cro_scraper.py

# coding: utf-8

import requests
import os
import json
import pandas as pd

for i in range(0, 34):
    url = 'https://cro.justice.cz/verejnost/api/funkcionari?sort=created&order=DESC&page=' + str(i) + '&pageSize=1000'
    r = requests.get(url)
    with open('./scratch/p_' + str(i) + '.json', 'wb') as f:
        f.write(r.content)

out = pd.DataFrame()
for file in os.listdir('./scratch'):
    with open('./scratch/' + file, encoding='utf-8') as f:
        temp = json.load(f)
        if len(temp['items']) > 0:
            out = out.append(temp['items'], ignore_index=True)

out = out.drop('workingPositions', axis=1)
out.drop_duplicates(inplace=True)
out.to_excel('./osoby.xlsx')