__init__(self, siteId, urlString, urlType=URLStatus.URL_TYPE_URL, stateField=None, statusField=None, normalizeMask=URL.URL_NORMALIZE_MASK, urlObject=None) | dc.EventObjects.URLUpdate | |
dc::EventObjects::URL.__init__(self, siteId, url, state=STATE_ENABLED, urlUpdate=None, normalizeMask=URL_NORMALIZE_MASK) | dc.EventObjects.URL | |
app::Utils::JsonSerializable.__init__(self) | app.Utils.JsonSerializable | |
attributes | dc.EventObjects.URLUpdate | |
batchId | dc.EventObjects.URLUpdate | |
CDate | dc.EventObjects.URLUpdate | |
chainId | dc.EventObjects.URLUpdate | |
charset | dc.EventObjects.URLUpdate | |
classifierMask | dc.EventObjects.URLUpdate | |
CONTENT_EMPTY | dc.EventObjects.URL | static |
CONTENT_STORED_ON_DISK | dc.EventObjects.URL | static |
CONTENT_TYPE_TEXT_HTML | dc.EventObjects.URL | static |
CONTENT_TYPE_UNDEFINED | dc.EventObjects.URL | static |
contentMask | dc.EventObjects.URL | |
contentType | dc.EventObjects.URLUpdate | |
contentURLMd5 | dc.EventObjects.URLUpdate | |
crawled | dc.EventObjects.URLUpdate | |
crawlingTime | dc.EventObjects.URLUpdate | |
criterions | dc.EventObjects.URLUpdate | |
depth | dc.EventObjects.URLUpdate | |
errorMask | dc.EventObjects.URLUpdate | |
eTag | dc.EventObjects.URLUpdate | |
fillMD5(self, urlString, urlType) | dc.EventObjects.URLUpdate | |
freq | dc.EventObjects.URLUpdate | |
getURL(self, normalizeMask=URL_NORMALIZE_MASK) | dc.EventObjects.URL | |
httpCode | dc.EventObjects.URLUpdate | |
httpMethod | dc.EventObjects.URLUpdate | |
httpTimeout | dc.EventObjects.URLUpdate | |
json_serial(obj) | app.Utils.JsonSerializable | static |
lastModified | dc.EventObjects.URLUpdate | |
linksE | dc.EventObjects.URLUpdate | |
linksI | dc.EventObjects.URLUpdate | |
maxURLsFromPage | dc.EventObjects.URLUpdate | |
mRate | dc.EventObjects.URLUpdate | |
mRateCounter | dc.EventObjects.URLUpdate | |
parentMd5 | dc.EventObjects.URLUpdate | |
pDate | dc.EventObjects.URL | |
priority | dc.EventObjects.URLUpdate | |
processed | dc.EventObjects.URLUpdate | |
processingDelay | dc.EventObjects.URLUpdate | |
processingTime | dc.EventObjects.URLUpdate | |
rawContentMd5 | dc.EventObjects.URLUpdate | |
requestDelay | dc.EventObjects.URLUpdate | |
SITE_SELECT_TYPE_AUTO | dc.EventObjects.URL | static |
SITE_SELECT_TYPE_EXPLICIT | dc.EventObjects.URL | static |
SITE_SELECT_TYPE_NONE | dc.EventObjects.URL | static |
SITE_SELECT_TYPE_QUALIFY_URL | dc.EventObjects.URL | static |
siteId | dc.EventObjects.URLUpdate | |
siteSelect | dc.EventObjects.URLUpdate | |
size | dc.EventObjects.URLUpdate | |
state | dc.EventObjects.URLUpdate | |
STATE_DISABLED | dc.EventObjects.URL | static |
STATE_ENABLED | dc.EventObjects.URL | static |
STATE_ERROR | dc.EventObjects.URL | static |
status | dc.EventObjects.URLUpdate | |
STATUS_CRAWLED | dc.EventObjects.URL | static |
STATUS_CRAWLING | dc.EventObjects.URL | static |
STATUS_NEW | dc.EventObjects.URL | static |
STATUS_PROCESSED | dc.EventObjects.URL | static |
STATUS_PROCESSING | dc.EventObjects.URL | static |
STATUS_SELECTED_CRAWLING | dc.EventObjects.URL | static |
STATUS_SELECTED_CRAWLING_INCREMENTAL | dc.EventObjects.URL | static |
STATUS_SELECTED_PROCESSING | dc.EventObjects.URL | static |
STATUS_UNDEFINED | dc.EventObjects.URL | static |
tagsCount | dc.EventObjects.URLUpdate | |
tagsMask | dc.EventObjects.URLUpdate | |
tcDate | dc.EventObjects.URLUpdate | |
toJSON(self) | app.Utils.JsonSerializable | |
totalTime | dc.EventObjects.URLUpdate | |
type | dc.EventObjects.URLUpdate | |
TYPE_CHAIN | dc.EventObjects.URL | static |
TYPE_FETCHED | dc.EventObjects.URL | static |
TYPE_NEW_SITE | dc.EventObjects.URL | static |
TYPE_REAL_TIME_CRAWLER | dc.EventObjects.URL | static |
TYPE_REGULAR | dc.EventObjects.URL | static |
TYPE_REGULAR_EXT | dc.EventObjects.URL | static |
TYPE_SINGLE | dc.EventObjects.URL | static |
UDate | dc.EventObjects.URLUpdate | |
url | dc.EventObjects.URLUpdate | |
URL_NORMALIZE_MASK | dc.EventObjects.URL | static |
urlMd5 | dc.EventObjects.URLUpdate | |
urlPut | dc.EventObjects.URL | |
urlUpdate | dc.EventObjects.URL | |