2018-01-24 17:43:35 -06:00
|
|
|
# -*- coding: utf-8 -*-
|
2018-01-26 12:56:50 -06:00
|
|
|
import os
|
|
|
|
import requests
|
2018-01-24 17:43:35 -06:00
|
|
|
import threading
|
|
|
|
import logging
|
2019-06-17 06:01:55 -05:00
|
|
|
import types
|
2019-06-24 09:41:22 -05:00
|
|
|
import extractors
|
|
|
|
from importlib import reload
|
2018-01-26 12:56:50 -06:00
|
|
|
from pubsub import pub
|
2018-01-24 17:43:35 -06:00
|
|
|
|
|
|
|
log = logging.getLogger("utils")
|
|
|
|
|
|
|
|
def call_threaded(func, *args, **kwargs):
|
|
|
|
#Call the given function in a daemonized thread and return the thread.
|
|
|
|
def new_func(*a, **k):
|
|
|
|
func(*a, **k)
|
|
|
|
thread = threading.Thread(target=new_func, args=args, kwargs=kwargs)
|
2019-05-06 02:20:01 -05:00
|
|
|
thread.daemon = True
|
2018-01-24 17:43:35 -06:00
|
|
|
thread.start()
|
|
|
|
return thread
|
|
|
|
|
|
|
|
class RepeatingTimer(threading.Thread):
|
|
|
|
"""Call a function after a specified number of seconds, it will then repeat again after the specified number of seconds
|
|
|
|
Note: If the function provided takes time to execute, this time is NOT taken from the next wait period
|
|
|
|
|
|
|
|
t = RepeatingTimer(30.0, f, args=[], kwargs={})
|
|
|
|
t.start()
|
|
|
|
t.cancel() # stop the timer's actions
|
|
|
|
"""
|
|
|
|
|
|
|
|
def __init__(self, interval, function, daemon=True, *args, **kwargs):
|
|
|
|
threading.Thread.__init__(self)
|
|
|
|
self.daemon = daemon
|
|
|
|
self.interval = float(interval)
|
|
|
|
self.function = function
|
|
|
|
self.args = args
|
|
|
|
self.kwargs = kwargs
|
|
|
|
self.finished = threading.Event()
|
|
|
|
|
|
|
|
def cancel(self):
|
|
|
|
"""Stop the timer if it hasn't finished yet"""
|
|
|
|
log.debug("Stopping repeater for %s" % (self.function,))
|
|
|
|
self.finished.set()
|
|
|
|
stop = cancel
|
|
|
|
|
|
|
|
def run(self):
|
|
|
|
while not self.finished.is_set():
|
|
|
|
self.finished.wait(self.interval)
|
|
|
|
if not self.finished.is_set(): #In case someone has canceled while waiting
|
|
|
|
try:
|
|
|
|
self.function(*self.args, **self.kwargs)
|
|
|
|
except:
|
|
|
|
log.exception("Execution failed. Function: %r args: %r and kwargs: %r" % (self.function, self.args, self.kwargs))
|
2018-01-26 12:56:50 -06:00
|
|
|
|
|
|
|
def download_file(url, local_filename):
|
2018-03-12 17:11:05 -06:00
|
|
|
log.debug("Download started: filename={0}, url={1}".format(local_filename, url))
|
2018-01-26 12:56:50 -06:00
|
|
|
r = requests.get(url, stream=True)
|
|
|
|
pub.sendMessage("change_status", status=_(u"Downloading {0}.").format(local_filename,))
|
|
|
|
total_length = r.headers.get("content-length")
|
|
|
|
dl = 0
|
|
|
|
total_length = int(total_length)
|
2018-03-12 17:11:05 -06:00
|
|
|
log.debug("Downloading file of {0} bytes".format(total_length))
|
2018-01-26 12:56:50 -06:00
|
|
|
with open(local_filename, 'wb') as f:
|
|
|
|
for chunk in r.iter_content(chunk_size=64):
|
|
|
|
if chunk: # filter out keep-alive new chunks
|
|
|
|
dl += len(chunk)
|
|
|
|
f.write(chunk)
|
|
|
|
done = int(100 * dl / total_length)
|
|
|
|
msg = _(u"Downloading {0} ({1}%).").format(os.path.basename(local_filename), done)
|
|
|
|
pub.sendMessage("change_status", status=msg)
|
2018-02-28 17:44:18 -06:00
|
|
|
pub.sendMessage("download_finished", file=os.path.basename(local_filename))
|
2018-03-12 17:11:05 -06:00
|
|
|
log.debug("Download finished successfully")
|
2018-01-26 12:56:50 -06:00
|
|
|
return local_filename
|
2019-06-17 06:01:55 -05:00
|
|
|
|
2019-06-24 09:41:22 -05:00
|
|
|
def get_extractors(import_all=False):
|
2019-06-17 06:01:55 -05:00
|
|
|
""" Function for importing everything wich is located in the extractors package and has a class named interface."""
|
|
|
|
module_type = types.ModuleType
|
2019-06-24 09:41:22 -05:00
|
|
|
# first of all, import all classes for the package so we can reload everything if they have changes in config.
|
|
|
|
_classes = [m for m in extractors.__dict__.values() if type(m) == module_type and hasattr(m, 'interface')]
|
|
|
|
for cls in _classes:
|
|
|
|
reload(cls)
|
|
|
|
if not import_all:
|
|
|
|
classes = [m for m in extractors.__dict__.values() if type(m) == module_type and hasattr(m, 'interface') and m.interface.enabled != False]
|
|
|
|
else:
|
|
|
|
classes = [m for m in extractors.__dict__.values() if type(m) == module_type and hasattr(m, 'interface')]
|
2019-06-17 06:01:55 -05:00
|
|
|
return classes#sorted(classes, key=lambda c: c.name)
|