|
def | __init__ (self, cfgParser) |
|
def | process (self, drceObject) |
|
def | fieldsRecalculating (self, sites) |
|
def | collectedURLsRecalculating (self, siteId) |
|
def | customRequest (self, query, dbName, includeFieldsNames=dbi.EventObjects.CustomRequest.SQL_BY_INDEX) |
|
def | urlUpdate (self, urlUpdateObject, criterionsWere=None, criterionsLimit=None, criterionsOrder=None) |
|
def | urlStatus (self, urlStatusObject, useMd5Resolving=False) |
|
def | urlContent (self, items) |
|
def | putURLContent (self, urlPut_list) |
|
def | urlNew (self, urlNewObject) |
|
def | siteNewOrUpdate (self, siteObject, properties=None, filters=None, siteId=None, stype=dc.EventObjects.SiteUpdate) |
|
def | siteStatus (self, siteStatusObject) |
|
def | proxyStatus (self, proxyStatusObject) |
|
def | proxyUpdate (self, proxyUpdateObject) |
|
def | putAttributes (self, attributes) |
|
Definition at line 25 of file DBTasksWrapper.py.
◆ __init__()
def dc_crawler.DBTasksWrapper.DBTasksWrapper.__init__ |
( |
|
self, |
|
|
|
cfgParser |
|
) |
| |
Definition at line 31 of file DBTasksWrapper.py.
32 self.dbTask = DBTasksManager(cfgParser)
33 self.fieldRecalculator = DBFieldRecalculator()
def __init__(self)
constructor
◆ collectedURLsRecalculating()
def dc_crawler.DBTasksWrapper.DBTasksWrapper.collectedURLsRecalculating |
( |
|
self, |
|
|
|
siteId |
|
) |
| |
Definition at line 59 of file DBTasksWrapper.py.
59 def collectedURLsRecalculating(self, siteId):
61 self.fieldRecalculator.updateCollectedURLs(siteId, self.dbTask.executeQuery)
◆ customRequest()
Definition at line 69 of file DBTasksWrapper.py.
69 def customRequest(self, query, dbName, includeFieldsNames=dbi.EventObjects.CustomRequest.SQL_BY_INDEX):
73 customObject.includeFieldsNames = includeFieldsNames
75 retDRCE = self.dbTask.
process(drceObject)
76 if retDRCE.eventType == dc.Constants.EVENT_TYPES.SQL_CUSTOM_RESPONSE:
77 if retDRCE.eventObject.rid == self.rid:
78 if retDRCE.eventObject.errString
is None:
79 ret = retDRCE.eventObject.result
81 logger.error(
"SQL_CUSTOM_RESPONSE >>> Resonse error = " + retDRCE.eventObject.errString)
83 logger.error(
"SQL_CUSTOM_RESPONSE >>> Wrong response rid")
85 logger.error(
"SQL_CUSTOM_RESPONSE >>> Wrong response type")
◆ fieldsRecalculating()
def dc_crawler.DBTasksWrapper.DBTasksWrapper.fieldsRecalculating |
( |
|
self, |
|
|
|
sites |
|
) |
| |
Definition at line 46 of file DBTasksWrapper.py.
46 def fieldsRecalculating(self, sites):
48 fieldRecalculatingObjList = []
52 fieldRecalculatingObjList)
53 retDRCE = self.dbTask.
process(drceObject)
◆ process()
def dc_crawler.DBTasksWrapper.DBTasksWrapper.process |
( |
|
self, |
|
|
|
drceObject |
|
) |
| |
◆ proxyStatus()
def dc_crawler.DBTasksWrapper.DBTasksWrapper.proxyStatus |
( |
|
self, |
|
|
|
proxyStatusObject |
|
) |
| |
Definition at line 223 of file DBTasksWrapper.py.
223 def proxyStatus(self, proxyStatusObject):
227 if proxyStatusObject
is None:
228 logger.error(
"PROXY_STATUS: proxyObject is None!")
230 if isinstance(proxyStatusObject, list):
231 proxyStatusObjectList = proxyStatusObject
233 proxyStatusObjectList = [proxyStatusObject]
236 retDRCE = self.dbTask.
process(drceObject)
237 if retDRCE.eventType == dc.Constants.EVENT_TYPES.PROXY_STATUS_RESPONSE:
238 ret = retDRCE.eventObject
240 logger.error(
"PROXY_STATUS_RESPONSE: Wrong type of response object!")
◆ proxyUpdate()
def dc_crawler.DBTasksWrapper.DBTasksWrapper.proxyUpdate |
( |
|
self, |
|
|
|
proxyUpdateObject |
|
) |
| |
Definition at line 249 of file DBTasksWrapper.py.
