simplejson.scanner.JSONDecodeError: Invalid \X escape sequence u's': line 1 column 468 (char 467)

simplejson.scanner.JSONDecodeError: Invalid \X escape sequence u's': line 1 column 468 (char 467)

我在向 REST api 发出 HTTP 请求时遇到问题,我的 JSON 格式的响应格式不正确。 JSON 中的转义序列被正确解释,但随后有一个特定的句子包含单词 "inner\spiritual",使 JSON 解码器认为“\s”是转义顺序,当它不应该是。

通过 Whosebug 文章搜索,我找不到适合我的精确用例的解决方案,但我想出了一个很好的 hack 使用异常和索引 JSON 字符串并进行简单替换。我认为值得分享,因为它可能会帮助处于类似情况的人。快乐黑客:)

完整代码:

import requests
import os
import json

base_url = 'http://www.omdbapi.com/'
tv_series = {}
films = {}

#for i in range(1, 9999999):
#imdb_id = 'tt' + str(i).zfill(7)
imdb_id = 'tt0120690'
print imdb_id



payload = {
            'i':imdb_id,
            'plot':'full',
            'r':'json'      
}
response = requests.get(base_url, params=payload)
if response.status_code == 200:     
    result = None
    result = response.json()

    if result != None:
        if result['Response'] != 'False':
            if result['Type'] == 'movie':
                films[result['Title']] = result
            elif result['Type'] == 'series':
                tv_series[result['Title']] = result
            else:
                print '[ERROR] Type:', result['Type']
with open('tv_series.json', 'w') as tv_series_outfile:
    json.dump(tv_series, tv_series_outfile)

with open('films.json', 'w') as films_outfile:
    json.dump(films, films_outfile)

错误:

Traceback (most recent call last):
  File "import_imdb.py", line 41, in <module>
    result = response.json()
  File "C:\Python27\lib\site-packages\requests\models.py", line 797, in json
    return json.loads(self.text, **kwargs)
  File "C:\Python27\lib\site-packages\simplejson\__init__.py", line 516, in loads
    return _default_decoder.decode(s)
  File "C:\Python27\lib\site-packages\simplejson\decoder.py", line 370, in decode
    obj, end = self.raw_decode(s)
  File "C:\Python27\lib\site-packages\simplejson\decoder.py", line 400, in raw_decode
    return self.scan_once(s, idx=_w(s, idx).end())
  File "C:\Python27\lib\site-packages\simplejson\scanner.py", line 127, in scan_once
    return _scan_once(string, idx)
  File "C:\Python27\lib\site-packages\simplejson\scanner.py", line 93, in _scan_once
    _scan_once, object_hook, object_pairs_hook, memo)
  File "C:\Python27\lib\site-packages\simplejson\decoder.py", line 194, in JSONObject
    value, end = scan_once(s, end)
  File "C:\Python27\lib\site-packages\simplejson\scanner.py", line 90, in _scan_once
    return parse_string(string, idx + 1, encoding, strict)
  File "C:\Python27\lib\site-packages\simplejson\decoder.py", line 99, in py_scanstring
    raise JSONDecodeError(msg, s, end)
simplejson.scanner.JSONDecodeError: Invalid \X escape sequence u's': line 1 column 468 (char 467)

我的修复:

def fix_JSON(json_message=None):
    result = None
    try:        
        result = json.loads(json_message)
    except Exception as e:      
        # Find the offending character index:
        idx_to_replace = int(e.message.split(' ')[-1].replace(')',''))      
        # Remove the offending character:
        json_message = list(json_message)
        json_message[idx_to_replace] = ' '
        new_message = ''.join(json_message)     
        return fix_JSON(json_message=new_message)
    return result

完整代码:

import requests
import os
import json


def fix_JSON(json_message=None):
    result = None
    try:        
        result = json.loads(json_message)
    except Exception as e:      
        # Find the offending character index:
        idx_to_replace = int(e.message.split(' ')[-1].replace(')',''))      
        # Remove the offending character:
        json_message = list(json_message)
        json_message[idx_to_replace] = ' '
        new_message = ''.join(json_message)     
        return fix_JSON(json_message=new_message)
    return result


base_url = 'http://www.omdbapi.com/'
tv_series = {}
films = {}
for i in range(1, 9999999):
    imdb_id = 'tt' + str(i).zfill(7)
    #imdb_id = 'tt0120690'
    print imdb_id



    payload = {
                'i':imdb_id,
                'plot':'full',
                'r':'json'      
    }
    response = requests.get(base_url, params=payload)
    if response.status_code == 200:     
        result = None
        result = fix_JSON(json_message=response.content)

        if result != None:
            if result['Response'] != 'False':
                if result['Type'] == 'movie':
                    films[result['Title']] = result
                elif result['Type'] == 'series':
                    tv_series[result['Title']] = result
                else:
                    print '[ERROR] Type:', result['Type']
with open('tv_series.json', 'w') as tv_series_outfile:
    json.dump(tv_series, tv_series_outfile)

with open('films.json', 'w') as films_outfile:
    json.dump(films, films_outfile)