質問編集履歴
2
タグ文字を削除して半角スペース文字4つをインデントにして浄書いたしました。
test
CHANGED
File without changes
|
test
CHANGED
@@ -24,9 +24,13 @@
|
|
24
24
|
|
25
25
|
Traceback (most recent call last):
|
26
26
|
|
27
|
-
File "C:\Users\satoru\horse\kami-2.py", line 4
|
27
|
+
File "C:\Users\satoru\horse\kami-2.py", line 46, in <module>
|
28
28
|
|
29
|
-
print j_name,race_date,
|
29
|
+
print jockey_name,race_date,kaisai,weather,race_name,tousuu,frame_number,horse_number,single_win
|
30
|
+
|
31
|
+
_racio,popularity,horse_arrival,horse_name,weight,distance,baba,race_time,difference,horse_pass,pace
|
32
|
+
|
33
|
+
,nobori,horse_weight,win_horse
|
30
34
|
|
31
35
|
UnicodeEncodeError: 'cp932' codec can't encode character u'\xa0' in position 4: illegal multibyte se
|
32
36
|
|
@@ -52,7 +56,7 @@
|
|
52
56
|
|
53
57
|
from bs4 import BeautifulSoup
|
54
58
|
|
55
|
-
f = codecs.open('horse.csv',
|
59
|
+
f = codecs.open('horse.csv','w','utf-8')
|
56
60
|
|
57
61
|
f.write('jockey_name,race_date,kaisai,weather,race_number,race_name,tousuu,frame_number,horse_number,single_win_ratio,popularity,horse_arrival,horse_name,weight,distance,baba, race_time,difference,horse_pass,pace,nobori,horse_weight,win_horse'+ u"\n")
|
58
62
|
|
@@ -62,99 +66,83 @@
|
|
62
66
|
|
63
67
|
|
64
68
|
|
65
|
-
for i in xrange(1,
|
69
|
+
for i in xrange(1,2):
|
66
70
|
|
67
|
-
|
71
|
+
url=tpl_url.format( i )
|
68
72
|
|
69
|
-
|
73
|
+
soup = BeautifulSoup(urllib2.urlopen(url).read(),"lxml")
|
70
74
|
|
71
75
|
|
72
76
|
|
73
|
-
j_name = soup.find('div',
|
77
|
+
jockey_name = soup.find('div',{'class':'db_head_name'}).find('h1').text.replace("\n","")
|
74
|
-
|
75
|
-
|
76
|
-
|
77
|
-
tr_arr = soup.select("table.race_table_01 > tbody > tr")
|
78
|
-
|
79
|
-
|
80
|
-
|
81
|
-
for tr in tr_arr:
|
82
|
-
|
83
|
-
|
84
|
-
|
85
|
-
tds = tr.findAll("td")
|
86
|
-
|
87
|
-
time.sleep(1)
|
88
|
-
|
89
|
-
race_date = tds[0].a.text #日付
|
90
|
-
|
91
|
-
kaisai = tds[1].a.text #開催
|
92
|
-
|
93
|
-
weather=tds[2].text #天気
|
94
|
-
|
95
|
-
race_number=tds[3].text #R
|
96
|
-
|
97
|
-
race_name=tds[4].a.text #レース名
|
98
|
-
|
99
|
-
tousuu=tds[6].text #頭数
|
100
|
-
|
101
|
-
frame_number=tds[7].text #枠番
|
102
|
-
|
103
|
-
horse_number=tds[8].text #馬番
|
104
|
-
|
105
|
-
single_win_racio=tds[9].text #単勝
|
106
|
-
|
107
|
-
popularity=tds[10].text #人気
|
108
|
-
|
109
|
-
horse_arrival=tds[11].text #着順
|
110
|
-
|
111
|
-
horse_name=tds[12].a.text #馬名
|
112
|
-
|
113
|
-
weight=tds[13].text #斤量
|
114
|
-
|
115
|
-
distance=tds[14].text #距離
|
116
|
-
|
117
|
-
baba=tds[15].text #馬場
|
118
|
-
|
119
|
-
race_time=tds[16].text #タイム
|
120
|
-
|
121
|
-
difference=tds[17].text #着差
|
122
|
-
|
123
|
-
horse_pass=tds[18].text #通過
|
124
|
-
|
125
|
-
pace=tds[19].text #ペース
|
126
|
-
|
127
|
-
nobori=tds[20].text #上り
|
128
|
-
|
129
|
-
horse_weight=tds[21].text #馬体重
|
130
|
-
|
131
|
-
win_horse=tds[22].a.text #勝ち馬
|
132
