特Pの駐車場検索JSONレスポンスをCSVに変換、1時間あたりの駐車料金を抽出するスクリプト

pickprice.py

import csv
import io
import re
import sys

sys.stdout = io.TextIOWrapper(sys.stdout.buffer, encoding='utf-8')
sys.stderr = io.TextIOWrapper(sys.stderr.buffer, encoding='utf-8')


def get_price(s):
    def per_hour(yen, per):
        return yen * 60.0 / per

    m = re.search(r"(\d+)円.?(\d+)分", s)
    if m:
        yen = int(m.group(1))
        per = int(m.group(2))
        return per_hour(yen, per)
    m = re.search(r"(\d+)分[^\d]?(\d+)円", s)
    if m:
        per = int(m.group(1))
        yen = int(m.group(2))
        return per_hour(yen, per)
    m = re.search(r"(\d+)分[^\d]?¥(\d+)", s)
    if m:
        per = int(m.group(1))
        yen = int(m.group(2))
        return per_hour(yen, per)
    m = re.search(r"24時間[^\d]?(\d+)円", s)
    if m:
        yen = int(m.group(1))
        return yen
    m = re.search(r"24時間[^\d]?¥(\d+)", s)
    if m:
        yen = int(m.group(1))
        return yen
    m = re.search(r"(\d+)時間[^\d]?¥(\d+)", s)
    if m:
        per = int(m.group(1))
        yen = int(m.group(2))
        return per_hour(yen, per * 60)
    m = re.search(r"(\d+)時間[^\d]?(\d+)円", s)
    if m:
        per = int(m.group(1))
        yen = int(m.group(2))
        return per_hour(yen, per * 60)
    m = re.search(r"(\d+)円[^\d]?(\d+)時間", s)
    if m:
        yen = int(m.group(1))
        per = int(m.group(2))
        return per_hour(yen, per * 60)
    m = re.search(r"1日[^\d]?(\d+)円", s)
    if m:
        yen = int(m.group(1))
        return yen
    m = re.search(r"1日1回[^\d]?(\d+)円", s)
    if m:
        yen = int(m.group(1))
        return yen
    return None


def read_csv(fname):
    data = []
    with open(fname, encoding="utf-8") as f:
        reader = csv.DictReader(f)
        for row in reader:
            # print(f'{get_price(row["feature"])}, {row["feature"]}')
            row["price"] = get_price(row["feature"])
            del row["is_toku_p"]
            data.append(row)
    with open(f"{fname[:-4]}_price.csv", "w", newline="\n", encoding="utf-8") as f:
        writer = csv.DictWriter(f, ["id", "parking_lot", "price", "latitude", "longitude", "name", "feature"])
        writer.writeheader()
        writer.writerows(data)

if __name__ == "__main__":
    for fname in sys.argv[1:]:
        read_csv(fname)

tocsv.sh

#!/bin/bash
# for f in json/*.json; do ./tocsv.sh <$f >${f//json/csv}; done
jq -r  '.content[]|[.id,.is_toku_p,.parking_lot,.latitude,.longitude,.name,(.feature|gsub("\n";";"))]|@csv'

# grep -h '^[0-9]*,false,[0-9]' csv/*.csv | sort -t, -k 6 -u >all.csv