def load_data(path):
""" Load datasets
Loads Post and Comments datasets and merge them together.
:param path: data directory path
:param path: str
:return: DF of raw data
"""
# Dropbox client
team_dbx = dropbox.DropboxTeam(credentials.dropbox_team_access_token)
team_root = team_dbx.with_path_root(
dropbox.common.PathRoot.namespace_id(
credentials.dropbox_team_namespace_id))
user_dbx = team_root.as_user(credentials.dropbox_team_member_id)
# Load Posts and Comments DF
_, res_posts = user_dbx.files_download(os.path.join(path, "PolPosts.csv"))
posts = pd.read_csv(res_posts.raw, low_memory=False)
_, res_comments = user_dbx.files_download(
os.path.join(path, "UserComments.csv"))
comments = pd.read_csv(res_comments, low_memory=False)
# Merge Posts with Comments DFs
raw_data = pd.concat([posts, comments], sort=False)
return raw_data
def dump_data(df, path):
""" Dump cleaned DF
:param df: DF of cleaned data
:param df: pd.DataFrame
:param path: data directory path
:param path: str
:return: -
"""
# Dropbox client
team_dbx = dropbox.DropboxTeam(credentials.dropbox_team_access_token)
team_root = team_dbx.with_path_root(
dropbox.common.PathRoot.namespace_id(
credentials.dropbox_team_namespace_id))
user_dbx = team_root.as_user(credentials.dropbox_team_member_id)
# Dump
dump_path = os.path.join(path, "CleanedTextDF_interim.csv")
user_dbx.files_upload(bytes(df.to_csv(index=False), "utf-8"),
dump_path,
mode=dropbox.files.WriteMode.overwrite)
def load_data(path):
""" Load Datasets
Loads Post dataset.
:param path: data directory path
:param path: str
:return: DF of raw Posts data
"""
# Dropbox client
team_dbx = dropbox.DropboxTeam(credentials.dropbox_team_access_token)
team_root = team_dbx.with_path_root(
dropbox.common.PathRoot.namespace_id(
credentials.dropbox_team_namespace_id))
user_dbx = team_root.as_user(credentials.dropbox_team_member_id)
# Load Posts
_, res_posts = user_dbx.files_download(os.path.join(path, "PolPosts.csv"))
posts = pd.read_csv(res_posts.raw, low_memory=False)
return posts
def save_data(data, path, name):
""" Persist data (incl. assigned topics) to disk.
:param data: DF with assigned topics to persist
:type data: pd.DataFrame
:param path: data directory path
:type path: str
:param name: model name
:type name: str
:return: -
"""
# Dropbox client
team_dbx = dropbox.DropboxTeam(credentials.dropbox_team_access_token)
team_root = team_dbx.with_path_root(
dropbox.common.PathRoot.namespace_id(
credentials.dropbox_team_namespace_id))
user_dbx = team_root.as_user(credentials.dropbox_team_member_id)
# Persist to disk
persist_fpath = os.path.join(path, "topics", name + ".csv")
user_dbx.files_upload(bytes(data.to_csv(index=False), "utf-8"),
persist_fpath,
mode=dropbox.files.WriteMode.overwrite)
def listlinks():
'''print all public links urls for all members'''
for (memberid, email) in getmembers():
links = getlinks(memberid)
link_count = len(links)
print("Public Links: %s User: %s" % (link_count, email))
for link in links:
print(" %s" % link.url)
if __name__ == '__main__':
print(
"This script requires a API token with 'Team Member File Access premissions'"
)
token = (input("Enter your token: "))
mode = (input("Enter a mode (either 'list' or 'delete'): "))
dbxt = dropbox.DropboxTeam(token)
if mode == "list":
listlinks()
## CAUTION: Enabling this mode will allow deletion of unprotected shared links
## This could result in disruption to your team
# elif mode == "delete":
# delall()
else:
print("Please enter a mode of list or delete")
path = i.path_lower
filedate = findModified(path)
print("Last Modified Date: ", filedate)
if (filedate < oldestdate):
oldestdate = filedate
print("-")
print("The oldest file in this account is ", oldestdate)
#######
# MAIN
#######
TOKEN = 'REDACTED'
PERSONAL = 'REDACTED'
dbx = dropbox.DropboxTeam(TOKEN)
#dbx = dropbox.Dropbox(PERSONAL)
#membersList = WriteTeamMembers(dbx)
#GetUsage(dbx)
#LogEvents(dbx)
ListFiles(dbx.as_user(PERSONAL))
#getOldDate(dbx.as_user(PERSONAL))
if sys.version.startswith('2'):
input = raw_input # pylint: disable=redefined-builtin,undefined-variable,useless-suppression
def process_entries(current_state, entries):
for entry in entries:
if (
isinstance(entry, dropbox.files.FileMetadata) or
isinstance(entry, dropbox.files.FolderMetadata)
):
current_state[entry.path_lower] = entry
elif isinstance(entry, dropbox.files.DeletedMetadata):
current_state.pop(entry.path_lower, None)
return current_state
# Initialize Dropbox API
dbx_team = dropbox.DropboxTeam("ACCESS TOKEN")
# Prompt for account email
email = input("Enter team member email: ")
# Select a user via email
team_member_info = dbx_team.team_members_get_info(
[dropbox.team.UserSelectorArg.email(email)]
).pop()
# Verify that user is a valid team member
if team_member_info and team_member_info.is_member_info():
team_member_id = team_member_info.get_member_info().profile.team_member_id
user_dbx = dbx_team.as_user(team_member_id)
else:
print("User " + email + " was not found. Exiting...")
