|
@@ -17,7 +17,7 @@ def scrape():
|
17
|
17
|
|
18
|
18
|
# 如果没有待爬取的直播,则等一秒,循环
|
19
|
19
|
if room_info is None:
|
20
|
|
- time.sleep(1)
|
|
20
|
+ time.sleep(0.1)
|
21
|
21
|
continue
|
22
|
22
|
|
23
|
23
|
# 判断是否到达爬取时间以确定是否需要爬取弹幕,并直接塞回队列尾部
|
|
@@ -79,7 +79,7 @@ def scrape():
|
79
|
79
|
rds.push_data_list(data)
|
80
|
80
|
else:
|
81
|
81
|
print('直播ID%s %d秒前曾爬取过,暂无需继续抓取' % (room_id, time_diff))
|
82
|
|
- time.sleep(1)
|
|
82
|
+ time.sleep(0.1)
|
83
|
83
|
rds.push_request_id(json.dumps(room_dict))
|
84
|
84
|
|
85
|
85
|
except Exception as e:
|
|
@@ -95,6 +95,6 @@ if __name__ == "__main__":
|
95
|
95
|
|
96
|
96
|
print(time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()) + ' ' + ' 开始执行,待爬取直播队列长度:' + str(rds.get_len()))
|
97
|
97
|
|
98
|
|
- for i in range(1, 50):
|
|
98
|
+ for i in range(1, 80):
|
99
|
99
|
task = threading.Thread(target=scrape, name=i)
|
100
|
100
|
task.start() # 准备就绪,等待cpu执行
|