|
-
|
133
|
-
|
134
|
-
|
135
|
-
print j_name,race_date, kaisai,weather,race_name,tousuu,frame_number,horse_number,\
|
136
|
-
|
137
|
-
single_win_racio,popularity,horse_arrival,horse_name,weight,distance,baba,\
|
138
|
-
|
139
|
-
race_time,difference,horse_pass,pace,nobori,horse_weight,win_horse
|
140
78
|
|
141
79
|
|
142
80
|
|
143
|
-
|
81
|
+
tr_arr = soup.select("table.race_table_01>tbody>tr")
|
144
82
|
|
145
|
-
|
83
|
+
for tr in tr_arr:
|
146
84
|
|
147
|
-
|
85
|
+
tds = tr.findAll("td")
|
148
86
|
|
149
|
-
|
87
|
+
time.sleep(1)
|
150
88
|
|
151
|
-
|
89
|
+
race_date = tds[0].a.text #日付
|
152
90
|
|
153
|
-
|
91
|
+
kaisai = tds[1].a.text #開催
|
154
92
|
|
155
|
-
|
93
|
+
weather=tds[2].text #天気
|
156
94
|
|
157
|
-
|
95
|
+
race_number=tds[3].text #R
|
96
|
+
|
97
|
+
race_name=tds[4].a.text #レース名
|
98
|
+
|
99
|
+
tousuu=tds[6].text #頭数
|
100
|
+
|
101
|
+
frame_number=tds[7].text #枠番
|
102
|
+
|
103
|
+
horse_number=tds[8].text #馬番
|
104
|
+
|
105
|
+
single_win_racio=tds[9].text #単勝
|
106
|
+
|
107
|
+
popularity=tds[10].text #人気
|
108
|
+
|
109
|
+
horse_arrival=tds[11].text #着順
|
110
|
+
|
111
|
+
horse_name=tds[12].a.text #馬名
|
112
|
+
|
113
|
+
weight=tds[13].text #斤量
|
114
|
+
|
115
|
+
distance=tds[14].text #距離
|
116
|
+
|
117
|
+
baba=tds[15].text #馬場
|
118
|
+
|
119
|
+
race_time=tds[16].text #タイム
|
120
|
+
|
121
|
+
difference=tds[17].text #着差
|
122
|
+
|
123
|
+
horse_pass=tds[18].text #通過
|
124
|
+
|
125
|
+
pace=tds[19].text #ペース
|
126
|
+
|
127
|
+
nobori=tds[20].text #上り
|
128
|
+
|
129
|
+
horse_weight=tds[21].text #馬体重
|
130
|
+
|
131
|
+
win_horse=tds[22].a.text #勝ち馬
|
132
|
+
|
133
|
+
|
134
|
+
|
135
|
+
print jockey_name,race_date,kaisai,weather,race_name,tousuu,frame_number,horse_number,single_win_racio,popularity,horse_arrival,horse_name,weight,distance,baba,race_time,difference,horse_pass,pace,nobori,horse_weight,win_horse
|
136
|
+
|
137
|
+
|
138
|
+
|
139
|
+
cols = [jockey_name,race_date,kaisai,weather,race_number,race_name,tousuu,frame_number,horse_number,single_win_racio,popularity,horse_arrival,horse_name,weight,distance,baba,race_time,difference,horse_pass,pace,nobori,horse_weight,win_horse]
|
140
|
+
|
141
|
+
|
142
|
+
|
143
|
+
f.write(",".join(cols) + "\n")
|
144
|
+
|
145
|
+
|
158
146
|
|
159
147
|
f.close()
|
160
148
|
|
1
エラーメッセージの更新、ソースコードの訂正、インデントの訂正(しかしながらうまく貼り付けることが出来ませんでした、申し訳ございません。)タグの訂正
test
CHANGED
File without changes
|
test
CHANGED
@@ -20,23 +20,17 @@
|
|
20
20
|
|
21
21
|
```
|
22
22
|
|
23
|
-
<h1>
|
24
|
-
|
25
|
-
陋ッ蜷肴ュ」鄒ゥツ
|
26
|
-
|
27
|
-
(繧ィ繝薙リ繝槭し繝ィ繧キ)
|
28
|
-
|
29
|
-
</h1> 2016/08/07 2新潟4 晴 3歳上500万下 15 7 13 6.9 3 2 チェイスダウン 54 ダ1200 良 1:11.9 0.3 8-8 3
|
30
|
-
|
31
|
-
|
23
|
+
C:\Users\satoru\horse>kami-2.py
|
32
24
|
|
33
25
|
Traceback (most recent call last):
|
34
26
|
|
35
|
-
File "C:\Users\satoru\horse\kami-2.py", line
|
27
|
+
File "C:\Users\satoru\horse\kami-2.py", line 48, in <module>