import dropbox
from dropbox.team_log import EventCategory
from dropbox.team_common import TimeRange
from datetime import datetime, timedelta
import csv
import sys
dbx = dropbox.DropboxTeam("<ACCESS TOKEN>")
headers = ["Timestamp", "Email", "Login Error"]
csvwriter = csv.writer(sys.stdout, lineterminator='\n')
# Collect login events
start = datetime.utcnow() - timedelta(days=30)
result = dbx.team_log_get_events(category=EventCategory.logins,
time=TimeRange(start_time=start))
events = result.events
# Collect additional events if needed
while result.has_more:
result = dbx.team_log_get_events_continue(result.cursor)
events.extend(result.events)
csvwriter.writerow(headers)
for event in events:
if event.event_type.is_login_fail() and event.actor.is_admin():
csvwriter.writerow((event.timestamp, event.actor.get_admin().email,
event.details.get_login_fail_details().
error_details.user_friendly_message))
if str(entry.name).endswith(".csv"):
interim_results_files.append(str(entry.name))
if results_fname in interim_results_files:
interim_results_files.remove(results_fname)
for file_name in interim_results_files:
_, res = user_dbx.files_download(os.path.join(data_path, file_name))
interim_results.append(pd.read_csv(res.raw))
return pd.concat(interim_results, axis=0)
if __name__ == "__main__":
# Dropbox client
team_dbx = dropbox.DropboxTeam(credentials.dropbox_team_access_token)
team_root = team_dbx.with_path_root(
dropbox.common.PathRoot.namespace_id(
credentials.dropbox_team_namespace_id))
user_dbx = team_root.as_user(credentials.dropbox_team_member_id)
# Paths and filenames
info_path = "/Data/Info Lists"
data_path = "/Data/CSVData/ads"
results_fname = "Test_AdLibAll.csv"
# Monitoring period constraints
monitoring_period_start = date(2019, 9, 8)
monitoring_period_stop = date(2019, 9, 29)
monitoring_window = (monitoring_period_start, monitoring_period_stop)
missing_stop_accounts = [] # bookkeep accounts w/ missing stop dates
import dropbox
import sys
if sys.version.startswith('2'):
input = raw_input # pylint: disable=redefined-builtin,undefined-variable,useless-suppression
dbx_team = dropbox.DropboxTeam("<ACCESS_TOKEN>")
def process_entries(current_state, entries):
for entry in entries:
if (isinstance(entry, dropbox.files.FileMetadata)
or isinstance(entry, dropbox.files.FolderMetadata)):
current_state[entry.path_lower] = entry
elif isinstance(entry, dropbox.files.DeletedMetadata):
current_state.pop(entry.path_lower, None)
return current_state
# Prompt for admin account email
email = input("Enter team admin email: ")
# Select a user via email
team_member_info = dbx_team.team_members_get_info(
[dropbox.team.UserSelectorArg.email(email)]).pop()
# Verify that user is a valid team member, and also a full team admin
if (team_member_info and team_member_info.is_member_info()
and team_member_info.get_member_info().role.is_team_admin()):
team_member_id = team_member_info.get_member_info().profile.team_member_id
admin_dbx = dbx_team.as_admin(team_member_id)
