def checkAllLz(filePath, taskResultId):
taskResult = TaskResult.getOne(TaskResult.taskResultId == taskResultId)
delayDay = taskResult.taskId.intervalDay
#根据当前任务编号目录获取该目录下的所有xml文件
print '目录路径:',filePath
fnames=os.listdir(filePath)
for name in fnames:
xmlName = filePath+'/'+name
print 'xmlName:',xmlName
data = parseXMLFile(xmlName, 'CheckItem')
print 'data:',data
# 将需要检查的信息入库
for d in data:
cname = d.get('cname')
url = d.get('url')
if url != '':
if url[-1] == '/':
url = url.replace('http://', '')[0:-1].replace(' ','')
if cname!='':
cname = cname.replace(' ','')
webArea = d.get('area')
webtype = d.get('WebType')
# 检查更新company
if Company.getOne(Company.coname == cname) is None:
c = Company()
c.coname = cname
c.save(force_insert=True)
# 检查更新website
if Website.getOne(Website.domain == url) is not None:
q = Website.update(domain=url, type=webtype, area=webArea).where(Website.domain == url)
q.execute()
else:
com = Company.getOne(Company.coname == cname)
w = Website()
w.regID = com
w.domain = url
w.area = webArea
w.type = webtype
w.save(force_insert=True)
updateWeb = Website.getOne(Website.domain == url)
subTask = TaskInfo()
subTask.taskResultId = taskResult
subTask.webId = updateWeb
subTask.state = '1'
subTask.save(force_insert=True)
taskResultId = str(taskResultId)
if delayDay > 0:
# 需要周期执行的任务
executeMultiTaskInfo(taskResultId)
else:
#logger.debug("开始调用单次任务")
# 单次执行的任务
executeSingleTaskInfo(taskResultId)
def intervalFetch(taskResultId, lastTaskResultId, delayTag):
# 获取上次任务taskResultId
taskInfos = TaskInfo.select().where(TaskInfo.taskResultId == lastTaskResultId)
for task in taskInfos:
subTask = TaskInfo()
subTask.taskResultId = taskResultId
subTask.state = ''
subTask.cname = task.cname
subTask.url = task.url
subTask.save(force_insert=True)
fetchCycle.apply_async((subTask.id, taskResultId, delayTag), queue="celery")