Consumindo API de Dados Aberto Fortaleza da Citinova

datasetconsuming.py

import json
import pandas as pd
from urllib import request

# Get the data from the API
arquivo_local = "C:\\Users\\edcly\\Downloads" \
                "\\transparencia_informacoes_servidores_012021.csv"
url = "https://dados.fortaleza.ce.gov.br/api/3/action/package_search"


def ckan_package_search_organizations(url, organizacao):
    query = "?fq=organization:"
    retorno = request.urlopen(url + query + organizacao)
    json_retorno = json.loads(retorno.read())
    return json.dumps(json_retorno, indent = 4, sort_keys = True,
                      ensure_ascii = False)


def ckan_package_search_groups(url, grupo):
    query = "?fq=groups:"
    retorno = request.urlopen(url + query + grupo)
    json_retorno = json.loads(retorno.read())
    return json.dumps(json_retorno, indent = 4, sort_keys = True,
                      ensure_ascii = False)


def ckan_package_search_tags(url, tag):
    query = "?fq=tags:"
    retorno = request.urlopen(url + query + tag)
    json_retorno = json.loads(retorno.read())
    return json.dumps(json_retorno, indent = 4, sort_keys = True,
                      ensure_ascii = False)


def ckan_package_search_format(url, formato):
    query = "?fq=res_format:"
    formato = formato.upper()
    retorno = request.urlopen(url + query + formato)
    json_retorno = json.loads(retorno.read())
    return json.dumps(json_retorno, indent = 4, sort_keys = True,
                      ensure_ascii = False)


def ckan_package_search_license(url, licenca):
    query = "?fq=license_id:"
    retorno = request.urlopen(url + query + licenca)
    json_retorno = json.loads(retorno.read())
    return json.dumps(json_retorno, indent = 4, sort_keys = True,
                      ensure_ascii = False)


def dataset_local(arquivo_local):
    # Read the file
    df = pd.read_csv(arquivo_local)
    # Print the first 5 rows of the data
    print(df.head())
    # Print the last 5 rows of the data
    print(df.tail())
    # Print the number of rows and columns
    print(df.shape)
    # Print the column names
    print(df.columns)
    # Print the data type of each column
    print(df.dtypes)
    # Print the summary statistics for each of the numeric columns
    print(df.describe())
    # Print the unique values for each of your categorical columns
    print(df["NOME DO SERVIDOR"].unique())
    # Print the Dataframe information
    print(pd.DataFrame(df["NOME DO SERVIDOR"] + ["ENTIDADE OU ÓRGÃO"] + [
        "REMUNERAÇÃO"]))


if __name__ == "__main__":
    print("Dataset Local Consuming")
    dataset_local(arquivo_local)
    print("="*10)

    print("Dataset Remote Consuming:\n")
    print("Dataset Remote Consuming by Organization")
    print(ckan_package_search_organizations(url, "sepog"))
    print("="*10)
    print("Dataset Remote Consuming by Group")
    print(ckan_package_search_groups(url, "meioambiente"))
    print("="*10)
    print("Dataset Remote Consuming by Tag")
    print(ckan_package_search_tags(url, "cgm"))
    print("="*10)
    print("Dataset Remote Consuming by Format")
    print(ckan_package_search_format(url, "csv"))
    print("="*10)
    print("Dataset Remote Consuming by License")
    print(ckan_package_search_license(url, "cc-by-sa"))