def fetch_url():
suffix = yield q.get()
current_url = baseURL + suffix
try:
if suffix not in fetched:
user = suffix[1::]
full_name, email, location = yield get_info(current_url)
print user, email, location, len(fetched), q.qsize()
DBAccessor.insert_info(user, full_name, email, location)
urls = yield get_followers_url(current_url)
fetched.add(current_url)
for new_url in urls:
if new_url not in fetched and q.qsize() < queueSize:
yield q.put(new_url)
finally:
q.task_done()
def main():
q = queues.Queue()
start = time.time()
fetched = DBAccessor.get_all_user_path()
@gen.coroutine
def fetch_url():
suffix = yield q.get()
current_url = baseURL + suffix
try:
if suffix not in fetched:
user = suffix[1::]
full_name, email, location = yield get_info(current_url)
print user, email, location, len(fetched), q.qsize()
DBAccessor.insert_info(user, full_name, email, location)
urls = yield get_followers_url(current_url)
fetched.add(current_url)
for new_url in urls:
if new_url not in fetched and q.qsize() < queueSize:
yield q.put(new_url)
finally:
q.task_done()
@gen.coroutine
def worker():
while True:
yield fetch_url()
q.put(rootURL)
print 'start working...'
# Start workers, then wait for the work queue to be empty.
for _ in range(concurrency):
worker()
yield q.join(timeout=timedelta(seconds=2000))
print('Done in %d seconds, fetched %s URLs.' % (
time.time() - start, len(fetched)))
for new_url in urls:
if new_url not in fetched and q.qsize() < queueSize:
yield q.put(new_url)
finally:
q.task_done()
@gen.coroutine
def worker():
while True:
yield fetch_url()
q.put(rootURL)
print 'start working...'
# Start workers, then wait for the work queue to be empty.
for _ in range(concurrency):
worker()
yield q.join(timeout=timedelta(seconds=2000))
print('Done in %d seconds, fetched %s URLs.' % (
time.time() - start, len(fetched)))
if __name__ == '__main__':
import logging
logging.basicConfig()
io_loop = ioloop.IOLoop.current()
io_loop.run_sync(main)
DBAccessor.close_db()
