0

我已经使用 xmltodict 将许多 xml 文件转换为 json 并将它们插入到 arangodb 中。现在我很好地遍历集合并更改数据库中的一些值。就像从字符串到 int 的 day、mount 和 year。文档可以非常嵌套，我更改的值可以在不同的地方。

这就是我所拥有的代码。

    # Get the API wrapper for "FORM16" collection.
FORM16 = db.collection('FORM16')
  
def recursive_items(dictionary):
    for key, value in dictionary.items():
        if type(value) is dict:
            yield from recursive_items(value)
        else:
            yield (key, value)
 
 
search_key = 'LOW_VALUE'
 
for item in FORM16:
    for key, value in recursive_items(item):
        if search_key in list(key):
            item[search_key] = int(item[search_key])
            
        else:
            pass 
       
FORM16.update(item) 


{'_id': 'FORM16/2098312',
 '_key': '2098312',
 '_rev': '_blGxlRi---',
 '_old_rev': '_blGvpVO---'}

代码运行但它不会更新数据库，并且我收到的已更改文档只是集合中的最后一个文档。我必须在代码中进行哪些更改才能将键中的值（如 day、mount 和 year）转换为 int？

编辑：这是嵌套 json 的文档之一。我很好更新

{
  "DOFFIN_ESENDERS": {
    "DOFFIN_APPENDIX": {
      "AUTHORITY_ORGANISATION_NR": "986 105 174",
      "DOFFIN_FORM_TYPE": {
        "NATIONAL": {
          "EXPRESSION_OF_INTEREST_URL": "https://kgv.doffin.no/ctm/Supplier/Notice/260549",
          "EXTERNAL_DOCUMENT_URL": "https://kgv.doffin.no/ctm/Supplier/Documents/Folder/124452",
          "LOCATION": {
            "NATIONWIDE": null
          },
          "PUBLISH_TO_TED": null
        }
      }
    },
    "FORM_SECTION": {
      "PRIOR_INFORMATION_DEFENCE": {
        "CATEGORY": "ORIGINAL",
        "FD_PRIOR_INFORMATION_DEFENCE": {
          "AUTHORITY_PRIOR_INFORMATION_DEFENCE": {
            "NAME_ADDRESSES_CONTACT_PRIOR_INFORMATION": {
              "CA_CE_CONCESSIONAIRE_PROFILE": {
                "ADDRESS": "Postboks 800, Postmottak",
                "ATTENTION": "Ole Jan Skoglund",
                "CONTACT_POINT": "Forsvarets logistikkorganisasjon",
                "COUNTRY": {
                  "VALUE": "NO"
                },
                "E_MAILS": {
                  "E_MAIL": "olskoglund@mil.no"
                },
                "FAX": "+47 67863799",
                "ORGANISATION": {
                  "NATIONALID": "986105174",
                  "OFFICIALNAME": "Forsvarets logistikkorganisasjon"
                },
                "PHONE": "+47 67863787",
                "POSTAL_CODE": "LILLEHAMMER",
                "TOWN": "N-2617"
              },
              "FURTHER_INFORMATION": {
                "IDEM": null
              },
              "INTERNET_ADDRESSES_PRIOR_INFORMATION": {
                "URL_BUYER": "https://kgv.doffin.no/ctm/Supplier/CompanyInformation/Index/1127",
                "URL_GENERAL": "http://www.forsvaret.no"
              }
            },
            "TYPE_AND_ACTIVITIES_OR_CONTRACTING_ENTITY_AND_PURCHASING_ON_BEHALF": {
              "PURCHASING_ON_BEHALF": {
                "PURCHASING_ON_BEHALF_NO": null
              },
              "TYPE_AND_ACTIVITIES": {
                "TYPE_OF_ACTIVITY": {
                  "VALUE": "DEFENCE"
                },
                "TYPE_OF_CONTRACTING_AUTHORITY": {
                  "VALUE": "MINISTRY"
                }
              }
            }
          },
          "CTYPE": "SUPPLIES",
          "LEFTI_PRIOR_INFORMATION": null,
          "OBJECT_WORKS_SUPPLIES_SERVICES_PRIOR_INFORMATION": {
            "ADDITIONAL_INFORMATION": {
              "P": "Konkurransen vil bli utført som en forhandlet prosedyre etter en planlagt kunngjøring ultimo 2015 i henhold til “Forskrift 4. oktober 2013 nr. 1185 om forsvars og sikkerhetsanskaffelser“ basert på Eu direktiv 2009/81/EC fra Europa Parlamentet."
            },
            "CPV": {
              "CPV_ADDITIONAL": [
                {
                  "CPV_CODE": {
                    "CODE": "18900000"
                  }
                },
                {
                  "CPV_CODE": {
                    "CODE": "18930000"
                  }
                },
                {
                  "CPV_CODE": {
                    "CODE": "18937000"
                  }
                },
                {
                  "CPV_CODE": {
                    "CODE": "33000000"
                  }
                },
                {
                  "CPV_CODE": {
                    "CODE": "33120000"
                  }
                },
                {
                  "CPV_CODE": {
                    "CODE": "33124000"
                  }
                },
                {
                  "CPV_CODE": {
                    "CODE": "33140000"
                  }
                },
                {
                  "CPV_CODE": {
                    "CODE": "33141000"
                  }
                },
                {
                  "CPV_CODE": {
                    "CODE": "33141100"
                  }
                },
                {
                  "CPV_CODE": {
                    "CODE": "33141200"
                  }
                },
                {
                  "CPV_CODE": {
                    "CODE": "33141300"
                  }
                },
                {
                  "CPV_CODE": {
                    "CODE": "50400000"
                  }
                }
              ],
              "CPV_MAIN": {
                "CPV_CODE": {
                  "CODE": "33100000"
                }
              }
            },
            "FRAMEWORK_AGREEMENT": {
              "VALUE": "YES"
            },
            "QUANTITY_SCOPE_WORKS_DEFENCE": {
              "COSTS_RANGE_AND_CURRENCY": {
                "CURRENCY": "NOK",
                "RANGE_VALUE_COST": {
                  "HIGH_VALUE": "200000000",
                  "LOW_VALUE": "150000000"
                }
              },
              "F16_DIVISION_INTO_LOTS": {
                "DIV_INTO_LOT_NO": null
              },
              "TOTAL_QUANTITY_OR_SCOPE": {
                "P": "Forsvarets logistikkorganisasjon planlegger å skifte ut Forsvarets prehospitale sanitetssystem. Vi ser derfor etter en systemleverandør som kan levere test moduler, store initielle systemleveranser og ta ansvar for effektiv etterforsyning til Forsvaret på rammeavtaler med inntil syv års varighet."
              }
            },
            "SCHEDULED_DATE_PERIOD": {
              "PERIOD_WORK_DATE_STARTING": {
                "MONTHS": "84"
              }
            },
            "TITLE_CONTRACT": {
              "P": "RFI P9346 -Nytt Prehospital Sanitetssystem  til Forsvaret"
            },
            "TYPE_CONTRACT_PLACE_DELIVERY_DEFENCE": {
              "SITE_OR_LOCATION": {
                "LABEL": "N-2055 Nordkisa",
                "NUTS": {
                  "CODE": "NO"
                }
              },
              "TYPE_CONTRACT_PI_DEFENCE": {
                "TYPE_CONTRACT": {
                  "VALUE": "SUPPLIES"
                }
              }
            }
          },
          "OTH_INFO_PRIOR_INFORMATION": {
            "ADDITIONAL_INFORMATION": {
              "P": "Vi ønsker svar både fra Systemleverandører og Underleverandører på denne RFI."
            },
            "INFORMATION_REGULATORY_FRAMEWORK": {
              "TAX_LEGISLATION": {
                "TAX_LEGISLATION_VALUE": "www.lovdata.no"
              }
            },
            "NOTICE_DISPATCH_DATE": {
              "DAY": "28",
              "MONTH": '11',
              "YEAR": "2014"
            },
            "RELATES_TO_EU_PROJECT_NO": null
          }
        },
        "FORM": "16",
        "LG": "NB",
        "VERSION": "R2.0.8.S02"
      }
    },
    "VERSION": "V2.0.0",
    "http://www.w3.org/2001/XMLSchema-instance:noNamespaceSchemaLocation": "DOFFIN_ESENDERS.xd",
    "xmlns": {
      "xsi": "http://www.w3.org/2001/XMLSchema-instance"
    }
  }
}
4

