tools/assemblee_nationale/scrap_types.py

# encoding: utf-8
"""
Tool used to upload representatives from French National Assembly.
"""

import csv
import json
import os
import sys

TYPES = {
    "API": "Assemblée parlementaire internationale",
    "ASSEMBLEE": "Assemblée Nationale",
    "CJR": "Cour de Justice de la République",
    "CMP": "Commission mixte paritaire",
    "CNPE": "Commission d’enquête",
    "CNPS": "Commission spéciale",
    "COMNL": "Autre commission permanente",
    "COMPER": "Commission permanente législative",
    "COMSENAT": "Commission sénatoriale",
    "COMSPSENAT": "Commission spéciale sénatoriale",
    "CONFPT": "Conférence des Présidents",
    "CONSTITU": "Conseil constitutionnel",
    "DELEG": "Délégation parlementaire",
    "DELEGBUREAU": "Délégation du Bureau de l'Assemblée Nationale",
    "DELEGSENAT": "Délégation sénatoriale",
    "GA": "Groupe d'amitié",
    "GE": "Groupe d'études",
    "GEVI": "Groupe d’études à vocation internationale",
    "GOUVERNEMENT": "Gouvernement",
    "GP": "Groupe politique",
    "GROUPESENAT": "Groupe sénatorial",
    "HCJ": "Haut Cour de Justice",
    "MINISTERE": "Ministère",
    "MISINFO": "Mission d’information",
    "MISINFOCOM": "Mission d’information commune",
    "MISINFOPRE": "Missions d’information de la conférence des Présidents",
    "OFFPAR": "Office parlementaire ou délégation mixte",
    "ORGEXTPARL": "Organisme extra parlementaire",
    "PARPOL": "Parti politique",
    "PRESREP": "Présidence de la République",
    "SENAT": "Sénat",
}


data_root = os.environ.get("POLITIKORAMA_DATA_ROOT", "../tmp")
target_root = os.path.join(data_root, "assemblee_nationale")

# Extract types
data_source = os.path.join(data_root, "json/organe")
data_target = os.path.join(target_root, "assemblee_nationale_types.csv")
with open(data_target, "w", encoding="utf-8", newline="") as csvfile:
    writer = csv.writer(csvfile, delimiter=",", quotechar='"', quoting=csv.QUOTE_MINIMAL)
    writer.writerow(["code", "name"])

    types = {}
    for filename in os.listdir(data_source):
        print(".", end="")
        sys.stdout.flush()
        # Loading informations
        with open(os.path.join(data_source, filename)) as file_handler:
            organe = json.load(file_handler)["organe"]
        if organe["codeType"].upper() not in types:
            types[organe["codeType"].upper()] = TYPES.get(organe["codeType"].upper(), organe["codeType"].upper())
    for type_code in types:
        # CSV line
        writer.writerow([
            type_code,
            types[type_code],
        ])