回答編集履歴
1
追記
test
CHANGED
|
@@ -41,3 +41,125 @@
|
|
|
41
41
|
time.sleep(1)
|
|
42
42
|
|
|
43
43
|
```
|
|
44
|
+
|
|
45
|
+
|
|
46
|
+
|
|
47
|
+
|
|
48
|
+
|
|
49
|
+
### 追記
|
|
50
|
+
|
|
51
|
+
上記ではログインしている事を前提で～と回答を致しましたが
|
|
52
|
+
|
|
53
|
+
恐らくは質問者様はスクレイピングの際にログイン処理は行っていないでしょう。
|
|
54
|
+
|
|
55
|
+
ログイン処理については恐らくはseleniumを使用した方が簡易的でしょう。
|
|
56
|
+
|
|
57
|
+
となると、各項の取得もrequestsを使用するのではなくselenium上で取得を行い
|
|
58
|
+
|
|
59
|
+
`driver.page_source`でソースを取得しBSで各要素を出力するというのがベストな方法だと思います。
|
|
60
|
+
|
|
61
|
+
|
|
62
|
+
|
|
63
|
+
```python
|
|
64
|
+
|
|
65
|
+
from selenium import webdriver
|
|
66
|
+
|
|
67
|
+
from selenium.webdriver.chrome.options import Options
|
|
68
|
+
|
|
69
|
+
from bs4 import BeautifulSoup
|
|
70
|
+
|
|
71
|
+
import time
|
|
72
|
+
|
|
73
|
+
|
|
74
|
+
|
|
75
|
+
idpw = ('ID', 'PASSWORD')
|
|
76
|
+
|
|
77
|
+
url = 'https://input.medilink-study.com/index.php'
|
|
78
|
+
|
|
79
|
+
target = "https://input.medilink-study.com/detail.php?index={}"
|
|
80
|
+
|
|
81
|
+
|
|
82
|
+
|
|
83
|
+
|
|
84
|
+
|
|
85
|
+
options = Options()
|
|
86
|
+
|
|
87
|
+
options.add_argument('--headless') # ←コメントアウトでヘッドレスモード解除
|
|
88
|
+
|
|
89
|
+
driver = webdriver.Chrome(chrome_options=options)
|
|
90
|
+
|
|
91
|
+
driver.implicitly_wait(10)
|
|
92
|
+
|
|
93
|
+
driver.get(url)
|
|
94
|
+
|
|
95
|
+
|
|
96
|
+
|
|
97
|
+
# ログイン処理
|
|
98
|
+
|
|
99
|
+
login_button = driver.find_element_by_class_name('icon-login').click()
|
|
100
|
+
|
|
101
|
+
driver.find_element_by_class_name('cmn-form-userid').send_keys(idpw[0])
|
|
102
|
+
|
|
103
|
+
driver.find_element_by_class_name('cmn-form-password').send_keys(idpw[1])
|
|
104
|
+
|
|
105
|
+
driver.find_element_by_class_name('cmn-form-login-button').click()
|
|
106
|
+
|
|
107
|
+
time.sleep(5)
|
|
108
|
+
|
|
109
|
+
|
|
110
|
+
|
|
111
|
+
|
|
112
|
+
|
|
113
|
+
for i in range(1, 58):
|
|
114
|
+
|
|
115
|
+
driver.get(target.format(i))
|
|
116
|
+
|
|
117
|
+
html = driver.page_source
|
|
118
|
+
|
|
119
|
+
soup = BeautifulSoup(html, 'html.parser')
|
|
120
|
+
|
|
121
|
+
|
|
122
|
+
|
|
123
|
+
# お題と回答の取得
|
|
124
|
+
|
|
125
|
+
elements = soup.select('.heading')
|
|
126
|
+
|
|
127
|
+
title = elements[0].string
|
|
128
|
+
|
|
129
|
+
answer = elements[1].text
|
|
130
|
+
|
|
131
|
+
|
|
132
|
+
|
|
133
|
+
# 解説の取得
|
|
134
|
+
|
|
135
|
+
elements2 = soup.select("#detail > div.bg.bg-theme.border.type-detail > div > div > article > div:nth-child(5) > ul > li")
|
|
136
|
+
|
|
137
|
+
commentaries = {}
|
|
138
|
+
|
|
139
|
+
if len(elements2) != 0:
|
|
140
|
+
|
|
141
|
+
for cmt in elements2:
|
|
142
|
+
|
|
143
|
+
key, value = cmt.select('div')
|
|
144
|
+
|
|
145
|
+
key, value = key.text, value.text
|
|
146
|
+
|
|
147
|
+
commentaries[key] = value
|
|
148
|
+
|
|
149
|
+
# 解説要素がなかった場合
|
|
150
|
+
|
|
151
|
+
else:
|
|
152
|
+
|
|
153
|
+
commentaries = 'comment was none'
|
|
154
|
+
|
|
155
|
+
|
|
156
|
+
|
|
157
|
+
print(title, answer)
|
|
158
|
+
|
|
159
|
+
print(commentaries)
|
|
160
|
+
|
|
161
|
+
print('='*50)
|
|
162
|
+
|
|
163
|
+
time.sleep(1)
|
|
164
|
+
|
|
165
|
+
```
|