回答編集履歴
4
編集上の修正
answer
CHANGED
|
@@ -37,10 +37,10 @@
|
|
|
37
37
|
print("スキップ(GIF)")
|
|
38
38
|
else:
|
|
39
39
|
img = cv2.imread('/Users/username/banggood/u' + x)
|
|
40
|
-
print(img.shape)
|
|
40
|
+
# print(img.shape)
|
|
41
41
|
img2 = cv2.resize(img, dsize=None, fx=0.5, fy=0.5)
|
|
42
42
|
cv2.imwrite('/ Users/username/banggood/u' + x, img2)
|
|
43
|
-
print("保存(GIF以外) パス:",x)
|
|
43
|
+
print("保存(GIF以外) パス:",x, "shape",img.shape)
|
|
44
44
|
|
|
45
45
|
except urllib.error.HTTPError:
|
|
46
46
|
print("スキップ(HTTPエラー)")
|
3
変更4回目
answer
CHANGED
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
2回目＋3回目(エラー通知の変更）
|
|
1
|
+
2回目＋3回目(エラー通知の変更）+ 4回目(全条件のトレース）
|
|
2
2
|
---
|
|
3
3
|
```Python
|
|
4
4
|
import sys
|
|
@@ -14,7 +14,7 @@
|
|
|
14
14
|
headers = {
|
|
15
15
|
"User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:47.0) Gecko/20100101 Firefox/47.0"}
|
|
16
16
|
for column_name, item in df.iteritems():
|
|
17
|
-
|
|
17
|
+
print("捜査中 カラム",column_name,"アイテム",item ,"...",end="")
|
|
18
18
|
if column_name == 'url' or '_1' or '_2' or '_3' or '_4' or '_5' or '_6' or '_7' or '_8' or '_9':
|
|
19
19
|
for index, row in df.iterrows():
|
|
20
20
|
|
|
@@ -31,43 +31,35 @@
|
|
|
31
31
|
x = row['code'] + column_name.replace('URL', '') + ".jpeg"
|
|
32
32
|
with open('/Users/username/banggood/u/' + x, mode="wb") as f:
|
|
33
33
|
f.write(mem)
|
|
34
|
-
print(x)
|
|
34
|
+
# print(x)
|
|
35
35
|
|
|
36
36
|
if url_extension == ".gif":
|
|
37
|
-
print("
|
|
37
|
+
print("スキップ(GIF)")
|
|
38
38
|
else:
|
|
39
39
|
img = cv2.imread('/Users/username/banggood/u' + x)
|
|
40
40
|
print(img.shape)
|
|
41
41
|
img2 = cv2.resize(img, dsize=None, fx=0.5, fy=0.5)
|
|
42
|
-
cv2.imwrite(
|
|
43
|
-
|
|
42
|
+
cv2.imwrite('/ Users/username/banggood/u' + x, img2)
|
|
43
|
+
print("保存(GIF以外) パス:",x)
|
|
44
44
|
|
|
45
45
|
except urllib.error.HTTPError:
|
|
46
|
-
# print("エラー")
|
|
47
|
-
print("
|
|
46
|
+
print("スキップ(HTTPエラー)")
|
|
48
|
-
traceback.print_exc()
|
|
47
|
+
# traceback.print_exc()
|
|
49
48
|
except Exception as err:
|
|
50
|
-
print("
|
|
49
|
+
print("スキップ(HTTP以外のエラー)")
|
|
51
|
-
traceback.print_exc()
|
|
50
|
+
# traceback.print_exc()
|
|
52
51
|
time.sleep(1)
|
|
53
52
|
|
|
54
53
|
except Exception as err:
|
|
55
|
-
print("!!! URL 関連のエラー")
|
|
56
|
-
print("CSVに定義されている元の
|
|
54
|
+
print("スキップ(URLエラー) CSVに定義されている元のデータ[" + row[column_name] + ,url_extension + "]に問題があるようです。")
|
|
57
|
-
# print("ROW", row[column_name])
|
|
58
|
-
# print("EXT", url_extension )
|
|
59
55
|
|
|
60
|
-
# traceback.print_exc()
|
|
61
|
-
# except AttributeError as error:
|
|
62
|
-
# print()
|
|
63
|
-
# except ValueError as error:
|
|
64
|
-
# print()
|
|
65
56
|
else:
|
|
66
|
-
print()
|
|
57
|
+
print("スキップ 対象外のカラム名です。")
|
|
67
58
|
|
|
68
|
-
f.close()
|
|
69
59
|
print("正常に終了しました。")
|
|
70
60
|
|
|
61
|
+
# f.close() # <---with ○○ as fのため不要
|
|
62
|
+
|
|
71
63
|
```
|
|
72
64
|
|
|
73
65
|
|
2
編集3回目エラー通知の変更
answer
CHANGED
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
2回目
|
|
1
|
+
2回目＋3回目(エラー通知の変更）