249 def proxyUpdate(self, proxyUpdateObject):
253 if proxyUpdateObject
is not None:
254 if isinstance(proxyUpdateObject, list):
255 proxyUpdateObjectList = proxyUpdateObject
257 proxyUpdateObjectList = [proxyUpdateObject]
260 retDRCE = self.dbTask.
process(drceObject)
261 if retDRCE.eventType == dc.Constants.EVENT_TYPES.PROXY_UPDATE_RESPONSE:
262 ret = retDRCE.eventObject
264 logger.error(
"PROXY_UPDATE_RESPONSE >>> Wrong response type")
266 logger.error(
"PROXY_UPDATE >>> Not enough incoming data")
◆ putAttributes()
def dc_crawler.DBTasksWrapper.DBTasksWrapper.putAttributes |
( |
|
self, |
|
|
|
attributes |
|
) |
| |
Definition at line 275 of file DBTasksWrapper.py.
275 def putAttributes(self, attributes):
277 attributesList = attributes
if isinstance(attributes, list)
else [attributes]
280 responseDRCESyncTasksCover = self.dbTask.
process(drceSyncTasksCoverObj)
281 if responseDRCESyncTasksCover.eventType != dc.Constants.EVENT_TYPES.ATTR_SET_RESPONSE:
282 logger.error(
"Operation 'ATTR_SET' has error: Wrong response type")
◆ putURLContent()
def dc_crawler.DBTasksWrapper.DBTasksWrapper.putURLContent |
( |
|
self, |
|
|
|
urlPut_list |
|
) |
| |
Definition at line 142 of file DBTasksWrapper.py.
142 def putURLContent(self, urlPut_list):
146 responseDRCESyncTasksCover = self.dbTask.
process(drceSyncTasksCoverObj)
147 if responseDRCESyncTasksCover.eventType == dc.Constants.EVENT_TYPES.URL_PUT_RESPONSE:
148 for obj
in responseDRCESyncTasksCover.eventObject:
149 logger.debug(
"URL_PUT_RESPONSE: %s",
varDump(obj))
151 logger.error(
"URL_PUT_RESPONSE >>> Wrong response type")
153 if responseDRCESyncTasksCover.eventType != dc.Constants.EVENT_TYPES.URL_PUT_RESPONSE:
154 logger.error(
"URL_PUT_RESPONSE >>> Wrong response type")
def varDump(obj, stringify=True, strTypeMaxLen=256, strTypeCutSuffix='...', stringifyType=1, ignoreErrors=False, objectsHash=None, depth=0, indent=2, ensure_ascii=False, maxDepth=10)
◆ siteNewOrUpdate()
def dc_crawler.DBTasksWrapper.DBTasksWrapper.siteNewOrUpdate |
( |
|
self, |
|
|
|
siteObject, |
|
|
|
properties = None , |
|
|
|
filters = None , |
|
|
|
siteId = None , |
|
|
|
stype = dc.EventObjects.SiteUpdate |
|
) |
| |
Definition at line 175 of file DBTasksWrapper.py.
175 def siteNewOrUpdate(self, siteObject, properties=None, filters=None, siteId=None, stype=dc.EventObjects.SiteUpdate):
179 reqType = dc.Constants.EVENT_TYPES.SITE_NEW
180 respType = dc.Constants.EVENT_TYPES.SITE_NEW_RESPONSE
182 reqType = dc.Constants.EVENT_TYPES.SITE_UPDATE
183 respType = dc.Constants.EVENT_TYPES.SITE_UPDATE_RESPONSE
184 if siteObject
is None:
185 if siteId
is not None:
186 siteObject = stype(siteId)
187 if properties
is not None:
188 siteObject.properties = properties
189 if filters
is not None:
190 siteObject.filters = filters
191 if siteObject
is not None:
193 retDRCE = self.dbTask.
process(drceObject)
194 logger.debug(
"SITE_NEW_UPDATE_RESPONSE retDRCE: " +
varDump(retDRCE))
195 if retDRCE.eventType == respType:
196 ret = retDRCE.eventObject.statuses
198 logger.error(
"SITE_NEW_UPDATE_RESPONSE >>> Wrong response type")
200 logger.error(
"SITE_NEW_UPDATE >>> siteObject is None!")
def varDump(obj, stringify=True, strTypeMaxLen=256, strTypeCutSuffix='...', stringifyType=1, ignoreErrors=False, objectsHash=None, depth=0, indent=2, ensure_ascii=False, maxDepth=10)
◆ siteStatus()
def dc_crawler.DBTasksWrapper.DBTasksWrapper.siteStatus |
( |
|
self, |
|
|
|
siteStatusObject |
|
) |
| |
Definition at line 204 of file DBTasksWrapper.py.