|
36
28
|
|
37
|
-
|
29
|
+
print j_name,race_date, kaisai,weather,race_name,tousuu,frame_number,horse_number,\
|
38
30
|
|
39
|
-
|
31
|
+
UnicodeEncodeError: 'cp932' codec can't encode character u'\xa0' in position 4: illegal multibyte se
|
32
|
+
|
33
|
+
quence
|
40
34
|
|
41
35
|
```
|
42
36
|
|
@@ -76,7 +70,7 @@
|
|
76
70
|
|
77
71
|
|
78
72
|
|
79
|
-
j_name = soup.find('div', {'class':'db_head_name'}).find('h1')
|
73
|
+
j_name = soup.find('div', {'class':'db_head_name'}).find('h1').text.replace("\n", "")
|
80
74
|
|
81
75
|
|
82
76
|
|
@@ -88,69 +82,69 @@
|
|
88
82
|
|
89
83
|
|
90
84
|
|
91
|
-
|
85
|
+
tds = tr.findAll("td")
|
92
86
|
|
93
|
-
|
87
|
+
time.sleep(1)
|
94
88
|
|
95
|
-
|
89
|
+
race_date = tds[0].a.text #日付
|
96
90
|
|
97
|
-
|
91
|
+
kaisai = tds[1].a.text #開催
|
98
92
|
|
99
|
-
|
93
|
+
weather=tds[2].text #天気
|
100
94
|
|
101
|
-
|
95
|
+
race_number=tds[3].text #R
|
102
96
|
|
103
|
-
|
97
|
+
race_name=tds[4].a.text #レース名
|
104
98
|
|
105
|
-
|
99
|
+
tousuu=tds[6].text #頭数
|
106
100
|
|
107
|
-
|
101
|
+
frame_number=tds[7].text #枠番
|
108
102
|
|
109
|
-
|
103
|
+
horse_number=tds[8].text #馬番
|
110
104
|
|
111
|
-
|
105
|
+
single_win_racio=tds[9].text #単勝
|
112
106
|
|
113
|
-
|
107
|
+
popularity=tds[10].text #人気
|
114
108
|
|
115
|
-
|
109
|
+
horse_arrival=tds[11].text #着順
|
116
110
|
|
117
|
-
|
111
|
+
horse_name=tds[12].a.text #馬名
|
118
112
|
|
119
|
-
|
113
|
+
weight=tds[13].text #斤量
|
120
114
|
|
121
|
-
|
115
|
+
distance=tds[14].text #距離
|
122
116
|
|
123
|
-
|
117
|
+
baba=tds[15].text #馬場
|
124
118
|
|
125
|
-
|
119
|
+
race_time=tds[16].text #タイム
|
126
120
|
|
127
|
-
|
121
|
+
difference=tds[17].text #着差
|
128
122
|
|
129
|
-
|
123
|
+
horse_pass=tds[18].text #通過
|
130
124
|
|
131
|
-
|
125
|
+
pace=tds[19].text #ペース
|
132
126
|
|
133
|
-
|
127
|
+
nobori=tds[20].text #上り
|
134
128
|
|
135
|
-
|
129
|
+
horse_weight=tds[21].text #馬体重
|
136
130
|
|
137
|
-
|
131
|
+
win_horse=tds[22].a.text #勝ち馬
|
138
132
|
|
139
133
|
|
140
134
|
|
141
|
-
|
135
|
+
print j_name,race_date, kaisai,weather,race_name,tousuu,frame_number,horse_number,\
|
142
136
|
|
143
|
-
|
137
|
+
single_win_racio,popularity,horse_arrival,horse_name,weight,distance,baba,\
|
144
138
|
|
145
|
-
|
139
|
+
race_time,difference,horse_pass,pace,nobori,horse_weight,win_horse
|
146
140
|
|
147
141
|
|
148
142
|
|
149
|
-
|
143
|
+
cols = [j_name,race_date, kaisai,weather,race_number,race_name,tousuu,frame_number,\
|
150
144
|
|
151
|
-
|
145
|
+
horse_number,single_win_racio,popularity,horse_arrival,horse_name,weight,\
|
152
146
|
|
153
|
-
|
147
|
+
distance,baba,race_time,difference,horse_pass,pace,nobori,horse_weight,win_horse]
|
154
148
|
|
155
149
|
|
156
150
|
|
@@ -158,7 +152,7 @@
|
|
158
152
|
|
159
153
|
|
160
154
|
|
161
|
-
|
155
|
+
f.write(",".join(cols) + "\n")
|
162
156
|
|
163
157
|
|
164
158
|
|