|
|
2
2
|
---
|
|
3
3
|
```Python
|
|
4
4
|
import sys
|
|
@@ -53,7 +53,11 @@
|
|
|
53
53
|
|
|
54
54
|
except Exception as err:
|
|
55
55
|
print("!!! URL 関連のエラー")
|
|
56
|
+
print("CSVに定義されている元のURL[" + row[column_name] + "]に問題があるようです。スキップします。")
|
|
57
|
+
# print("ROW", row[column_name])
|
|
58
|
+
# print("EXT", url_extension )
|
|
59
|
+
|
|
56
|
-
traceback.print_exc()
|
|
60
|
+
# traceback.print_exc()
|
|
57
61
|
# except AttributeError as error:
|
|
58
62
|
# print()
|
|
59
63
|
# except ValueError as error:
|
|
@@ -62,6 +66,8 @@
|
|
|
62
66
|
print()
|
|
63
67
|
|
|
64
68
|
f.close()
|
|
69
|
+
print("正常に終了しました。")
|
|
70
|
+
|
|
65
71
|
```
|
|
66
72
|
|
|
67
73
|
|
1
修正案を提示
answer
CHANGED
|
@@ -1,4 +1,73 @@
|
|
|
1
|
+
2回目
|
|
2
|
+
---
|
|
1
3
|
```Python
|
|
4
|
+
import sys
|
|
5
|
+
import time
|
|
6
|
+
import os
|
|
7
|
+
import pandas as pd
|
|
8
|
+
import cv2
|
|
9
|
+
import traceback # エラーが出た際にエラーが起きた旨の通知用に追加
|
|
10
|
+
|
|
11
|
+
|
|
12
|
+
df = pd.read_csv('/Users/username/banggood/img_ban.csv', encoding='cp932', dtype=object)
|
|
13
|
+
|
|
14
|
+
headers = {
|
|
15
|
+
"User-Agent": "Mozilla/5.0 (X11; Ubuntu; Linux x86_64; rv:47.0) Gecko/20100101 Firefox/47.0"}
|
|
16
|
+
for column_name, item in df.iteritems():
|
|
17
|
+
|
|
18
|
+
if column_name == 'url' or '_1' or '_2' or '_3' or '_4' or '_5' or '_6' or '_7' or '_8' or '_9':
|
|
19
|
+
for index, row in df.iterrows():
|
|
20
|
+
|
|
21
|
+
try:
|
|
22
|
+
url_separate = os.path.splitext(row[column_name])
|
|
23
|
+
url_extension = url_separate[1].replace('URL', '')
|
|
24
|
+
url_extension = url_extension.replace('#username', '')
|
|
25
|
+
|
|
26
|
+
request = urllib.request.Request(
|
|
27
|
+
row[column_name], headers=headers)
|
|
28
|
+
try:
|
|
29
|
+
mem = urllib.request.urlopen(request).read()
|
|
30
|
+
|
|
31
|
+
x = row['code'] + column_name.replace('URL', '') + ".jpeg"
|
|
32
|
+
with open('/Users/username/banggood/u/' + x, mode="wb") as f:
|
|
33
|
+
f.write(mem)
|
|
34
|
+
print(x)
|
|
35
|
+
|
|
36
|
+
if url_extension == ".gif":
|
|
37
|
+
print("!!!gif!!!")
|
|
38
|
+
else:
|
|
39
|
+
img = cv2.imread('/Users/username/banggood/u' + x)
|
|
40
|
+
print(img.shape)
|
|
41
|
+
img2 = cv2.resize(img, dsize=None, fx=0.5, fy=0.5)
|
|
42
|
+
cv2.imwrite(
|
|
43
|
+
'/ Users/username/banggood/u' + x, img2)
|
|
44
|
+
|
|
45
|
+
except urllib.error.HTTPError:
|
|
46
|
+
# print("エラー")
|
|
47
|
+
print("!!! HTTP エラー")
|
|
48
|
+
traceback.print_exc()
|
|
49
|
+
except Exception as err:
|
|
50
|
+
print("!!! HTTP エラー以外のエラー")
|
|
51
|
+
traceback.print_exc()
|
|
52
|
+
time.sleep(1)
|
|
53
|
+
|
|
54
|
+
except Exception as err:
|
|
55
|
+
print("!!! URL 関連のエラー")
|
|
56
|
+
traceback.print_exc()
|
|
57
|
+
# except AttributeError as error:
|
|
58
|
+
# print()
|
|
59
|
+
# except ValueError as error:
|
|
60
|
+
# print()
|
|
61
|
+
else:
|
|
62
|
+
print()
|
|
63
|
+
|
|
64
|
+
f.close()
|
|
65
|
+
```
|
|
66
|
+
|
|
67
|
+
|
|
68
|
+
初回分
|
|
69
|
+
---
|
|
70
|
+
```Python
|
|
2
71
|
try:
|
|
3
72
|
except:
|
|
4
73
|
```
|