回答編集履歴
3
追記
answer
CHANGED
|
@@ -65,13 +65,13 @@
|
|
|
65
65
|
f_salarys = browser.find_elements_by_id('ctl00_ContentPlaceHolder1_lblIncomeIcon')
|
|
66
66
|
for f_salary in f_salarys:
|
|
67
67
|
_mix = f_salary.text
|
|
68
|
-
|
|
68
|
+
f_salary_mix[n] = _mix
|
|
69
69
|
|
|
70
70
|
#勤務地
|
|
71
71
|
areas = browser.find_elements_by_id('ctl00_ContentPlaceHolder1_lblWorkLocateIcon')
|
|
72
72
|
for area in areas:
|
|
73
73
|
_mix = area.text
|
|
74
|
-
|
|
74
|
+
area_mix[n] = _mix
|
|
75
75
|
|
|
76
76
|
|
|
77
77
|
#従業員数
|
|
@@ -79,19 +79,19 @@
|
|
|
79
79
|
if not len(staffs) == len(c_names):
|
|
80
80
|
for staff in staffs:
|
|
81
81
|
_mix = staff.text
|
|
82
|
-
|
|
82
|
+
staff_mix[n] = _mix
|
|
83
83
|
|
|
84
84
|
#本社所在地
|
|
85
85
|
c_addresses = browser.find_elements_by_id('ctl00_ContentPlaceHolder1_lblHeadofficelocation')
|
|
86
86
|
for c_address in c_addresses:
|
|
87
87
|
_mix = c_address.text
|
|
88
|
-
|
|
88
|
+
c_address_mix[n] = (_mix)
|
|
89
89
|
|
|
90
90
|
#HP
|
|
91
91
|
hps = browser.find_elements_by_id('ctl00_ContentPlaceHolder1_lblLink_Body1')
|
|
92
92
|
for hp in hps:
|
|
93
93
|
_mix = hp.text
|
|
94
|
-
|
|
94
|
+
hp_mix[n] = (_mix)
|
|
95
95
|
|
|
96
96
|
#連絡先
|
|
97
97
|
pattern = r'[(]{0,1}[0-9]{2,4}[)\-(]{0,1}[0-9]{2,4}[)\-]{0,1}[0-9]{3,4}'
|
|
@@ -101,7 +101,7 @@
|
|
|
101
101
|
#regex = re.compile(pattern, flags=0)
|
|
102
102
|
#mo = regex.search(_mix)
|
|
103
103
|
#mo.group()
|
|
104
|
-
|
|
104
|
+
info_mix[n] = (_mix)
|
|
105
105
|
|
|
106
106
|
df = pd.DataFrame()
|
|
107
107
|
|
2
追記
answer
CHANGED
|
@@ -115,6 +115,8 @@
|
|
|
115
115
|
df['本社所在地'] = c_address_mix
|
|
116
116
|
df['HP'] = hp_mix
|
|
117
117
|
df['連絡先'] = info_mix
|
|
118
|
+
|
|
119
|
+
df = df.drop([0])
|
|
118
120
|
```
|
|
119
121
|
|
|
120
122
|
これで10行目にある
|
1
追記
answer
CHANGED
|
@@ -26,7 +26,7 @@
|
|
|
26
26
|
|
|
27
27
|
urls_num = len(list_urls)
|
|
28
28
|
|
|
29
|
-
empty_list = [[""] * urls_num
|
|
29
|
+
empty_list = [[""] * urls_num for i in range(10)]
|
|
30
30
|
industry_mix, up_mix,c_mix,occ_mix,f_salary_mix, area_mix,staff_mix,c_address_mix, hp_mix,info_mix = empty_list
|
|
31
31
|
|
|
32
32
|
|