| __init__(self, usageModel=APP_CONSTS.APP_USAGE_MODEL_PROCESS, configFile=None, logger=None, inputData=None) | dc_processor.Scraper.Scraper | |
| addCustomTag(self, result, tag_name, tag_value) | dc_processor.Scraper.Scraper | |
| adjustLinkURL(self, response) | dc_processor.Scraper.Scraper | |
| adjustPartialReferences(self, response) | dc_processor.Scraper.Scraper | |
| adjustTitle(self, response) | dc_processor.Scraper.Scraper | |
| algorithm_name | dc_processor.Scraper.Scraper | |
| altTagsMask | dc_processor.Scraper.Scraper | |
| applyHTTPRedirectLink(self, siteId, url, properties, response) | dc_processor.Scraper.Scraper | |
| applyPostProcessing(self, result, key, postProcessingRE) | dc_processor.Scraper.Scraper | |
| applyPubdate(self, response, pubdate) | dc_processor.Scraper.Scraper | |
| article | dc_processor.Scraper.Scraper | |
| attrConditions | dc_processor.Scraper.Scraper | |
| baseUrl | dc_processor.Scraper.Scraper | |
| calcUrlDomainCrc(self, url) | dc_processor.Scraper.Scraper | |
| checkDOMElement(self, elem) | dc_processor.Scraper.Scraper | |
| checkMediaTag(self, urlStringMedia) | dc_processor.Scraper.Scraper | |
| commonResultOperations(self, result) | dc_processor.Scraper.Scraper | |
| compileResults(self, result, resultsList, key, xPathPreparing=None) | dc_processor.Scraper.Scraper | |
| config | dc_processor.Scraper.Scraper | |
| configFile | dc_processor.Scraper.Scraper | |
| createArticle(self) | dc_processor.Scraper.Scraper | |
| createModule(self, module_name) | dc_processor.Scraper.Scraper | |
| dataUrlsCanonizator(self, data, baseUrl=None, useAdditionEncoding=False) | dc_processor.Scraper.Scraper | |
| datetimeNewsNames | dc_processor.Scraper.Scraper | |
| datetimeTemplateTypes | dc_processor.Scraper.Scraper | |
| dbWrapper | dc_processor.Scraper.Scraper | |
| elemUrlsCanoizator(self, data, baseUrl=None, firstDelim=' ', secondDelim=', useAdditionEncoding=False) | dc_processor.Scraper.Scraper | |
| entry | dc_processor.Scraper.Scraper | |
| errorMask | dc_processor.Scraper.Scraper | |
| exitCode | dc_processor.Scraper.Scraper | |
| extractAdditionTagsByScrapy(self, localResult, key, tagsXpaths) | dc_processor.Scraper.Scraper | |
| extractBaseUrlRssFeed(self, siteId, url) | dc_processor.Scraper.Scraper | |
| extractFeedUrlRssFeed(self, siteId, url) | dc_processor.Scraper.Scraper | |
| extractor | dc_processor.Scraper.Scraper | |
| extractors | dc_processor.Scraper.Scraper | |
| extractPubDate(self, response, dataTagName) | dc_processor.Scraper.Scraper | |
| extractPubdateRssFeed(self, siteId, url) | dc_processor.Scraper.Scraper | |
| feedParserProcess(self) | dc_processor.Scraper.Scraper | |
| formatOutpuElement(self, elem, localOutputFormat) | dc_processor.Scraper.Scraper | |
| formatOutputData(self, response, localOutputFormat) | dc_processor.Scraper.Scraper | |
| formatTag(self, result, path, key, pathDict, isExtract) | dc_processor.Scraper.Scraper | |
| getBestDatatimeData(self, data) | dc_processor.Scraper.Scraper | |
| getDomainsForUrlSourcesRules(self, urlSourcesRules) | dc_processor.Scraper.Scraper | |
| getExitCode(self) | dc_processor.Scraper.Scraper | |
| getExtractorByName(self, extractorName) | dc_processor.Scraper.Scraper | |
