Process Twitter followers fetched with get_followers.py

process_followers.py

#!/usr/bin/env python3

import re
import json
import glob

def print_user(user):
    print(
        user['id'],
        user['screen_name'],
        user['name'].replace('\r\n', ' ').replace('\n', ' '),
        user['statuses_count'],
        user['followers_count'],
        user['friends_count'],
        user['description'].replace('\r\n', ' ').replace('\n', ' '),
        user['default_profile_image'],

        # This adds an embedded image to Google Spreadsheets, but may be slow
        # if the file is large.

        # '=image("{}")'.format(user['profile_image_url_https']),

        sep='\t')

followers = []
for fname in glob.glob('followers*.txt'):
    with open(fname) as f:
        json_data = json.load(f)
        followers.extend(json_data)


HEBREW = re.compile(u'[\u0590-\u05FF]')
CYRILLIC = re.compile(u'[\u0400-\u0500]')
KANJI = re.compile(u'[\u3000-\u303f\u3040-\u309f\u30a0-\u30ff\uff00-\uffef\u4e00-\u9faf\u3400-\u4dbf]')

print(
    'User ID',
    'screen name',
    'name',
    'tweet count',
    'followers',
    'following',
    'description',
    'egg avatar',
    sep='\t'
)

for user in followers:
    print_user(user)

    continue # Stop here

    # Skip users you trust
    if HEBREW.search(user['name']) or HEBREW.search(user['description']):
        continue

    # Enable/disable these as needed

    if len(CYRILLIC.findall(user['name'])) > 3:
        continue
        print_user(user)

    if len(CYRILLIC.findall(user['description'])) > 3:
        continue
        print_user(user)

    if len(KANJI.findall(user['name'])) > 5:
        continue
        print_user(user)

    if len(KANJI.findall(user['description'])) > 5:
        continue
        print_user(user)

    if user['statuses_count'] == 0:
        continue
        print_user(user)