teratail
回答率
85.47%
質問するログイン新規登録
トップに関する質問seleniumとBeautihulSoupを用いて社会科のキーワードとそのリンク先の説明を取得したい

編集履歴

質問編集履歴

7

初心者

2020/04/23 13:38

投稿

YummyD
YummyD

スコア5

test CHANGED
File without changes
test CHANGED
@@ -1,6 +1,6 @@
1
1
  ### python3でseleniumとbs4を使用 使用機材はmac
2
2
 
3
-
3
+ 　
4
4
 
5
5
  seleniumとbs4を用いてスクレイピングをしています。社会科のキーワード集作成のためにキーワードとそのリンク先の説明を取得したいです。
6
6
 

6

ソースコードの変更

2020/04/23 13:38

投稿

YummyD
YummyD

スコア5

test CHANGED
File without changes
test CHANGED
@@ -112,11 +112,15 @@
112
112
 
113
113
  ```python
114
114
 
115
- import requests, bs4
115
+ import requests, bs4, sys
116
116
 
117
117
  from selenium import webdriver
118
118
 
119
119
  from time import sleep
120
+
121
+ import urllib
122
+
123
+ urllib.request.http.client
120
124
 
121
125
 
122
126
 
@@ -124,13 +128,13 @@
124
128
 
125
129
  print('Next...')
126
130
 
127
- driver = webdriver.Firefox(executable_path='/Users/katsuhisaoikawa/opt/anaconda3/bin/geckodriver')
131
+ driver = webdriver.Firefox(executable_path='/Users/****/opt/anaconda3/bin/geckodriver')
128
132
 
129
133
  url = 'http://ssd.cswiki.jp/index.php?%E6%AD%B4%E5%8F%B2%EF%BC%A1%E3%83%A9%E3%83%B3%E3%82%AF'
130
134
 
131
135
  driver.get(url)
132
136
 
133
- sleep(30)
137
+ sleep(10)
134
138
 
135
139
 
136
140
 
@@ -151,6 +155,8 @@
151
155
  time.sleep(30)
152
156
 
153
157
  driver.back()
158
+
159
+
154
160
 
155
161
 
156
162
 

5

requestsの再インストール

2020/04/23 11:46

投稿

YummyD
YummyD

スコア5

test CHANGED
File without changes
test CHANGED
@@ -22,7 +22,7 @@
22
22
 
23
23
  File "Selelelen.py", line 1, in <module>
24
24
 
25
- import requests, bs4
25
+ import requests, bs4, sys
26
26
 
27
27
  File "/Users/****/opt/anaconda3/lib/python3.7/site-packages/requests/__init__.py", line 43, in <module>
28
28
 
@@ -80,7 +80,7 @@
80
80
 
81
81
  from . import _html5lib
82
82
 
83
- File "/Users/****a/opt/anaconda3/lib/python3.7/site-packages/bs4/builder/_html5lib.py", line 20, in <module>
83
+ File "/Users/****/opt/anaconda3/lib/python3.7/site-packages/bs4/builder/_html5lib.py", line 20, in <module>
84
84
 
85
85
  import html5lib
86
86
 
@@ -101,8 +101,6 @@
101
101
  if hasattr(http.client, 'HTTPSConnection'):
102
102
 
103
103
  AttributeError: module 'http' has no attribute 'client'
104
-
105
-
106
104
 
107
105
  ```
108
106
 

4

エラーメッセージ全文に変更

2020/04/23 11:44

投稿

YummyD
YummyD

スコア5

test CHANGED
File without changes
test CHANGED
@@ -17,8 +17,6 @@
17
17
 
18
18
 
19
19
 
20
-
21
- (base) ****@****noMacBook-Air program % python Selelelen.py
22
20
 
23
21
  Traceback (most recent call last):
24
22
 
@@ -82,7 +80,7 @@
82
80
 
83
81
  from . import _html5lib
84
82
 
85
- File "/Users/****/opt/anaconda3/lib/python3.7/site-packages/bs4/builder/_html5lib.py", line 20, in <module>
83
+ File "/Users/****a/opt/anaconda3/lib/python3.7/site-packages/bs4/builder/_html5lib.py", line 20, in <module>
86
84
 
87
85
  import html5lib
88
86
 
@@ -103,8 +101,6 @@
103
101
  if hasattr(http.client, 'HTTPSConnection'):
104
102
 
105
103
  AttributeError: module 'http' has no attribute 'client'
106
-
107
-
108
104
 
