HCE Project Python language Distributed Tasks Manager Application, Distributed Crawler Application and client API bindings.
2.0.0-chaika
Hierarchical Cluster Engine Python language binding
|
Public Member Functions | |
def | __init__ (self, keyValueStorageDir, rawDataDir, dBDataTask) |
def | process (self, urlCleanups, queryCallback) |
def | extractUrlByCriterions (self, siteId, isUrlExtract, criterions, queryCallback, dbName=Constants.SECONDARY_DB_ID, tablePrefix=Constants.DC_URLS_TABLE_NAME_TEMPLATE) |
def | getSiteFields (self, siteId, queryCallback, dbName=Constants.PRIMARY_DB_ID) |
def | deleteFromDataStorage (self, urlCleanup, queryCallback) |
def | deleteFromRawStorage (self, urlCleanup) |
def | updateMysqlDB (self, urlCleanup, queryCallback, siteId) |
def | copyUrlToDeleteDB (self, urlCleanup, queryCallback) |
Public Member Functions inherited from dc_db.BaseTask.BaseTask | |
def | isSiteExist (self, siteId, queryCallback, userId=None) |
def | generateCriterionSQL (self, criterions, additionWhere=None, siteId=None) |
def | fetchByCriterions (self, criterions, queryCallback) |
def | dbLock (self, mutexName, queryCallback, sleepTime=1, mutexLockTTL=Constants.DEFAULT_LOCK_TTL) |
def | dbUnlock (self, mutexName, queryCallback) |
def | createUrlsInsertQuery (self, siteId, localKeys, localValues) |
def | copyUrlsToDcUrls (self, siteId, queryCallback) |
def | statisticLogUpdate (self, localObj, urlMd5, siteId, status, queryCallback, isInsert=False) |
def | calculateMd5FormUrl (self, url, urlType, useNormilize=False) |
Public Attributes | |
keyValueStorageDir | |
rawDataDir | |
recalculator | |
dBDataTask | |
urlMd5 | |
Additional Inherited Members | |
Static Public Member Functions inherited from dc_db.BaseTask.BaseTask | |
def | readValueFromSiteProp (siteId, propName, queryCallback, urlMd5=None) |
Definition at line 29 of file URLCleanupTask.py.
def dc_db.URLCleanupTask.URLCleanUpTask.__init__ | ( | self, | |
keyValueStorageDir, | |||
rawDataDir, | |||
dBDataTask | |||
) |
Definition at line 36 of file URLCleanupTask.py.
def dc_db.URLCleanupTask.URLCleanUpTask.copyUrlToDeleteDB | ( | self, | |
urlCleanup, | |||
queryCallback | |||
) |
Definition at line 190 of file URLCleanupTask.py.
def dc_db.URLCleanupTask.URLCleanUpTask.deleteFromDataStorage | ( | self, | |
urlCleanup, | |||
queryCallback | |||
) |
Definition at line 136 of file URLCleanupTask.py.
def dc_db.URLCleanupTask.URLCleanUpTask.deleteFromRawStorage | ( | self, | |
urlCleanup | |||
) |
Definition at line 150 of file URLCleanupTask.py.
def dc_db.URLCleanupTask.URLCleanUpTask.extractUrlByCriterions | ( | self, | |
siteId, | |||
isUrlExtract, | |||
criterions, | |||
queryCallback, | |||
dbName = Constants.SECONDARY_DB_ID , |
|||
tablePrefix = Constants.DC_URLS_TABLE_NAME_TEMPLATE |
|||
) |
Definition at line 99 of file URLCleanupTask.py.
def dc_db.URLCleanupTask.URLCleanUpTask.getSiteFields | ( | self, | |
siteId, | |||
queryCallback, | |||
dbName = Constants.PRIMARY_DB_ID |
|||
) |
def dc_db.URLCleanupTask.URLCleanUpTask.process | ( | self, | |
urlCleanups, | |||
queryCallback | |||
) |
Definition at line 50 of file URLCleanupTask.py.
def dc_db.URLCleanupTask.URLCleanUpTask.updateMysqlDB | ( | self, | |
urlCleanup, | |||
queryCallback, | |||
siteId | |||
) |
Definition at line 169 of file URLCleanupTask.py.
dc_db.URLCleanupTask.URLCleanUpTask.dBDataTask |
Definition at line 41 of file URLCleanupTask.py.
dc_db.URLCleanupTask.URLCleanUpTask.keyValueStorageDir |
Definition at line 38 of file URLCleanupTask.py.
dc_db.URLCleanupTask.URLCleanUpTask.rawDataDir |
Definition at line 39 of file URLCleanupTask.py.
dc_db.URLCleanupTask.URLCleanUpTask.recalculator |
Definition at line 40 of file URLCleanupTask.py.
dc_db.URLCleanupTask.URLCleanUpTask.urlMd5 |
Definition at line 42 of file URLCleanupTask.py.