回答編集履歴
2
修正
test
CHANGED
|
@@ -18,7 +18,7 @@
|
|
|
18
18
|
|
|
19
19
|
--
|
|
20
20
|
|
|
21
|
-
提示されたデータとコード片でも`Win10,Python3.6.7,コマンドプロンプト`環境にて`print`できました。
|
|
21
|
+
提示されたデータとコード片でも`Win10,Python3.6.7,コマンドプロンプト`環境にて`print`できました。また、ファイル出力結果も正常です。
|
|
22
22
|
|
|
23
23
|
```Python
|
|
24
24
|
|
|
@@ -94,6 +94,18 @@
|
|
|
94
94
|
|
|
95
95
|
comment = comment.encode('utf-16', 'surrogatepass').decode('utf-16')
|
|
96
96
|
|
|
97
|
+
|
|
98
|
+
|
|
99
|
+
# ファイルに出力
|
|
100
|
+
|
|
101
|
+
with open('ret.txt', 'w', encoding='utf-16') as f:
|
|
102
|
+
|
|
103
|
+
f.write(comment)
|
|
104
|
+
|
|
105
|
+
|
|
106
|
+
|
|
97
107
|
print(comment) # 長崎出身です????
|
|
98
108
|
|
|
99
109
|
```
|
|
110
|
+
|
|
111
|
+
|
1
追記
test
CHANGED
|
@@ -11,3 +11,89 @@
|
|
|
11
11
|
print(s) # 長崎出身です????
|
|
12
12
|
|
|
13
13
|
```
|
|
14
|
+
|
|
15
|
+
|
|
16
|
+
|
|
17
|
+
追記
|
|
18
|
+
|
|
19
|
+
--
|
|
20
|
+
|
|
21
|
+
提示されたデータとコード片でも`Win10,Python3.6.7,コマンドプロンプト`環境にて`print`できました。
|
|
22
|
+
|
|
23
|
+
```Python
|
|
24
|
+
|
|
25
|
+
import re
|
|
26
|
+
|
|
27
|
+
|
|
28
|
+
|
|
29
|
+
page_source = """window.content_Data_k = {
|
|
30
|
+
|
|
31
|
+
"config": {
|
|
32
|
+
|
|
33
|
+
"token": "dsf78sadf9sdfasd7s9df7safd6",
|
|
34
|
+
|
|
35
|
+
"seer": null,
|
|
36
|
+
|
|
37
|
+
"seerId": null
|
|
38
|
+
|
|
39
|
+
},
|
|
40
|
+
|
|
41
|
+
"country_code": "JP",
|
|
42
|
+
|
|
43
|
+
"language_code": "ja",
|
|
44
|
+
|
|
45
|
+
"locale": "ja_JP",
|
|
46
|
+
|
|
47
|
+
"index_data": {
|
|
48
|
+
|
|
49
|
+
"contentPage": [{
|
|
50
|
+
|
|
51
|
+
"logging_page_id": "contentPage_728394298",
|
|
52
|
+
|
|
53
|
+
"show_suggested_contents": false,
|
|
54
|
+
|
|
55
|
+
"graphql": {
|
|
56
|
+
|
|
57
|
+
"user": {
|
|
58
|
+
|
|
59
|
+
"name": "aaa",
|
|
60
|
+
|
|
61
|
+
"comment":"\u9577\u5d0e\u51fa\u8eab\u3067\u3059\ud83d\udd4a",
|
|
62
|
+
|
|
63
|
+
"block": false,
|
|
64
|
+
|
|
65
|
+
"country_block": false,
|
|
66
|
+
|
|
67
|
+
"expect_url": null,
|
|
68
|
+
|
|
69
|
+
"expect_url_linkshimmed": null,
|
|
70
|
+
|
|
71
|
+
"key_number": {
|
|
72
|
+
|
|
73
|
+
"count": 13
|
|
74
|
+
|
|
75
|
+
}
|
|
76
|
+
|
|
77
|
+
}
|
|
78
|
+
|
|
79
|
+
}
|
|
80
|
+
|
|
81
|
+
}]
|
|
82
|
+
|
|
83
|
+
}
|
|
84
|
+
|
|
85
|
+
}"""
|
|
86
|
+
|
|
87
|
+
|
|
88
|
+
|
|
89
|
+
comment = re.search(r'"comment"\s*:\s*"([^"]*)"',page_source).group(1)
|
|
90
|
+
|
|
91
|
+
#print(comment) # UnicodeEncodeError: 'utf-8' codec can't encode characters in position 6-7: surrogates not allowed
|
|
92
|
+
|
|
93
|
+
|
|
94
|
+
|
|
95
|
+
comment = comment.encode('utf-16', 'surrogatepass').decode('utf-16')
|
|
96
|
+
|
|
97
|
+
print(comment) # 長崎出身です????
|
|
98
|
+
|
|
99
|
+
```
|