从字典中获取值

Question

I have a text file and it includes dictionaries, I want to get the value for all the Swiss-Prot and print them in separate lines.

For example, I want them to be like this as two column of query and swiss-prot

Query  Swiss-Prot

MED13  Q9UHV7

NIPBL  Q6KC79

This is a short example of the text type:

[{"query": "MED13", "_id": "9969", "_score": 89.814735, "uniprot": {"Swiss-Prot": "Q9UHV7", "TrEMBL": ["J3QRB7", "A0A024QZ75"]}}, {"query": "NIPBL", "_id": "25836", "_score": 90.15312, "uniprot": {"Swiss-Prot": "Q6KC79", "TrEMBL": ["H0Y8M3", "A0A590UJS4"]}}, {"query": "XPO1", "_id": "7514", "_score": 90.00326, "uniprot": {"Swiss-Prot": "O14980", "TrEMBL": ["A0A7I2V461", "A0A7I2V2Y6", "A0A7I2V6B9", "B3KWD0", "A0A7I2V396", "A0A7I2V531", "C9J673", "A0A7I2V3P3", "A0A7I2V3J1", "A0A7I2V2H0", "A0A7I2YQV4", "C9IYM2", "A0A7I2YQP1", "A0A7I2V3N0", "A0A7I2V2S3", "C9JKM9", "A0A7I2V3W6", "A0A7P0Z4B7", "A0A7I2V2C5", "A0A7I2V4A3", "F8WF71", "A0A7I2V488", "A0A7I2YQX3"]}}, {"query": "PRR12", "_id": "57479", "_score": 93.08752, "uniprot": {"Swiss-Prot": "Q9ULL5"}}, {"query": "USP9X", "_id": "8239", "_score": 91.546684, "uniprot": {"Swiss-Prot": "Q93008", "TrEMBL": ["Q86X58", "Q6P468"]}}, {"query": "POLA1", "_id": "5422", "_score": 87.691986, "uniprot": {"Swiss-Prot": "P09884", "TrEMBL": ["A0A5F9ZHW2", "A6NMQ1", "A0A7I2V2V3"]}}, {"query": "SYNGAP1", "_id": "8831", "_score": 92.250496, "uniprot": {"Swiss-Prot": "Q96PV0", "TrEMBL": ["B7ZCA0", "A0A1U9X8L0", "A0A2R8YDS2", "A0A1B0GW70", "A0A140T8W4", "A0A0A0MQZ2", "A0A2R8Y6T2", "A0A804HJ92"]}}, {"query": "PRKDC", "_id": "5591", "_score": 87.73935, "uniprot": {"Swiss-Prot": "P78527", "TrEMBL": ["F5GX40", "H0YG84"]}}, {"query": "HDAC4", "_id": "9759", "_score": 87.96423, "uniprot": {"Swiss-Prot": "P56524", "TrEMBL": ["H7C397", "A0A7I2SVS4", "C9J0X4", "H7BZT3", "C9J481"]}}, {"query": "SMG1", "_id": "23049", "_score": 87.58261, "uniprot": {"Swiss-Prot": "Q96Q15", "TrEMBL": ["H3BR09", "I3L400", "J3KRA9", "H3BPS6", "A0A087X1K8", "I3L0W2", "E9PNP6", "I3L144", "H3BQN7"]}}, {"query": "ZC3H4", "_id": "23211", "_score": 88.41728, "uniprot": {"Swiss-Prot": "Q9UPT8", "TrEMBL": "M0QY97"}}, {"query": "COL5A1", "_id": "1289", "_score": 88.062645, "uniprot": {"Swiss-Prot": "P20908", "TrEMBL": ["B2ZZ86", "A0A024R8E5", "Q59EE7", "H7BY82"]}}, {"query": "SMARCA4", "_id": "6597", "_score": 91.729965, "uniprot": {"Swiss-Prot": "P51532", "TrEMBL": ["A7E2E1", "Q9HBD4", "B3KNW7", "A0A2R8Y7S2", "A0A2R8YF80", "A0A2R8Y523", "A0A2R8Y6N0", "A0A2R8Y583", "A0A2R8Y7Y7", "A0A2R8Y7R0", "A0A2R8Y440", "A0A2R8YGP5", "A0A2R8Y866", "A0A2R8YFK5", "A0A2R8YDA1", "A0A2R8YF38", "K7EP28", "A0A2R8Y526", "A0A2R8Y5K3", "A0A2R8YFV8", "A0A2R8YF58", "A0A2R8YGG3", "A0A2R8Y7F3", "K7EQF0", "A0A2R8YG32", "A0A2R8Y4P4", "A0A2R8Y4C5", "A0A2R8YCY3", "A0A2R8Y6V2", "A0A2R8Y4R6"]}}, {"query": "TNPO1", "_id": "3842", "_score": 87.91549, "uniprot": {"Swiss-Prot": "Q92973", "TrEMBL": ["E7EW37", "A0A024RAM0", "A0A7P0T9C0", "S4R398", "A0A7P0T944", "A0A7P0TBF0", "A0A7P0Z4D3"]}}, {"query": "AGO1", "_id": "26523", "_score": 91.19263, "uniprot": {"Swiss-Prot": "Q9UL18", "TrEMBL": ["B2RAD8", "Q5TA58", "A0A6I8PTZ8", "B3KME0", "A0A0U1RQZ8"]}}, {"query": "ARHGAP35", "_id": "2909", "_score": 90.83041, "uniprot": {"Swiss-Prot": "Q9NRY4"}}, {"query": "LRP1", "_id": "4035", "_score": 90.87773, "uniprot": {"Swiss-Prot": "Q07954", "TrEMBL": ["Q6PJ72", "Q59FG2", "Q7Z7K9", "H0YJ88", "H0YJI8"]}}, {"query": "TOP1", "_id": "7150", "_score": 88.75276, "uniprot": {"Swiss-Prot": "P11387", "TrEMBL": ["A0A7P0T852", "Q9BVT2", "A0A7P0T9R7"]}}, {"query": "TRIP12", "_id": "9320", "_score": 87.6137, "uniprot": {"Swiss-Prot": "Q14669", "TrEMBL": ["A0A6Q8PGG9", "A0A6Q8PHK0", "G5E9G6", "C9JSX9", "C9JLJ5", "C9JLD7", "H7C1L9", "H7C2Y1", "F8W9P3"]}}, {"query": "KMT2E", "_id": "55904", "_score": 87.338264, "uniprot": {"Swiss-Prot": "Q8IZD2", "TrEMBL": ["C9JNE1", "A0A087WYW5", "S4R363", "C9JQ68", "H7C5C4", "A0A590UK87", "H7C4F3", "C9JYI9", "F8WAU9"]}}, {"query": "HCFC1", "_id": "3054", "_score": 92.59821, "uniprot": {"Swiss-Prot": "P51610", "TrEMBL": ["H7C1C4", "A6NEM2"]}}, {"query": "UBTF", "_id": "7343", "_score": 88.12895, "uniprot": {"Swiss-Prot": "P17480", "TrEMBL": ["E9PLT2", "E9PKP7", "H0YDH7", "E9PMM2"]}}, {"query": "HUWE1", "_id": "10075", "_score": 88.91688, "uniprot": {"Swiss-Prot": "Q7Z6Z7", "TrEMBL": ["A0A1B0GXC7", "A0A024R9W5", "H0Y659", "A0A087X146", "A0A087X1S3"]}}, {"query": "KDM3B", "_id": "51780", "_score": 87.94795, "uniprot": {"Swiss-Prot": "Q7LBC6", "TrEMBL": ["H0Y946", "H0Y9V5"]}}, {"query": "TRRAP", "_id": "8295", "_score": 90.83041, "uniprot": {"Swiss-Prot": "Q9Y4A5", "TrEMBL": ["A0A2R8YFJ4", "F2Z2U4", "C9K0N1", "H0Y4W2"]}}, {"query": "GRIN2B", "_id": "2904", "_score": 89.35281, "uniprot": {"Swiss-Prot": "Q13224", "TrEMBL": ["A0A1B0GU78", "A0A0D9SFK0", "A0A0D9SFA0"]}}, {"query": "USP7", "_id": "7874", "_score": 87.70774, "uniprot": {"Swiss-Prot": "Q93009", "TrEMBL": ["B7ZAX6", "B7Z855", "Q6U8A4", "I3L2D8", "H3BVA7", "H3BQD1", "H3BRI4", "F5H2X1", "H3BTM1", "H3BND8", "H3BMF6", "H3BRA2", "H3BUV0", "A0A669KBL1"]}}, {"query": "ATP1A3", "_id": "478", "_score": 93.2793, "uniprot": {"Swiss-Prot": "P13637", "TrEMBL": ["M0R116", "Q53ES0", "A0A0A0MT26", "M0QXF2"]}}, {"query": "ASH1L", "_id": "55870", "_score": 87.80293, "uniprot": {"Swiss-Prot": "Q9NR48", "TrEMBL": ["A0A7I2YQU9", "A0A7I2V316", "A0A7I2V3D6", "H0YI82", "A0A7I2V4K0", "A0A7I2YQL4", "F8VWK7", "A0A7I2V542", "A0A7I2V4H9"]}}, {"query": "ANKRD17", "_id": "26057", "_score": 90.394646, "uniprot": {"Swiss-Prot": "O75179", "TrEMBL": ["H0YLQ3", "H0YM23"]}}, {"query": "SMC1A", "_id": "8243", "_score": 89.55028, "uniprot": {"Swiss-Prot": "Q14683", "TrEMBL": ["G8JLG1", "A0A384MR33", "Q68EN4", "A0A6Q8PHC3", "V9GY57", "V9GYN9"]}}]

