Queue
example a concurrent web spider
tornado 的 tornado.queues 模块实现了异步协程生产/消费者模式，类似于 python 标准库中的 queue 模块实现的多线程模式。
一个协程 yield Queue.get 会暂停直到队列中有对象。如果队列设置了最大值，一个协程 yield Queue.put 会暂停直到队列中有位置。
一个 Queue 维护着未完成的任务数量，始于0。
put 增加了任务值。task_done 消除一个计数。
在 web-爬虫例子里，队列开始只包含 base_url。当一个 worker 获取一个页面他解析链接并 put 到队列中，然后调用 task_done 消除一次计数。
最终，当一个 worker 在一个页面中解析的所有的 urls 都已记录，并且队列中也没有剩下 work。这时，worker's 调用 task_done 将计数消除为 0。等待 join 的主协程不再停顿并且结束。
#!/usr/bin/env python
import time
from datetime import timedelta
try:
from HTMLParser import HTMLParser
from urlparse import urljoin, urldefrag
except ImportError:
from html.parser import HTMLParser
from urllib.parse import urljoin, urldefrag
from tornado import httpclient, gen, ioloop, queues
base_url =
concurrency = 10
@gen.coroutine
def get_links_from_url(url):
"""Download the page at `url` and parse it for links.
Returned links have had the fragment after `#` removed, and have been made
absolute so, e.g. the URL 'gen.html#tornado.gen.coroutine' becomes
"""
try:
response = yield httpclient.AsyncHTTPClient().fetch(url)
print('fetched %s' % url)
html = response.body if isinstance(response.body, str) \
else response.body.decode(errors='ignore')
urls = [urljoin(url, remove_fragment(new_url))
for new_url in get_links(html)]
except Exception as e:
print('Exception: %s %s' % (e, url))
raise gen.Return([])
raise gen.Return(urls)
def remove_fragment(url):
pure_url, frag = urldefrag(url)
return pure_url
def get_links(html):
class URLSeeker(HTMLParser):
def __init__(self):
HTMLParser.__init__(self)
self.urls = []
def handle_starttag(self, tag, attrs):
href = dict(attrs).get('href')
if href and tag == 'a':
self.urls.append(href)
url_seeker = URLSeeker()
url_seeker.feed(html)
return url_seeker.urls
@gen.coroutine
def main():
q = queues.Queue()
start = time.time()
fetching, fetched = set(), set()
@gen.coroutine
def fetch_url():
current_url = yield q.get()
try:
if current_url in fetching:
return
print('fetching %s' % current_url)
fetching.add(current_url)
urls = yield get_links_from_url(current_url)
fetched.add(current_url)
for new_url in urls:
# Only follow links beneath the base URL
if new_url.startswith(base_url):
yield q.put(new_url)
finally:
q.task_done()
@gen.coroutine
def worker():
while True:
yield fetch_url()
q.put(base_url)
# Start workers, then wait for the work queue to be empty.
for _ in range(concurrency):
worker()
yield q.join(timeout=timedelta(seconds=300))
assert fetching == fetched
print('Done in %d seconds, fetched %s URLs.' % (
time.time() - start, len(fetched)))
if __name__ == '__main__':
io_loop = ioloop.IOLoop.current()
io_loop.run_sync(main)