Question

我有一个包含448条记录的.json文件。该文件是这样的格式 - 2记录为样本数据

{
    "_id" : ObjectId("5a5faa4f8b91277fde0212b1"),
    "geo_accession" : [ 
        "GSE86910"
    ],
    "title" : [ 
        "RNA-seq transcriptonal profiling in human primary adult erythroid progenitor celression"
    ],
    "summary" : [ 
        "The developing erythroid cerythroid cells, and performed RNA-seq transcriptional profiling analysis."
    ],
    "num_samples" : 6,
    "overall_design" : [ 
        "Human primary adult erythroblasts were generated ex vivo from extracted for RNA-seq analysis."
    ],
    "samples" : {
        "GSM2310252" : {
            "title" : "RNAseq_A5-ProE-shNT-rep1",
            "treatment_protocol_ch1" : "NA",
            "source_name_ch1" : "Human primary adult proerythroblasts (ProEs)",
            "organism_ch1" : "Homo sapiens",
            "library_strategy" : "RNA-Seq"
        },
        "GSM2310253" : {
            "title" : "RNAseq_A5-ProE-shNT-rep2",
            "treatment_protocol_ch1" : "NA",
            "source_name_ch1" : "Human primary adult proerythroblasts (ProEs)",
            "organism_ch1" : "Homo sapiens",
            "library_strategy" : "RNA-Seq"
        },
        "GSM2310254" : {
            "title" : "RNAseq_A5-ProE-shTFAM-rep1",
            "treatment_protocol_ch1" : "NA",
            "source_name_ch1" : "Human primary adult proerythroblasts (ProEs)",
            "organism_ch1" : "Homo sapiens",
            "library_strategy" : "RNA-Seq"
        },
        "GSM2310255" : {
            "title" : "RNAseq_A5-ProE-shTFAM-rep2",
            "treatment_protocol_ch1" : "NA",
            "source_name_ch1" : "Human primary adult proerythroblasts (ProEs)",
            "organism_ch1" : "Homo sapiens",
            "library_strategy" : "RNA-Seq"
        },
        "GSM2310256" : {
            "title" : "RNAseq_A5-ProE-shPHB2-rep1",
            "treatment_protocol_ch1" : "NA",
            "source_name_ch1" : "Human primary adult proerythroblasts (ProEs)",
            "organism_ch1" : "Homo sapiens",
            "library_strategy" : "RNA-Seq"
        },
        "GSM2310257" : {
            "title" : "RNAseq_A5-ProE-shPHB2-rep2",
            "treatment_protocol_ch1" : "NA",
            "source_name_ch1" : "Human primary adult proerythroblasts (ProEs)",
            "organism_ch1" : "Homo sapiens",
            "library_strategy" : "RNA-Seq"
        }
    },
    "geo_signal" : {}
}


{
    "_id" : ObjectId("5a5faa4f8b91277fde0212b6"),
    "geo_accession" : [ 
        "GSE83592"
    ],
    "title" : [ 
        "JQ1 +/- Vemurafenib in BRAF mutant melanoma (A375)"
    ],
    "summary" : [ 
        "The apoptotic genes significantly down-regulated."
    ],
    "num_samples" : 2,
    "overall_design" : [ 
        "dsf"
    ],
    "samples" : {
        "GSM2210563" : {
            "title" : "16L",
            "source_name_ch1" : "A375 cell line",
            "organism_ch1" : "Homo sapiens",
            "library_strategy" : "RNA-Seq"
        },
        "GSM2210564" : {
            "title" : "16R",
            "source_name_ch1" : "A375 cell line",
            "organism_ch1" : "Homo sapiens",
            "library_strategy" : "RNA-Seq"
        },
            },
    "geo_signal" : {}
}

现在我对这种格式完全没问题，但显然json.load对这种格式不起作用并且给出了错误

raise ValueError(errmsg("Extra data", s, end, len(s)))
ValueError: Extra data: line 2 column 1