Answer 1

It looks like you have a json-formatted file. You can read this using the json module , and process the resulting list of dictionaries to print the output you want.

import json

with open("input.txt") as f:
    data = json.load(f)

print("Query\tSwiss-Prot")
for item in data:
    q = item["query"]
    sp = item["uniprot"]["Swiss-Prot"]
    print(f"{q}\t{sp}")

Which gives:

Query   Swiss-Prot
MED13   Q9UHV7
NIPBL   Q6KC79

---

If you have multiple lines in your input file which are all separately json-formatted, you could use the following to parse your file. Here, I read each line from the file, parse the json, and add all the elements of the resulting list to the data list. The code to print the output remains the same.

import json

data = []
with open("input.txt") as f:
    for line in f:
        data.extend(json.loads(line))        

Answer 2

Your datas are in a list with a dictionnary for each entry. Iterate with a loop over entries and extract values.

print("Query\tSwiss-Prot")

for entry in datas:
    if 'query' in entry:
        if ('uniprot' in entry) and ('Swiss-Prot' in entry['uniprot']):
            print(f"{entry['query']}\t{entry['uniprot']['Swiss-Prot']}")
        else:
            print(f"{entry['query']}\tUnknown")

Answer 3

# import json for converting your text file
import json

# open your text file
with open("yourfile.txt", "r") as file:
    data = file.read()

# convert your data to json (dictionary)
convert_to_dict = json.loads(data)

# loop through the dict file and print the results
for i in convert_to_dict:
    print(i["query"], " ", i["uniprot"]["Swiss-Prot"])