 1
|
|
42
|
+
|
|
43
|
+
|
|
44
|
+
|
|
45
|
+
data = []
|
|
46
|
+
|
|
47
|
+
data1 = [] #デイリー
|
|
48
|
+
|
|
49
|
+
data2 = [] #週刊
|
|
50
|
+
|
|
51
|
+
data3 = [] #月間
|
|
52
|
+
|
|
53
|
+
data4 = [] #年間
|
|
54
|
+
|
|
55
|
+
genre = ""
|
|
56
|
+
|
|
57
|
+
path = r"C:パス"
|
|
58
|
+
|
|
59
|
+
wb = opx.load_workbook(path)
|
|
60
|
+
|
|
61
|
+
|
|
62
|
+
|
|
63
|
+
#メイン処理を行う
|
|
64
|
+
|
|
65
|
+
def mainData(baseURL,pages):
|
|
66
|
+
|
|
67
|
+
while pages <= 5:
|
|
68
|
+
|
|
69
|
+
url = baseURL + str(pages)
|
|
70
|
+
|
|
71
|
+
OpenURL = requests.get(url)
|
|
72
|
+
|
|
73
|
+
content = OpenURL.content
|
|
74
|
+
|
|
75
|
+
soup = BeautifulSoup(content, 'html.parser')
|
|
76
|
+
|
|
77
|
+
|
|
78
|
+
|
|
79
|
+
for div in soup.select("div.desc"):
|
|
80
|
+
|
|
81
|
+
title = div.a.string
|
|
82
|
+
|
|
83
|
+
users = div.select_one(".info-users").span.get_text(strip=True)
|
|
84
|
+
|
|
85
|
+
author = div.select_one(".itemInfoElmBox").a.string
|
|
86
|
+
|
|
87
|
+
|
|
88
|
+
|
|
89
|
+
data.append(
|
|
90
|
+
|
|
91
|
+
{
|
|
92
|
+
|
|
93
|
+
"title": title,
|
|
94
|
+
|
|
95
|
+
"users": users,
|
|
96
|
+
|
|
97
|
+
"author": author,
|
|
98
|
+
|
|
99
|
+
}
|
|
100
|
+
|
|
101
|
+
)
|
|
102
|
+
|
|
103
|
+
next
|
|
104
|
+
|
|
105
|
+
|
|
106
|
+
|
|
107
|
+
pages += 1
|
|
108
|
+
|
|
109
|
+
return data
|
|
110
|
+
|
|
111
|
+
|
|
112
|
+
|
|
113
|
+
#データ4回*4（ジャンル）
|
|
114
|
+
|
|
115
|
+
for i in range(4):
|
|
116
|
+
|
|
117
|
+
if i == 0:
|
|
118
|
+
|
|
119
|
+
genre = "book"
|
|
120
|
+
|
|
121
|
+
|
|
122
|
+
|
|
123
|
+
elif i == 1:
|
|
124
|
+
|
|
125
|
+
genre = "bunko"
|
|
126
|
+
|
|
127
|
+
|
|
128
|
+
|
|
129
|
+
elif i == 2:
|
|
130
|
+
|
|
131
|
+
genre = "shinsho"
|
|
132
|
+
|
|
133
|
+
|
|
134
|
+
|
|
135
|
+
elif i == 3:
|
|
136
|
+
|
|
137
|
+
genre ="comic"
|
|
138
|
+
|
|
139
|
+
|
|
140
|
+
|
|
141
|
+
for config in range(4):
|
|
142
|
+
|
|
143
|
+
if config == 0:
|
|
144
|
+
|
|
145
|
+
baseURL = "https://booklog.jp/ranking/" + genre + "?page="
|
|
146
|
+
|
|
147
|
+
data1 = mainData(baseURL,1)
|
|
148
|
+
|
|
149
|
+
data = [] #初期化
|
|
150
|
+
|
|
151
|
+
|
|
152
|
+
|
|
153
|
+
elif config == 1:
|
|
154
|
+
|
|
155
|
+
baseURL ="https://booklog.jp/ranking/weekly/201908/1/" + genre + "?page="
|
|
156
|
+
|
|
157
|
+
data2 = mainData(baseURL,1)
|
|
158
|
+
|
|
159
|
+
data = [] #初期化
|
|
160
|
+
|
|
161
|
+
|
|
162
|
+
|
|
163
|
+
elif config == 2:
|
|
164
|
+
|
|
165
|
+
baseURL ="https://booklog.jp/ranking/monthly/201907/" + genre + "?page="
|
|
166
|
+
|
|
167
|
+
data3 = mainData(baseURL,1)
|
|
168
|
+
|
|
169
|
+
data = [] #初期化
|
|
170
|
+
|
|
171
|
+
|
|
172
|
+
|
|
173
|
+
elif config == 3:
|
|
174
|
+
|
|
175
|
+
baseURL = "https://booklog.jp/ranking/annual/2018/" + genre + "?page="
|
|
176
|
+
|
|
177
|
+
data4 = mainData(baseURL,1)
|
|
178
|
+
|
|
179
|
+
data = [] #初期化
|
|
180
|
+
|
|
181
|
+
|
|
182
|
+
|
|
183
|
+
books1 = pd.DataFrame(data1)
|
|
184
|
+
|
|
185
|
+
books2 = pd.DataFrame(data2)
|
|
186
|
+
|
|
187
|
+
books3 = pd.DataFrame(data3)
|
|
188
|
+
|
|
189
|
+
books4 = pd.DataFrame(data4)
|
|
190
|
+
|
|
191
|
+
|
|
192
|
+
|
|
193
|
+
with pd.ExcelWriter(path)as writer:
|
|
194
|
+
|
|
195
|
+
books1.to_excel(xlsxwriter, sheet_name=genre+'デイリー')
|
|
196
|
+
|
|
197
|
+
books2.to_excel(xlsxwriter, sheet_name=genre+'週間')
|
|
198
|
+
|
|
199
|
+
books3.to_excel(xlsxwriter, sheet_name=genre+'月間')
|
|
200
|
+
|
|
201
|
+
books4.to_excel(xlsxwriter, sheet_name=genre+'年間')
|
|
202
|
+
|
|
203
|
+
|
|
204
|
+
|
|
205
|
+
|
|
206
|
+
|
|
207
|
+
|
|
46
208
|
|
|
47
209
|
|
|
48
210
|
|