def __init__(
self,
stddatatype: EStandardDataType,
platform: str,
cmdstatus: ECommandStatus,
cmdrcvmsg: str = None,
currenttime: str = None,
):
OutputData.__init__(self, platform, stddatatype)
OutputDataSeg.__init__(self)
self._cmdstatus: ECommandStatus = None
if isinstance(cmdstatus, ECommandStatus):
self._cmdstatus = cmdstatus
else:
try:
self._cmdstatus = ECommandStatus(int(cmdstatus))
except Exception:
pass
self._cmdrcvmsg: str = None
if isinstance(cmdrcvmsg, str) and cmdrcvmsg != '':
self._cmdrcvmsg = cmdrcvmsg
# 当前时间, 字符串的datetime
self._time: str = datetime.now(
pytz.timezone('Asia/Shanghai')).strftime('%Y-%m-%d %H:%M:%S')
if currenttime is not None and currenttime != '':
self._time = currenttime
def __init__(self, task: IscoutTask, level: int, parentobj: str,
parentobjtype: EObjectType, url: str, keyword: str):
if not isinstance(task, IscoutTask):
raise Exception("Invalid iscouttask")
# if not isinstance(level, int):
# raise Exception("Invalid level")
if not isinstance(parentobjtype, EObjectType):
raise Exception("Invalid parentobjtype")
if not isinstance(url, str) or url == '':
raise Exception("Invalid url")
if not isinstance(keyword, str) or keyword == '':
raise Exception("Invalid keyword")
OutputData.__init__(self, task.platform,
EStandardDataType.IScoutScreenShotSE)
OutputDataSeg.__init__(self)
# OutputData.__init__(self, task._platform, EStandardDataType.IScoutScreenShotUrl)
self._task: IscoutTask = task
self._level: int = level
self._parentobj: str = parentobj
self.parentobjtype: EObjectType = parentobjtype
self.url = url
self.keyword: str = keyword
# self.platform = platform
# self.datatype: EStandardDataType = datatype
self._stream: io.RawIOBase = None
def __init__(self, task: IscoutTask, platform: str, url: str, source: str,
rsctp: EResourceType):
if not isinstance(task, IscoutTask):
raise Exception("Invalid IscoutTask")
if not isinstance(platform, str):
raise Exception("Invalid platform")
if not isinstance(url, str):
raise Exception("Invalid url")
if not isinstance(source, str):
raise Exception("Invalid source")
Resource.__init__(self, url, rsctp)
OutputData.__init__(self, platform,
EStandardDataType.IScoutNetworkResource)
OutputDataSeg.__init__(self)
self._task: IscoutTask = task
self._source: str = source
self.resourceid: str = None
self.filename: str = None
self.extension: str = None
self.remark: str = None
self.stream = None
def __init__(self,
suffix,
datatype: EStandardDataType,
task: Task,
apptype: int,
clientid: str,
is_muti_seg: bool = False):
UniqueData.__init__(self, task, apptype)
OutputData.__init__(self, self._task.platform, datatype)
OutputDataSeg.__init__(self)
if not isinstance(clientid, str) or clientid == "":
raise Exception("Invalid param 'clientid' for FeedDataBase")
self._clientid: str = clientid
# 东8区时间
self.time = datetime.datetime.now(
pytz.timezone('Asia/Shanghai')).strftime('%Y-%m-%d %H:%M:%S')
if not isinstance(suffix, str) or suffix == "":
raise Exception("Suffix is invalid.")
self._is_muti_seg: bool = False
if isinstance(is_muti_seg, bool):
self._is_muti_seg = is_muti_seg
self._suffix: str = suffix # 文件后缀
self.__innerdatas: list = [] # 内部多段数据
self.__innerdata_locker = threading.Lock()
self._io_stream = None # 从网上下载回来的数据流
# 统一使用ha来获取head里面的length
# resp = ha.get_response()
# lengthn = resp.headers.get('Content-Length')
# responseio = ResponseIO(resp)
self.stream_length = 0 # 下载的文件流大小，用来做文件大小过滤
self.remarks = None # 用于将一些爬取过程中有用的东西记录下来