207 if siteStatusObject
is not None:
209 retDRCE = self.dbTask.
process(drceObject)
210 if retDRCE.eventType == dc.Constants.EVENT_TYPES.SITE_STATUS_RESPONSE:
211 ret = retDRCE.eventObject
213 logger.error(
"SITE_STATUS_RESPONSE >>> Wrong response type")
215 logger.error(
"SITE_STATUS >>> Not enough incoming data")
◆ urlContent()
def dc_crawler.DBTasksWrapper.DBTasksWrapper.urlContent |
( |
|
self, |
|
|
|
items |
|
) |
| |
Definition at line 131 of file DBTasksWrapper.py.
131 def urlContent(self, items):
134 retDRCE = self.dbTask.
process(drceSyncTasksCoverObj)
135 if retDRCE.eventType == dc.Constants.EVENT_TYPES.URL_CONTENT_RESPONSE:
136 ret = retDRCE.eventObject
138 logger.error(
"URL_CONTENT_RESPONSE >>> Wrong response type")
◆ urlNew()
def dc_crawler.DBTasksWrapper.DBTasksWrapper.urlNew |
( |
|
self, |
|
|
|
urlNewObject |
|
) |
| |
Definition at line 159 of file DBTasksWrapper.py.
159 def urlNew(self, urlNewObject):
162 if isinstance(urlNewObject, list):
163 urlNewList = urlNewObject
165 urlNewList = [urlNewObject]
167 retDRCE = self.dbTask.
process(drceObject)
168 if retDRCE.eventType == dc.Constants.EVENT_TYPES.URL_NEW_RESPONSE:
169 ret = len([i
for i
in retDRCE.eventObject.statuses
if i == 0])
171 logger.error(
"URL_NEW_RESPONSE >>> Wrong response type")
◆ urlStatus()
def dc_crawler.DBTasksWrapper.DBTasksWrapper.urlStatus |
( |
|
self, |
|
|
|
urlStatusObject, |
|
|
|
useMd5Resolving = False |
|
) |
| |
Definition at line 117 of file DBTasksWrapper.py.
117 def urlStatus(self, urlStatusObject, useMd5Resolving=False):
121 urlStatusObject.urlType = dc.EventObjects.URLStatus.URL_TYPE_MD5
123 retDRCE = self.dbTask.
process(drceObject)
124 if retDRCE.eventType == dc.Constants.EVENT_TYPES.URL_STATUS_RESPONSE:
125 ret = retDRCE.eventObject
127 logger.error(
"URL_STATUS_RESPONSE >>> Wrong response type")
◆ urlUpdate()
def dc_crawler.DBTasksWrapper.DBTasksWrapper.urlUpdate |
( |
|
self, |
|
|
|
urlUpdateObject, |
|
|
|
criterionsWere = None , |
|
|
|
criterionsLimit = None , |
|
|
|
criterionsOrder = None |
|
) |
| |
Definition at line 89 of file DBTasksWrapper.py.
89 def urlUpdate(self, urlUpdateObject, criterionsWere=None, criterionsLimit=None, criterionsOrder=None):
92 if isinstance(urlUpdateObject, list):
93 urlUpdateObjectList = urlUpdateObject
95 urlUpdateObjectList = [urlUpdateObject]
96 if criterionsWere
is not None or criterionsLimit
is not None or criterionsOrder
is not None:
97 urlUpdateObject.criterions = {}
98 if criterionsWere
is not None:
99 urlUpdateObject.criterions[dc.EventObjects.URLFetch.CRITERION_WHERE] = criterionsWere
100 if criterionsLimit
is not None:
101 urlUpdateObject.criterions[dc.EventObjects.URLFetch.CRITERION_LIMIT] = criterionsLimit
102 if criterionsOrder
is not None:
103 urlUpdateObject.criterions[dc.EventObjects.URLFetch.CRITERION_ORDER] = criterionsOrder
106 retDRCE = self.dbTask.
process(drceObject)
107 if retDRCE.eventType == dc.Constants.EVENT_TYPES.URL_UPDATE_RESPONSE:
108 if hasattr(retDRCE.eventObject.statuses,
'__iter__')
and len(retDRCE.eventObject.statuses) > 0
and \
109 retDRCE.eventObject.statuses[0]
is False:
110 logger.error(
"URL_UPDATE_RESPONSE >>> Operation failure, look db-task log")
111 ret = len([i
for i
in retDRCE.eventObject.statuses
if i])
113 logger.error(
"URL_UPDATE_RESPONSE >>> Wrong response type")
◆ affect_db
dc_crawler.DBTasksWrapper.DBTasksWrapper.affect_db |
◆ dbTask
dc_crawler.DBTasksWrapper.DBTasksWrapper.dbTask |
◆ fieldRecalculator
dc_crawler.DBTasksWrapper.DBTasksWrapper.fieldRecalculator |
◆ rid
dc_crawler.DBTasksWrapper.DBTasksWrapper.rid |
The documentation for this class was generated from the following file: