scape.py

# Scrapes duolingo for all users

import  requests 

from datetime import datetime, timezone

def date(epoch_time):
    date_obj = datetime.fromtimestamp(epoch_time, timezone.utc)
    # Format the datetime object to dd/mm/yy hh:mm:ss format
    formatted_date = date_obj.strftime('%d/%m/%y %H:%M:%S')
    return formatted_date

for i in range(1, 1000000000000000000):
    headers = {'User-Agent': 'Mozilla/5.0 (X11; Windows x86_64; rv:120.0) Gecko/20100101 Firefox/120.0',}
    res = requests.get(f'https://www.duolingo.com/2017-06-30/users/{i}?fields=courses,creationDate,fromLanguage,gemsConfig,globalAmbassadorStatus,hasPlus,id,learningLanguage,lingots,name,picture,roles,streak,streakData{{currentStreak,previousStreak}},subscriberLevel,totalXp,username', headers=headers)
    if not res.text.startswith('404'):
        json = res.json()
        if json == {}:
            continue
        f = open("output.txt", "a")
        f.write(str(json))


        print(f'User Id: {json["id"]}')
        print(f'Username: {json["username"]}')
        print(f'Speaks: {json["fromLanguage"]}')
        print(f'Streak: {json["streak"]}')
        print(f'Account Creation Date: {date(json["creationDate"])}')
        print(f'Total XP: {json["totalXp"]}')
        if 'name' in json:
            print(f'Name: {json["name"]}')
        print(f'Learning:')
        duplicates = []
        for course in json["courses"]:
            if course['title'] not in duplicates:
                print(f'  {course["title"]}')
            duplicates.append(course['title'])

        print()