Convert only last X rows of csv into json-CodePudding

I have the following python code to convert csv file into json file.

def make_json_from_csv(csv_file_path, json_file_path, unique_column_name):
    import csv
    import json
    # create a dictionary
    data = {}

    # Open a csv reader called DictReader
    with open(csv_file_path, encoding='utf-8') as csvf:
        csv_reader = csv.DictReader(csvf)

        primary_key_column_name = unique_column_name.lstrip()  # remove leading space in string
        # Convert each row into a dictionary
        # and add it to data
        for rows in csv_reader:
            key = rows[primary_key_column_name]
            data[key] = rows

    # Open a json writer, and use the json.dumps()
    # function to dump data
    with open(json_file_path, 'w', encoding='utf-8') as jsonf:
        jsonf.write(json.dumps(data, indent=4))
    return None

The code above will convert ALL the rows in the CSV file into json file. I want to convert only the last X number of rows into json.

I am using python v3.

CodePudding user response：

In Python 3.6 the dict keep the insertion order, so to fetch the last rows of a dictionary, just do:

from itertools import islice

x = 5
d = {}
for i, v in enumerate("abcdedfghi"):
    d[i] = v

d = dict(islice(d.items(), len(d) - x, len(d)))
print(d)

Output

{5: 'd', 6: 'f', 7: 'g', 8: 'h', 9: 'i'}

Basically add (change) these lines into your code:

from itertools import islice

x = 5
data = dict(islice(data.items(), len(data) - x, len(data)))

# Open a json writer, and use the json.dumps()
# function to dump data
with open(json_file_path, 'w', encoding='utf-8') as jsonf:
    jsonf.write(json.dumps(data, indent=4))

CodePudding user response：

I would like to answer my own question by building on Dani Mesejo's answer. The credit goes entirely to him.

def make_json(csv_file_path, json_file_path,
              unique_column_name, no_of_rows_to_extract):
    import csv
    import json
    from itertools import islice
    # create a dictionary
    data = {}

    # Open a csv reader called DictReader
    with open(csv_file_path, encoding='utf-8') as csvf:
        csv_reader = csv.DictReader(csvf)

        primary_key_column_name = unique_column_name.lstrip()  # remove leading space in string
        # Convert each row into a dictionary
        # and add it to data
        for rows in csv_reader:
            key = rows[primary_key_column_name]
            data[key] = rows

    data = dict(islice(data.items(), len(data) - no_of_rows_to_extract, len(data)))

    # Open a json writer, and use the json.dumps()
    # function to dump data
    with open(json_file_path, 'w', encoding='utf-8') as jsonf:
        jsonf.write(json.dumps(data, indent=4))
    return None