Method Detail

• registerClosable

   abstract Boolean registerClosable(AutoCloseable closable)

  Close objects when sessions closes

• disableCache

   abstract Unit disableCache()

• options

   abstract LoadOptions options(String args)

  Create a new options, with a new volatile config

• normalize

   abstract NormUrl normalize(String url, LoadOptions options, Boolean toItemOption)

• normalize

   abstract List<NormUrl> normalize(Iterable<String> urls, LoadOptions options, Boolean toItemOption)

• normalize

   abstract NormUrl normalize(UrlAware url, LoadOptions options, Boolean toItemOption)

• normalize

   abstract List<NormUrl> normalize(Collection<UrlAware> urls, LoadOptions options, Boolean toItemOption)

• normalizeOrNull

   abstract NormUrl normalizeOrNull(String url, LoadOptions options, Boolean toItemOption)

• normalizeOrNull

   abstract NormUrl normalizeOrNull(UrlAware url, LoadOptions options, Boolean toItemOption)

• inject

   abstract WebPage inject(String url)

  Inject a url

  Parameters:

  url - The url followed by options

• get

   abstract WebPage get(String url)

• getOrNull

   abstract WebPage getOrNull(String url)

• exists

   abstract Boolean exists(String url)

• fetchState

   abstract CheckState fetchState(WebPage page, LoadOptions options)

• load

   abstract WebPage load(String url, String args)

  Load a url with specified options

  Parameters:

  url - The url to load

  args - The load args

• load

   abstract WebPage load(String url, LoadOptions options)

  Load a url with specified options

  Parameters:

  url - The url to load

  options - The load options

• load

   abstract WebPage load(UrlAware url, String args)

• load

   abstract WebPage load(UrlAware url, LoadOptions options)

• load

   abstract WebPage load(NormUrl normUrl)

• loadDeferred

   abstract WebPage loadDeferred(String url, LoadOptions options)

• loadDeferred

   abstract WebPage loadDeferred(UrlAware url, String args)

• loadDeferred

   abstract WebPage loadDeferred(UrlAware url, LoadOptions options)

• loadDeferred

   abstract WebPage loadDeferred(NormUrl normUrl)

• loadAll

   abstract Collection<WebPage> loadAll(Iterable<String> urls, LoadOptions options, Boolean areItems)

  Load all urls with specified options, this causes a parallel fetching whenever applicable

  Parameters:

  urls - The urls to load

  options - The load options

• loadOutPages

   abstract Collection<WebPage> loadOutPages(String portalUrl, String args)

  Load all out pages in a portal page

  Parameters:

  portalUrl - The portal url from where to load pages

  args - The load args

• loadOutPages

   abstract Collection<WebPage> loadOutPages(String portalUrl, LoadOptions options)

  Load all out pages in a portal page

  Parameters:

  portalUrl - The portal url from where to load pages

  options - The load options

• parse

   abstract FeaturedDocument parse(WebPage page, Boolean noCache)

  Parse the Web page into DOM. If the Web page is not changed since last parse, use the last result if available

• loadDocument

   abstract FeaturedDocument loadDocument(String url, String args)

• loadDocument

   abstract FeaturedDocument loadDocument(String url, LoadOptions options)

• loadDocument

   abstract FeaturedDocument loadDocument(NormUrl normUrl)

• scrape

   abstract Map<String, String> scrape(String url, String args, Iterable<String> fieldSelectors)

• scrape

   abstract Map<String, String> scrape(String url, String args, Map<String, String> fieldSelectors)

• scrape

   abstract List<Map<String, String>> scrape(String url, String args, String restrictSelector, Iterable<String> fieldSelectors)

• scrape

   abstract List<Map<String, String>> scrape(String url, String args, String restrictSelector, Map<String, String> fieldSelectors)

• scrapeOutPages

   abstract List<Map<String, String>> scrapeOutPages(String portalUrl, String args, Iterable<String> fieldSelectors)

• scrapeOutPages

   abstract List<Map<String, String>> scrapeOutPages(String portalUrl, String args, String restrictSelector, Iterable<String> fieldSelectors)

• scrapeOutPages

   abstract List<Map<String, String>> scrapeOutPages(String portalUrl, String args, Map<String, String> fieldSelectors)

• scrapeOutPages

   abstract List<Map<String, String>> scrapeOutPages(String portalUrl, String args, String restrictSelector, Map<String, String> fieldSelectors)

• getVariable

   abstract Object getVariable(String name)

• setVariable

   abstract Unit setVariable(String name, Object value)

• putSessionBean

   abstract Unit putSessionBean(Object obj)

• delete

   abstract Unit delete(String url)

• flush

   abstract Unit flush()

• persist

   abstract Boolean persist(WebPage page)

• export

   abstract Path export(WebPage page, String ident)

• export

   abstract Path export(FeaturedDocument doc, String ident)

• exportTo

   abstract Path exportTo(FeaturedDocument doc, Path path)

• getId

   abstract Integer getId()

  The session id. Session id is expected to be set by the container, e.g. the h2 database runtime

• getContext

   abstract AbstractPulsarContext getContext()

  The pulsar context

• getSessionConfig

   abstract VolatileConfig getSessionConfig()

  The session scope volatile config, every setting is supposed to be changed at any time and any place

• getUnmodifiedConfig

   abstract ImmutableConfig getUnmodifiedConfig()

• getSessionBeanFactory

   abstract BeanFactory getSessionBeanFactory()

  The scoped bean factory: for each volatileConfig object, there is a bean factory TODO: session scoped?

• getDisplay

   abstract String getDisplay()

• getPageCache

   abstract ConcurrentExpiringLRUCache<String, WebPage> getPageCache()

• getDocumentCache

   abstract ConcurrentExpiringLRUCache<String, FeaturedDocument> getDocumentCache()

• getGlobalCacheFactory

   abstract GlobalCacheFactory getGlobalCacheFactory()