def init_socialWatcher_and_check_credentials():
try:
dataCollector = watcherAPI()
dataCollector.load_credentials_file(FB_CREDENTIALS_FILE)
dataCollector.check_tokens_account_valid()
return dataCollector
except Exception as Error:
send_email_error("Error: Credentials invalid")
raise Error
def query_facebook_audience(access_token,
user_id,
query_file,
extra_auth_data=[],
response_file=None):
"""
Build manual query and execute request.
access_token :: FB access token
user_id :: FB user ID
query_file :: JSON file containing query
extra_auth_data :: List of auth data pairs.
response_file :: Name of existing response file, if needed.
response :: DataFrame with query response(s) => one response per row
"""
watcher = watcherAPI()
if (not (access_token, user_id) in TOKENS):
watcher.add_token_and_account_number(access_token, user_id)
for (access_token_i, user_id_i) in extra_auth_data:
if (not (access_token_i, user_id_i) in TOKENS):
watcher.add_token_and_account_number(access_token_i, user_id_i)
print('%d FB tokens' % (len(TOKENS)))
## execute data collection
if (response_file is not None and os.path.exists(response_file)):
print('using response file %s' % (response_file))
response = watcher.load_data_and_continue_collection(response_file)
else:
response = watcher.run_data_collection(query_file)
## clean up temporary dataframes
file_matcher = re.compile('dataframe_.*.csv')
tmp_files = filter(lambda f: file_matcher.search(f) is not None,
os.listdir('.'))
for f in tmp_files:
os.remove(f)
return response
import os
from pysocialwatcher import watcherAPI
from time import time, localtime
from lib import PersistentSet
from string import ascii_lowercase
COLS = ('id', 'audience_size', 'name', 'path', 'type')
watcher = watcherAPI()
watcher.load_credentials_file('credentials.txt')
autosave_every_N_seconds = 60
def explore():
def save():
next_set.save()
running_set.save()
visited_set.save()
saved_set.save()
last_update = time()
working_folder = 'CACHE_interest_discovery'
visited_set = PersistentSet(working_folder + '/visited.txt')
saved_set = PersistentSet(working_folder + '/saved.txt')
running_set = PersistentSet(working_folder + '/running.txt',
set(ascii_lowercase))
next_set = PersistentSet(working_folder + '/next.txt')
