image_collect.py

import threading
import os
import urllib.request

def status(j,d):
    if 'extended_entities' in d and 'media' in d['extended_entities']:
        p = 'images/' + d['user']['screen_name']
        if not os.path.exists(p):
            os.makedirs(p)
        for m in d['extended_entities']['media']:
            if 'retweeted_status' in d:
                return
            n = p + '/' + m['id_str'] + '.txt'
            o = open(n,'wb')
            o.write(d['text'].encode('utf-8'))
            o.close()
            print('save: ' + n)
            u = m['media_url']
            e = '.xxx'
            #EXT
            if '.png' in u:
                e = '.png'
            if '.jpg' in u:
                e = '.jpg'
            #URL
            if 'twimg' in u:
                u += ':orig'
            n = p + '/' + m['id_str'] + e
            threading.Thread(target=urlretrieve, args=(u,n)).start()

def urlretrieve(url,dest):
    try:
        urllib.request.urlretrieve(url,dest)
    except:
        import traceback
        import sys
        traceback.print_exc(output=sys.stdout)
    print('save: ' + dest)