给定以下类:
from abc import ABCMeta, abstractmethod
from time import sleep
import threading
from threading import active_count, Thread
class ScraperPool(metaclass=ABCMeta):
Queue = []
ResultList = []
def __init__(self, Queue, MaxNumWorkers=0, ItemsPerWorker=50):
# Initialize attributes
self.MaxNumWorkers = MaxNumWorkers
self.ItemsPerWorker = ItemsPerWorker
self.Queue = Queue # For testing purposes.
def initWorkerPool(self, PrintIDs=True):
for w in range(self.NumWorkers()):
Thread(target=self.worker, args=(w + 1, PrintIDs,)).start()
sleep(1) # Explicitly wait one second for this worker to start.
def run(self):
self.initWorkerPool()
# Wait until all workers (i.e. threads) are done.
while active_count() > 1:
print("Active threads: " + str(active_count()))
sleep(5)
self.HandleResults()
def worker(self, id, printID):
if printID:
print("Starting worker " + str(id) + ".")
while (len(self.Queue) > 0):
self.scraperMethod()
if printID:
print("Worker " + str(id) + " is quiting.")
# Todo Kill is this Thread.
return
def NumWorkers(self):
return 1 # Simplified for testing purposes.
@abstractmethod
def scraperMethod(self):
pass
class TestScraper(ScraperPool):
def scraperMethod(self):
# print("I am scraping.")
# print("Scraping. Threads#: " + str(active_count()))
temp_item = self.Queue[-1]
self.Queue.pop()
self.ResultList.append(temp_item)
def HandleResults(self):
print(self.ResultList)
ScraperPool.register(TestScraper)
scraper = TestScraper(Queue=["Jaap", "Piet"])
scraper.run()
print(threading.active_count())
# print(scraper.ResultList)
完成所有线程完成后,仍然有一个活动线程-threading.active_count()
在最后一行中得到我的数字。
活动线程为<_MainThread(MainThread, started 12960)>
-用threading.enumerate()
打印。
我可以假设我所有的线程都在active_count() == 1
时完成吗?或例如,可以导入的模块启动其他线程,以便在active_count() > 1
时实际完成我的线程 - 也是我在运行方法中使用的环路的条件。
您可以假设您的线程是在active_count()
达到1时完成的。问题是,如果任何其他模块创建线程,您将永远不会达到1。您应该明确管理线程。
示例:您可以将线程放入列表中,然后一次加入它们。代码的相关更改是:
def __init__(self, Queue, MaxNumWorkers=0, ItemsPerWorker=50):
# Initialize attributes
self.MaxNumWorkers = MaxNumWorkers
self.ItemsPerWorker = ItemsPerWorker
self.Queue = Queue # For testing purposes.
self.WorkerThreads = []
def initWorkerPool(self, PrintIDs=True):
for w in range(self.NumWorkers()):
thread = Thread(target=self.worker, args=(w + 1, PrintIDs,))
self.WorkerThreads.append(thread)
thread.start()
sleep(1) # Explicitly wait one second for this worker to start.
def run(self):
self.initWorkerPool()
# Wait until all workers (i.e. threads) are done. Waiting in order
# so some threads further in the list may finish first, but we
# will get to all of them eventually
while self.WorkerThreads:
self.WorkerThreads[0].join()
self.HandleResults()
根据文档active_count()
包括主线程,因此,如果您在1处,则很可能完成,但是如果您程序中有其他新线程来源,则可以在active_count()
命中之前完成1.
我建议在您的ScraperPool
上实现明确的join
方法,并跟踪工人并在需要时明确将其加入到主线程中,而不是检查您对active_count()
调用的完成。
还记得有关吉尔...