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
dc_crawler.CollectURLs.CollectURLs Member List

This is the complete list of members for dc_crawler.CollectURLs.CollectURLs, including all inherited members.

__init__(self, isAbortedByTTL=None)dc_crawler.CollectURLs.CollectURLs
_normalize_attributes(self, kv)dc_crawler.CollectURLs.CollectURLsprivate
autoDetectMimedc_crawler.CollectURLs.CollectURLs
autoRemovePropsdc_crawler.CollectURLs.CollectURLs
baseUrldc_crawler.CollectURLs.CollectURLs
batchItemdc_crawler.CollectURLs.CollectURLs
BINARY_CONTENT_TYPE_PATTERNdc_crawler.CollectURLs.CollectURLsstatic
checkFieldsIsNone(self)dc_crawler.CollectURLs.CollectURLs
COLLECT_POST_DATAdc_crawler.CollectURLs.CollectURLsstatic
COLLECT_POST_DATA_NAMEdc_crawler.CollectURLs.CollectURLsstatic
crawledResourcedc_crawler.CollectURLs.CollectURLs
dbWrapperdc_crawler.CollectURLs.CollectURLs
DC_URLS_TABLE_PREFIXdc_crawler.CollectURLs.CollectURLsstatic
DETECT_MIME_COLLECTED_URLdc_crawler.CollectURLs.CollectURLsstatic
DETECT_MIME_MAIN_CONTENTdc_crawler.CollectURLs.CollectURLsstatic
DETECT_MIME_TIMEOUTdc_crawler.CollectURLs.CollectURLsstatic
domdc_crawler.CollectURLs.CollectURLs
evaluateDateMacro(self, localPattern, dateFromat)dc_crawler.CollectURLs.CollectURLs
extractFormURL(self, dom, siteProperties)dc_crawler.CollectURLs.CollectURLs
feeddc_crawler.CollectURLs.CollectURLs
feedElementsProcessing(self, urlMd5, httpCode, elemUrl, localSiteId, localUrlObj, localUrl, params, maxURLsFromPage, rootFeed=False)dc_crawler.CollectURLs.CollectURLs
feedItemsdc_crawler.CollectURLs.CollectURLs
feedparserParseDateFixes(self, aDateString)dc_crawler.CollectURLs.CollectURLs
filtersApply(inputFilters, subject, depth, wrapper, siteId, fields=None, opCode=Filters.OC_RE, stage=Filters.STAGE_COLLECT_URLS, selectSubject=None, defaultValue=False)dc_crawler.CollectURLs.CollectURLsstatic
getFieldParams(self, formFields, postForms, siteId)dc_crawler.CollectURLs.CollectURLs
insertNewSiteProperties(self, params, wrapper, siteId)dc_crawler.CollectURLs.CollectURLs
isAbortedByTTLdc_crawler.CollectURLs.CollectURLs
PATTERN_WITH_PROTOCOLdc_crawler.CollectURLs.CollectURLsstatic
postFormsdc_crawler.CollectURLs.CollectURLs
process(self, httpCode, readOnly=False, httpApplyHeaders=None, proxyName=None)dc_crawler.CollectURLs.CollectURLs
processContentTypesdc_crawler.CollectURLs.CollectURLs
processorNamedc_crawler.CollectURLs.CollectURLs
processProcessor(self, urlSet, dom, urlXpathList, urlObj)dc_crawler.CollectURLs.CollectURLs
realUrldc_crawler.CollectURLs.CollectURLs
robotsParserdc_crawler.CollectURLs.CollectURLs
sitedc_crawler.CollectURLs.CollectURLs
sitePropertiesdc_crawler.CollectURLs.CollectURLs
urldc_crawler.CollectURLs.CollectURLs
urlProcessdc_crawler.CollectURLs.CollectURLs
urlsXpathListdc_crawler.CollectURLs.CollectURLs
urlXpathListdc_crawler.CollectURLs.CollectURLs