def main():
thread_count = 3
pre_threads = []
initdb() # 初始化redis数据库
initGlobalArgs()
initContentUrl_dict() # 初始化去重表
log_thread = log.LogThread() # 启动日志记录线程
log_thread.start()
QueryWebsiteUrl_thread = QueryWebsiteUrlThread() # 启动读取网站地址线程
QueryWebsiteUrl_thread.start()
pre_threads.append(QueryWebsiteUrl_thread)
filterContentUrl_thread = FilterContentUrlThread() # 启动爬取内容地址线程
filterContentUrl_thread.start()
pre_threads.append(filterContentUrl_thread)
for i in range(thread_count):
thread = FilterContentInfoThread()
thread.start()
pre_threads.append(thread)
unrecognizedWebsiteUrl_thread = UnrecognizedWebsiteUrl_Thread()
unrecognizedWebsiteUrl_thread.start()
pre_threads.append(unrecognizedWebsiteUrl_thread)
unrecognizedContentUrl_thread = UnrecognizedContentUrl_Thread()
unrecognizedContentUrl_thread.start()
pre_threads.append(unrecognizedContentUrl_thread)
while not global_EXIT: pass
time.sleep(5)
saveWebsiteDelaytime() # 保存各网站的延迟时间
for t in pre_threads:
t.join()
log.logMsg(LogType.success, "--------------------bye---------------------\n")
while not Cache.qempty(cache.log_queue): pass # 等待把所有日志写到文件中
Cache.setDict(cache.globalArgs_dict, "LogThread_EXIT", True)
log_thread.join()
if db: db.dispose()
def run(self):
while not global_EXIT:
try:
if Cache.qempty(cache.websiteUrl_queue):
records = mysql.Mysql.queryWebsiteUrl()
for record in records: # record: id,url,xpath,detail,delay_time
record = [str(item) for item in record]
self.initWebsite_delay_dict(record)
t = threading.Thread(target=self.putRecord, args=(record,))
t.setDaemon(True)
t.start()
except Exception as e:
log.logMsg(LogType.error, "[QueryWebsiteUrlThread] %s" % (traceback.format_exc()))
for i in range(60):
if global_EXIT: break
time.sleep(1)
