def download_video_page_async_single_process(self):
key = 'new_tudou_video_url'
pid = os.getpid()
while connect_with_redis.length_of_set(key) > 0:
self.download_video_page_async()
print("platform: %s, action: download video page, pid: %s" %
(self.platform, pid))
def download_video_page_async_single_process(self):
pid = os.getpid()
key = 'iqiyi_video_url'
while connect_with_redis.length_of_set(key) > 0:
loop = asyncio.get_event_loop()
loop.run_until_complete(self.get_video_page(loop))
print("platform: %s, action: download video page, process_id: %s" %
(self.platform, pid))
def download_video_page(platform):
crawler_initialization = get_crawler(platform)
crawler = crawler_initialization()
if platform == '腾讯视频':
key = 'v_qq_url_dict'
else:
key= "%s_%s" % (platform, data_cate)
while True:
if connect_with_redis.length_of_set(key) > 0:
# pid_num = connect_with_redis.length_of_set(key=key_set)
# if pid_num < 20:
# process_num = int(20-pid_num)
crawler.download_video_page_async_multi_process()
# else:
# print("%s processes is working on %s" % (pid_num, platform))
# time.sleep(20)
else:
print("no %s url [dict] in redis" % platform)
time.sleep(300)