这是否可以将所有这些转换为json格式的记录列表，如此

    [
    {
    "_id" : ObjectId("5a5faa4f8b91277fde0212b1"),
    "geo_accession" : [ 
        "GSE86910"
    ],
    "title" : [ 
        "RNA-seq transcriptonal profiling in human primary adult erythroid progenitor celression"
    ],
    "summary" : [ 
        "The developing erythroid cerythroid cells, and performed RNA-seq transcriptional profiling analysis."
    ],
    "num_samples" : 6,
    "overall_design" : [ 
        "Human primary adult erythroblasts were generated ex vivo from extracted for RNA-seq analysis."
    ],
    "samples" : {
        "GSM2310252" : {
            "title" : "RNAseq_A5-ProE-shNT-rep1",
            "treatment_protocol_ch1" : "NA",
            "source_name_ch1" : "Human primary adult proerythroblasts (ProEs)",
            "organism_ch1" : "Homo sapiens",
            "library_strategy" : "RNA-Seq"
        },
        "GSM2310253" : {
            "title" : "RNAseq_A5-ProE-shNT-rep2",
            "treatment_protocol_ch1" : "NA",
            "source_name_ch1" : "Human primary adult proerythroblasts (ProEs)",
            "organism_ch1" : "Homo sapiens",
            "library_strategy" : "RNA-Seq"
        },
        "GSM2310254" : {
            "title" : "RNAseq_A5-ProE-shTFAM-rep1",
            "treatment_protocol_ch1" : "NA",
            "source_name_ch1" : "Human primary adult proerythroblasts (ProEs)",
            "organism_ch1" : "Homo sapiens",
            "library_strategy" : "RNA-Seq"
        },
        "GSM2310255" : {
            "title" : "RNAseq_A5-ProE-shTFAM-rep2",
            "treatment_protocol_ch1" : "NA",
            "source_name_ch1" : "Human primary adult proerythroblasts (ProEs)",
            "organism_ch1" : "Homo sapiens",
            "library_strategy" : "RNA-Seq"
        },
        "GSM2310256" : {
            "title" : "RNAseq_A5-ProE-shPHB2-rep1",
            "treatment_protocol_ch1" : "NA",
            "source_name_ch1" : "Human primary adult proerythroblasts (ProEs)",
            "organism_ch1" : "Homo sapiens",
            "library_strategy" : "RNA-Seq"
        },
        "GSM2310257" : {
            "title" : "RNAseq_A5-ProE-shPHB2-rep2",
            "treatment_protocol_ch1" : "NA",
            "source_name_ch1" : "Human primary adult proerythroblasts (ProEs)",
            "organism_ch1" : "Homo sapiens",
            "library_strategy" : "RNA-Seq"
        }
    },
    "geo_signal" : {}
}


{
    "_id" : ObjectId("5a5faa4f8b91277fde0212b6"),
    "geo_accession" : [ 
        "GSE83592"
    ],
    "title" : [ 
        "JQ1 +/- Vemurafenib in BRAF mutant melanoma (A375)"
    ],
    "summary" : [ 
        "The apoptotic genes significantly down-regulated."
    ],
    "num_samples" : 2,
    "overall_design" : [ 
        "dsf"
    ],
    "samples" : {
        "GSM2210563" : {
            "title" : "16L",
            "source_name_ch1" : "A375 cell line",
            "organism_ch1" : "Homo sapiens",
            "library_strategy" : "RNA-Seq"
        },
        "GSM2210564" : {
            "title" : "16R",
            "source_name_ch1" : "A375 cell line",
            "organism_ch1" : "Homo sapiens",
            "library_strategy" : "RNA-Seq"
        },
            },
    "geo_signal" : {}
}
    ]

最好使用python。感谢。

Answer 1

将正则表达式处理用作有效的JSON。

import re
import json
def replaceFun(match):
    return match.group(1)
f=open("file/test.json","r")
str=f.read()
pattern=re.compile(r",\s*}",re.M)
newstr=pattern.sub(r"\n}",str)
pattern=re.compile(r"ObjectId\((.+)\)",re.M)
newstr=pattern.sub(replaceFun,newstr)
f.close()
newdict=json.loads(newstr)
for v in newdict:
    print(v)

将.json文件中的大量Json字典转换为json记录列表

1 个答案: