質問編集履歴
4
codeの修正
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -36,6 +36,10 @@
|
|
|
36
36
|
|
|
37
37
|
import requests
|
|
38
38
|
|
|
39
|
+
from bs4 import BeautifulSoup
|
|
40
|
+
|
|
41
|
+
|
|
42
|
+
|
|
39
43
|
cakes = []
|
|
40
44
|
|
|
41
45
|
urls = create_url(http)
|
|
@@ -48,13 +52,11 @@
|
|
|
48
52
|
|
|
49
53
|
contents = bs.find_all('div',class_='Menu')
|
|
50
54
|
|
|
51
|
-
|
|
52
|
-
|
|
53
55
|
for content in contents:
|
|
54
56
|
|
|
55
|
-
|
|
57
|
+
cake_name = content.find('div',class_='cake').find('a')
|
|
56
58
|
|
|
57
|
-
|
|
59
|
+
cakes.append(cake_name.text)
|
|
58
60
|
|
|
59
61
|
|
|
60
62
|
|
3
codeの修正
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -2,19 +2,21 @@
|
|
|
2
2
|
|
|
3
3
|
```ここに言語を入力
|
|
4
4
|
|
|
5
|
-
|
|
5
|
+
cakes = []
|
|
6
|
-
|
|
7
|
-
messages = []
|
|
8
|
-
|
|
9
|
-
companys = []
|
|
10
|
-
|
|
11
|
-
links = []
|
|
12
6
|
|
|
13
7
|
```
|
|
14
8
|
|
|
15
|
-
この
|
|
9
|
+
このリストの中身を重複しないようにしたい。
|
|
16
10
|
|
|
17
11
|
どのような書き方があるのか知りたいです。
|
|
12
|
+
|
|
13
|
+
|
|
14
|
+
|
|
15
|
+
前回のコードは、規約違反でしたので削除しました。
|
|
16
|
+
|
|
17
|
+
指摘ありがとうございました。
|
|
18
|
+
|
|
19
|
+
|
|
18
20
|
|
|
19
21
|
|
|
20
22
|
|
|
@@ -30,100 +32,30 @@
|
|
|
30
32
|
|
|
31
33
|
```ここに言語名を入力
|
|
32
34
|
|
|
33
|
-
def create_url(words,live,pages):
|
|
34
35
|
|
|
35
|
-
urls = []
|
|
36
36
|
|
|
37
|
-
|
|
37
|
+
import requests
|
|
38
38
|
|
|
39
|
-
|
|
39
|
+
cakes = []
|
|
40
40
|
|
|
41
|
-
|
|
41
|
+
urls = create_url(http)
|
|
42
42
|
|
|
43
|
-
|
|
43
|
+
for url in urls:
|
|
44
44
|
|
|
45
|
-
|
|
45
|
+
r = requests.get(url)
|
|
46
46
|
|
|
47
|
+
bs =BeautifulSoup(r.text,'lxml')
|
|
48
|
+
|
|
49
|
+
contents = bs.find_all('div',class_='Menu')
|
|
50
|
+
|
|
51
|
+
|
|
52
|
+
|
|
47
|
-
ret
|
|
53
|
+
for content in contents:
|
|
54
|
+
|
|
55
|
+
title = content.find('div',class_='cake').find('a')
|
|
56
|
+
|
|
57
|
+
titles.append(title.text)
|
|
48
58
|
|
|
49
59
|
|
|
50
60
|
|
|
51
|
-
def job_search(words,live,pages):
|
|
52
|
-
|
|
53
|
-
|
|
54
|
-
|
|
55
|
-
import requests
|
|
56
|
-
|
|
57
|
-
from bs4 import BeautifulSoup
|
|
58
|
-
|
|
59
|
-
|
|
60
|
-
|
|
61
|
-
titles = []
|
|
62
|
-
|
|
63
|
-
messages = []
|
|
64
|
-
|
|
65
|
-
companys = []
|
|
66
|
-
|
|
67
|
-
links = []
|
|
68
|
-
|
|
69
|
-
scheme='https://jp.indeed.com/'
|
|
70
|
-
|
|
71
|
-
|
|
72
|
-
|
|
73
|
-
urls = create_url(words,live,pages)
|
|
74
|
-
|
|
75
|
-
for url in urls:
|
|
76
|
-
|
|
77
|
-
r = requests.get(url)
|
|
78
|
-
|
|
79
|
-
bs =BeautifulSoup(r.text,'lxml')
|
|
80
|
-
|
|
81
|
-
contents = bs.find_all('div',class_='jobsearch-SerpJobCard')
|
|
82
|
-
|
|
83
|
-
|
|
84
|
-
|
|
85
|
-
for content in contents:
|
|
86
|
-
|
|
87
|
-
title = content.find('div',class_='title').find('a')
|
|
88
|
-
|
|
89
|
-
titles.append(title.text)
|
|
90
|
-
|
|
91
|
-
|
|
92
|
-
|
|
93
|
-
message = content.find('div',class_='summary')
|
|
94
|
-
|
|
95
|
-
messages.append(message.text)
|
|
96
|
-
|
|
97
|
-
|
|
98
|
-
|
|
99
|
-
company = content.find('div',class_='sjcl').find('span',class_='company')
|
|
100
|
-
|
|
101
|
-
companys.append(company.text)
|
|
102
|
-
|
|
103
|
-
|
|
104
|
-
|
|
105
|
-
link = scheme+content.find('a').get('href')
|
|
106
|
-
|
|
107
|
-
links.append(link)
|
|
108
|
-
|
|
109
|
-
|
|
110
|
-
|
|
111
|
-
return titles,messages,companys,links
|
|
112
|
-
|
|
113
|
-
|
|
114
|
-
|
|
115
|
-
def job_printer(word,live,pages):
|
|
116
|
-
|
|
117
|
-
titles,messages,companys,links = job_search(word,live,pages)
|
|
118
|
-
|
|
119
|
-
print('\n\n')
|
|
120
|
-
|
|
121
|
-
print('{}社見つかりました。\n\n 検索ワード:{}\t所在市:{}\tページ数:{}'.format(len(companys),word,live,pages))
|
|
122
|
-
|
|
123
|
-
for i in range(len(messages)):
|
|
124
|
-
|
|
125
|
-
print(titles[i],'\n',messages[i],'\n',companys[i],'\n',links[i])
|
|
126
|
-
|
|
127
|
-
print('\n\n')
|
|
128
|
-
|
|
129
61
|
```
|
2
codeの修正
test
CHANGED
|
File without changes
|
test
CHANGED
|
@@ -66,8 +66,6 @@
|
|
|
66
66
|
|
|
67
67
|
links = []
|
|
68
68
|
|
|
69
|
-
checkbox = []
|
|
70
|
-
|
|
71
69
|
scheme='https://jp.indeed.com/'
|
|
72
70
|
|
|
73
71
|
|
|
@@ -82,25 +80,9 @@
|
|
|
82
80
|
|
|
83
81
|
contents = bs.find_all('div',class_='jobsearch-SerpJobCard')
|
|
84
82
|
|
|
85
|
-
|
|
86
83
|
|
|
87
|
-
_titles = ''
|
|
88
|
-
|
|
89
|
-
_messages = ''
|
|
90
|
-
|
|
91
|
-
_companys =''
|
|
92
|
-
|
|
93
|
-
_links = ''
|
|
94
|
-
|
|
95
|
-
_checkbox = []
|
|
96
|
-
|
|
97
|
-
|
|
98
84
|
|
|
99
85
|
for content in contents:
|
|
100
|
-
|
|
101
|
-
if content not in checkbox:
|
|
102
|
-
|
|
103
|
-
_checkbox.append(content)
|
|
104
86
|
|
|
105
87
|
title = content.find('div',class_='title').find('a')
|
|
106
88
|
|
|
@@ -124,30 +106,24 @@
|
|
|
124
106
|
|
|
125
107
|
links.append(link)
|
|
126
108
|
|
|
109
|
+
|
|
127
110
|
|
|
128
|
-
|
|
129
|
-
checkbox.append(_checkbox )
|
|
130
|
-
|
|
131
|
-
titles.append(_titles)
|
|
132
|
-
|
|
133
|
-
messages.append(_messages)
|
|
134
|
-
|
|
135
|
-
|
|
111
|
+
return titles,messages,companys,links
|
|
136
|
-
|
|
137
|
-
links.append(_links)
|
|
138
112
|
|
|
139
113
|
|
|
140
114
|
|
|
115
|
+
def job_printer(word,live,pages):
|
|
116
|
+
|
|
141
|
-
|
|
117
|
+
titles,messages,companys,links = job_search(word,live,pages)
|
|
118
|
+
|
|
119
|
+
print('\n\n')
|
|
120
|
+
|
|
121
|
+
print('{}社見つかりました。\n\n 検索ワード:{}\t所在市:{}\tページ数:{}'.format(len(companys),word,live,pages))
|
|
122
|
+
|
|
123
|
+
for i in range(len(messages)):
|
|
124
|
+
|
|
125
|
+
print(titles[i],'\n',messages[i],'\n',companys[i],'\n',links[i])
|
|
126
|
+
|
|
127
|
+
print('\n\n')
|
|
142
128
|
|
|
143
129
|
```
|
|
144
|
-
|
|
145
|
-
|
|
146
|
-
|
|
147
|
-
#試した解決方法
|
|
148
|
-
|
|
149
|
-
|
|
150
|
-
|
|
151
|
-
checkboxというリストに全て入れて、重複していたら処理を行わないように自分なりに書いてみたのですがErrorは起きませんが、リストの要素は重複しています。
|
|
152
|
-
|
|
153
|
-
改善した方が良いところなどもあれば教えていただきたいです。
|
1
codeの修正
test
CHANGED
|
@@ -1 +1 @@
|
|
|
1
|
-
|
|
1
|
+
listに重複が無いように追加していきたい。
|
test
CHANGED
|
File without changes
|