109
105
 
110
106
 

3

エラーメッセージ全文に変更

2020/04/22 16:15

投稿

YummyD
YummyD

スコア5

test CHANGED
File without changes
test CHANGED
@@ -16,7 +16,97 @@
16
16
 
17
17
 
18
18
 
19
+
20
+
21
+ (base) ****@****noMacBook-Air program % python Selelelen.py
22
+
23
+ Traceback (most recent call last):
24
+
25
+ File "Selelelen.py", line 1, in <module>
26
+
27
+ import requests, bs4
28
+
29
+ File "/Users/****/opt/anaconda3/lib/python3.7/site-packages/requests/__init__.py", line 43, in <module>
30
+
31
+ import urllib3
32
+
33
+ File "/Users/****/opt/anaconda3/lib/python3.7/site-packages/urllib3/__init__.py", line 7, in <module>
34
+
35
+ from .connectionpool import HTTPConnectionPool, HTTPSConnectionPool, connection_from_url
36
+
37
+ File "/Users/****/opt/anaconda3/lib/python3.7/site-packages/urllib3/connectionpool.py", line 11, in <module>
38
+
39
+ from .exceptions import (
40
+
41
+ File "/Users/****/opt/anaconda3/lib/python3.7/site-packages/urllib3/exceptions.py", line 2, in <module>
42
+
43
+ from .packages.six.moves.http_client import IncompleteRead as httplib_IncompleteRead
44
+
45
+ File "<frozen importlib._bootstrap>", line 983, in _find_and_load
46
+
47
+ File "<frozen importlib._bootstrap>", line 967, in _find_and_load_unlocked
48
+
49
+ File "<frozen importlib._bootstrap>", line 668, in _load_unlocked
50
+
51
+ File "<frozen importlib._bootstrap>", line 638, in _load_backward_compatible
52
+
53
+ File "/Users/****/opt/anaconda3/lib/python3.7/site-packages/urllib3/packages/six.py", line 199, in load_module
54
+
55
+ mod = mod._resolve()
56
+
57
+ File "/Users/****/opt/anaconda3/lib/python3.7/site-packages/urllib3/packages/six.py", line 113, in _resolve
58
+
59
+ return _import_module(self.mod)
60
+
61
+ File "/Users/****/opt/anaconda3/lib/python3.7/site-packages/urllib3/packages/six.py", line 82, in _import_module
62
+
63
+ __import__(name)
64
+
65
+ File "/Users/****/opt/anaconda3/lib/python3.7/http/client.py", line 72, in <module>
66
+
67
+ import email.message
68
+
69
+ File "/Users/****/opt/anaconda3/lib/python3.7/email/message.py", line 10, in <module>
70
+
71
+ import uu
72
+
73
+ File "/Users/****/Desktop/Program/uu.py", line 1, in <module>
74
+
75
+ import requests, sys, webbrowser, bs4
76
+
77
+ File "/Users/****/opt/anaconda3/lib/python3.7/site-packages/bs4/__init__.py", line 31, in <module>
78
+
79
+ from .builder import builder_registry, ParserRejectedMarkup
80
+
81
+ File "/Users/****/opt/anaconda3/lib/python3.7/site-packages/bs4/builder/__init__.py", line 475, in <module>
82
+
83
+ from . import _html5lib
84
+
85
+ File "/Users/****/opt/anaconda3/lib/python3.7/site-packages/bs4/builder/_html5lib.py", line 20, in <module>
86
+
87
+ import html5lib
88
+
89
+ File "/Users/****/opt/anaconda3/lib/python3.7/site-packages/html5lib/__init__.py", line 28, in <module>
90
+
91
+ from .serializer import serialize
92
+
93
+ File "/Users/****/opt/anaconda3/lib/python3.7/site-packages/html5lib/serializer.py", line 11, in <module>
94
+
95
+ from xml.sax.saxutils import escape
96
+
97
+ File "/Users/****/opt/anaconda3/lib/python3.7/xml/sax/saxutils.py", line 6, in <module>
98
+
99
+ import os, urllib.parse, urllib.request
100
+
101
+ File "/Users/****/opt/anaconda3/lib/python3.7/urllib/request.py", line 1351, in <module>
102
+
103
+ if hasattr(http.client, 'HTTPSConnection'):
104
+
19
105
  AttributeError: module 'http' has no attribute 'client'
106
+
107
+
108
+
109
+
20
110
 
21
111
  ```
22
112
 

2

エラーメッセージの訂正　sleepの秒数変更

2020/04/22 16:10

投稿

YummyD
YummyD

スコア5

test CHANGED
File without changes
test CHANGED
@@ -16,7 +16,7 @@
16
16
 
17
17
 
18
18
 
19
- AttributeError: 'str' object has no attribute 'append'
19
+ AttributeError: module 'http' has no attribute 'client'
20
20
 
21
21
  ```
22
22
 
@@ -46,7 +46,7 @@
46
46
 
47
47
  driver.get(url)
48
48
 
49
- sleep(2000)
49
+ sleep(30)
50
50
 
51
51
 
52
52
 

1

スペルミスの修正を行った。

2020/04/22 14:52

投稿

YummyD
YummyD

スコア5

test CHANGED
File without changes
test CHANGED
@@ -50,13 +50,13 @@
50
50
 
51
51
 
52
52
 
53
- explain_url = []
53
+ explain_urls = []
54
54
 
55
55
  elems_explain_url = driver.find_elements_by_css_selector('#body p a')
56
56
 
57
57
  for elem_explain_url in elems_explain_url:
58
58
 
59
- explain_urls = elem_explain_url.get_attribute('href')
59
+ explain_url = elem_explain_url.get_attribute('href')
60
60
 
61
61
  explain_urls.append(explain_url)
62
62