get_podcast_length.py

#!/usr/bin/env python3
import requests
import json
import re
import statistics
import time

resp = requests.get('https://russiancast.club/data.json')
data = resp.json()

RE_MINUTES = re.compile(r'•\s+(\d+) min')
for p in data:
    if not p.get('overcast'):
        continue
    print(p['title'])
    overcast = requests.get(p['overcast'])
    m = RE_MINUTES.findall(overcast.text)
    if m:
        minutes = [float(x) for x in m]
        p['duration'] = round(statistics.median(minutes))
    else:
        print('Could not find duration for {}'.format(p['overcast']))
    time.sleep(1)

with open('rupodcast_data_result.json', 'w') as f:
    json.dump(data, f, ensure_ascii=False, indent=1)