我用线程池写了一个简单的网站crowler。问题是:然后爬虫得到所有的网站它必须完成,但在现实中,它等待的东西结束了,脚本没有完成,为什么会发生这种情况?
from Queue import Queue
from threading import Thread
import sys
from urllib import urlopen
from BeautifulSoup import BeautifulSoup, SoupStrainer
import re
from Queue import Queue, Empty
from threading import Thread
visited = set()
queue = Queue()
class Worker(Thread):
"""Thread executing tasks from a given tasks queue"""
def __init__(self, tasks):
Thread.__init__(self)
self.tasks = tasks
self.daemon = True
self.start()
def run(self):
while True:
func, args, kargs = self.tasks.get()
print "startcall in thread",self
print args
try: func(*args, **kargs)
except Exception, e: print e
print "stopcall in thread",self
self.tasks.task_done()
class ThreadPool:
"""Pool of threads consuming tasks from a queue"""
def __init__(self, num_threads):
self.tasks = Queue(num_threads)
for _ in range(num_threads): Worker(self.tasks)
def add_task(self, func, *args, **kargs):
"""Add a task to the queue"""
self.tasks.put((func, args, kargs))
def wait_completion(self):
"""Wait for completion of all the tasks in the queue"""
self.tasks.join()
def process(pool,host,url):
try:
print "get url",url
#content = urlopen(url).read().decode(charset)
content = urlopen(url).read()
except UnicodeDecodeError:
return
for link in BeautifulSoup(content, parseOnlyThese=SoupStrainer('a')):
#print "link",link
try:
href = link['href']
except KeyError:
continue
if not href.startswith('http://'):
href = 'http://%s%s' % (host, href)
if not href.startswith('http://%s%s' % (host, '/')):
continue
if href not in visited:
visited.add(href)
pool.add_task(process,pool,host,href)
print href
def start(host,charset):
pool = ThreadPool(7)
pool.add_task(process,pool,host,'http://%s/' % (host))
pool.wait_completion()
start('simplesite.com','utf8')
发布于 2010-09-06 11:23:42
我看到的问题是,当中的运行时,您永远不会退出。因此,它将永远阻塞。当作业完成时,您需要打破这个循环。
您可以尝试:
1)插入
if not func: break
在task.get(...) in 之后,运行。
2)追加
pool.add_task(None, None, None)
在process的末尾。
这是 process 通知池他没有更多任务要处理的一种方式。
https://stackoverflow.com/questions/3648781
复制相似问题