| getHeaderContent(self, siteId, url) | dc_processor.Scraper.Scraper | |
| getNextBestExtractor(self) | dc_processor.Scraper.Scraper | |
| getProcessedContent(self, result) | dc_processor.Scraper.Scraper | |
| getTemplate(self, explicit=True) | dc_processor.Scraper.Scraper | |
| getVariableFromHeaderContent(self, headerContent, name, makeDecode=True) | dc_processor.Scraper.Scraper | |
| input_data | dc_processor.Scraper.Scraper | |
| itr | dc_processor.Scraper.Scraper | |
| loadConfig(self) | dc_processor.Scraper.Scraper | |
| loadExtractors(self) | dc_processor.Scraper.Scraper | |
| loadLogConfigFile(self) | dc_processor.Scraper.Scraper | |
| loadOptions(self) | dc_processor.Scraper.Scraper | |
| loadScraperProperties(self) | dc_processor.Scraper.Scraper | |
| logger | dc_processor.Scraper.Scraper | |
| mediaLimitsHandler | dc_processor.Scraper.Scraper | |
| message_queue | dc_processor.Scraper.Scraper | |
| metrics | dc_processor.Scraper.Scraper | |
| MSG_ERROR_WRONG_CONFIG_FILE_NAME | dc_processor.Scraper.Scraper | static |
| newsExtraction(self) | dc_processor.Scraper.Scraper | |
| normalizeAuthor(self, confProp, procProp, response) | dc_processor.Scraper.Scraper | |
| normalizeDatetime(self, response, algorithmName) | dc_processor.Scraper.Scraper | |
| output_data | dc_processor.Scraper.Scraper | |
| outputFormat | dc_processor.Scraper.Scraper | |
| parseFeed(self) | dc_processor.Scraper.Scraper | |
| postprocessing(self, result, rule, tag) | dc_processor.Scraper.Scraper | |
| prepareResults(self, resultsList) | dc_processor.Scraper.Scraper | |
| preparseResponse(self, response) | dc_processor.Scraper.Scraper | |
| process(self, config) | dc_processor.Scraper.Scraper | |
| processBatch(self) | dc_processor.Scraper.Scraper | |
| processedContent | dc_processor.Scraper.Scraper | |
| processingHTMLData(self, htmlBuf, bufFormat) | dc_processor.Scraper.Scraper | |
| properties | dc_processor.Scraper.Scraper | |
| pubdate | dc_processor.Scraper.Scraper | |
| pubdateMonthOrder(self, rawPubdate, properties, urlString) | dc_processor.Scraper.Scraper | |
| pubdateTransform(self, rawPubdate, rawTimezone, properties, urlString) | dc_processor.Scraper.Scraper | |
| refineBadDateTags(self, response) | dc_processor.Scraper.Scraper | |
| refineCommonText(self, tagName, result) | dc_processor.Scraper.Scraper | |
| replaceLoopValue(self, buf, replaceFrom, replaceTo) | dc_processor.Scraper.Scraper | |
| run(self) | dc_processor.Scraper.Scraper | |
| scraperPropFileName | dc_processor.Scraper.Scraper | |
| setup(self) | dc_processor.Scraper.Scraper | |
| splitMediaTagString(self, urlStringMedia) | dc_processor.Scraper.Scraper | |
| sqliteTimeout | dc_processor.Scraper.Scraper | |
| tagReduceMask | dc_processor.Scraper.Scraper | |
| tagsCount | dc_processor.Scraper.Scraper | |
| tagsMask | dc_processor.Scraper.Scraper | |
| tagsTypes | dc_processor.Scraper.Scraper | |
| templateExtraction(self, config, urlHost) | dc_processor.Scraper.Scraper | |
| urlHost | dc_processor.Scraper.Scraper | |
| urlSourcesRules | dc_processor.Scraper.Scraper | |
| usageModel | dc_processor.Scraper.Scraper | |
| useCurrentYear | dc_processor.Scraper.Scraper | |
| WWW_PREFIX | dc_processor.Scraper.Scraper | static |
| xpathSplitString | dc_processor.Scraper.Scraper | |
1.8.13