def test_move_most_recent_files(self):
self.data1 = pd.DataFrame({'data': [1, 2, 3, 4, 5]})
self.data1.to_csv(get_home_dir() + '/Downloads/test1.csv')
download_start = datetime.now().timestamp()
self.data2 = pd.DataFrame({'data': [1, 2, 3, 4, 5]})
self.data2.to_csv(
get_home_dir() +
'/Downloads/Britain Coronavirus Disease Prevention Map Mar 06 2020 Id Id Colocation Map_2020-03-31.csv'
)
self.assertTrue(os.path.exists(get_home_dir() +
'/Downloads/test1.csv'))
self.assertTrue(
os.path.exists(
get_home_dir() +
'/Downloads/Britain Coronavirus Disease Prevention Map Mar 06 2020 Id Id Colocation Map_2020-03-31.csv'
))
move_most_recent_files('./tmp1', ['url'], download_start)
self.assertTrue(os.path.exists(get_home_dir() +
'/Downloads/test1.csv'))
self.assertTrue(os.path.exists('./tmp1/Britain_2020_03_31.csv'))
os.remove(get_home_dir() + '/Downloads/test1.csv')
def main(_args):
'''
download colocation data
Parameters
----------
_args : listx
Arg list secret_key, username and pass dir, csv file specifying download countries and ids, outdir.
Returns
-------
None.
'''
username = input("Username: "******"Update datasets? (y/n): ")
if update == 'y':
update = True
elif update == 'n':
update = False
else:
sys.exit('Unknown update input. Choose "y", "n". Exiting.')
#read target datasets
data_target = pd.read_csv(_args[1])
for i, dataset_id in enumerate(data_target['id']):
country_output = _args[len(_args) - 1] + "/" + data_target.loc[i, 'country'] + '_mobility'
base_url = 'https://www.facebook.com/geoinsights-portal/downloads/vector/?id=' + str(dataset_id) + '&ds='
earliest_date = datetime(int(data_target.loc[i, 'year']), int(data_target.loc[i, 'month']), int(data_target.loc[i, 'day']), int(data_target.loc[i, 'hour']))
data_dates = get_file_dates(earliest_date)
if update:
data_dates = list(compress(data_dates, [x > get_update_date(country_output) for x in data_dates]))
if len(data_dates) == 0:
sys.exit('No datasets to download. Exiting.')
urls = get_urls(base_url, data_dates)
download_data(urls, keys)
move_most_recent_files(country_output, urls)
print('Success.')
def main(_args):
'''
download colocation data
Parameters
----------
_args : listx
Arg list secret_key, username and pass dir, csv file specifying download countries and ids, outdir.
Returns
-------
None.
'''
with open(_args[1], 'rb') as file:
fernet = Fernet(file.read())
with open(_args[2] + '/username.key', 'rb') as file:
username = file.read()
with open(_args[2] + '/password.key', 'rb') as file:
password = file.read()
keys = [
fernet.decrypt(username).decode("utf-8"),
fernet.decrypt(password).decode("utf-8")
]
#read target datasets
data_target = pd.read_csv(_args[3])
for i, dataset_id in enumerate(data_target['id']):
base_url = 'https://www.facebook.com/geoinsights-portal/downloads/vector/?id=' + str(
dataset_id) + '&ds='
earliest_date = datetime(int(data_target.loc[i, 'year']),
int(data_target.loc[i, 'month']),
int(data_target.loc[i, 'day']),
int(data_target.loc[i, 'hour']))
data_dates = get_file_dates(earliest_date)
urls = get_urls(base_url, data_dates)
download_data(urls, keys)
move_most_recent_files(
_args[len(_args) - 1] + "/" + data_target.loc[i, 'country'] +
'_mobility', urls)
print('Success.')
def pull_population(outdir, keys, country, dl_variables, update,
population_type):
'''
Parameters
----------
outdir : str
Output directory.
keys : list
user credentials [username, password].
country : str
Country name - must match .config file exactly (names with spaces must replace ' ' with '_').
dl_variables : dict
download specific variables in a dict, 'id' = dataset id, 'origin' = dataset origin datetime.datetime object.
update : boolean
Whether an existing dataset is being updated.
Returns
-------
None.
'''
country_output = outdir + "/" + country + '_' + population_type
base_url = 'https://www.facebook.com/geoinsights-portal/downloads/raster/?id=' + str(
dl_variables['id']) + '&ds='
earliest_date = dl_variables['origin']
data_dates = get_file_dates(earliest_date)
if update:
data_dates = list(
compress(data_dates,
[x > get_update_date(country_output)
for x in data_dates]))
if len(data_dates) == 0:
sys.exit('No datasets to download. Exiting.')
urls = get_urls(base_url, data_dates)
start_time = download_data(urls, keys)
move_most_recent_files(country_output, urls, start_time)
remove_empty_files(country_output)
print('Success.')