2 回答 2

0

看起来您的代码是正确的，假设底部的 JSON blob 是item. 只需确保您传递给的数据.update()包含有效_key和/或_id属性。

但是，看起来您的更新语句没有正确缩进和/或乱序。当您进行更改时，我会将更新内联：

FORM16 = db.collection('FORM16')
for item in FORM16:
    for key, value in recursive_items(item):
        if search_key in list(key):
            item[search_key] = int(item[search_key])
            FORM16.update(item)
        else:
            pass

或在顶级for循环中：

FORM16 = db.collection('FORM16')
for item in FORM16:
    for key, value in recursive_items(item):
        if search_key in list(key):
            item[search_key] = int(item[search_key])
        else:
            pass
    FORM16.update(item)
于 2020-12-18T18:16:51.423 回答
0

我确实找到了一个用于将 sting 转换为 int 并在 JSON 文件中浮动的函数。

def _decode(o):
    # Note the "unicode" part is only for python2
    if isinstance(o, str):
        try:
            return int(o)
        except ValueError:
            try:
                return float(o)
            except ValueError:
                return o

    elif isinstance(o, dict):
        return {k: _decode(v) for k, v in o.items()}
    elif isinstance(o, list):
        return [_decode(v) for v in o]
    else:
        return o


path = 'C:/doffin/test/'
for filename in os.listdir(path):
    if not filename.endswith('.json'):
        continue
    #26  
    #fullname = os.path.join(path, filename)
    fullname = os.path.join(path, filename)
    with open(fullname, 'rb') as f:
        jsonstr = f.read()

    json_sting = json.loads(jsonstr, object_hook=_decode)
    json_str2 = json.dumps(json_sting)
    
    with open(fullname[:-4] + ".json", 'w') as f:
        f.write(json_str2)

然后我使用 arango import form shell。它比 API 工作得更好。

于 2021-01-01T22:24:29.893 回答