@chilkat/react-native 11.6.1

package/src/specs/Spider.nitro.ts

@@ -0,0 +1,609 @@
+// Generated by ReactNativeNs.RnGenerator -- do not edit.
+import type { HybridObject } from 'react-native-nitro-modules'
+
+/**
+ * Crawl a website domain, manage URL queues, filter links, cache pages, and inspect fetched HTML.
+ *
+ * `Spider` crawls pages within a single initialized domain.
+ * It maintains internal lists of unspidered, spidered, failed, and outbound
+ * URLs; fetches one page at a time; extracts same-domain links for continued
+ * crawling; collects outbound links separately; respects `robots.txt`;
+ * supports wildcard include and avoid patterns; can use a dedicated cache
+ * directory; and exposes the last fetched HTML, title, meta description,
+ * keywords, redirect information, cache status, and last-modified date.
+ *
+ * **Domain-limited crawling**
+ *
+ * Initialize the spider with a domain and crawl only URLs that belong to
+ * that same domain.
+ *
+ * **URL queue management**
+ *
+ * Add starting URLs, crawl the next queued URL, skip selected URLs, and
+ * inspect unspidered, spidered, failed, and outbound URL lists.
+ *
+ * **Filtering rules**
+ *
+ * Add wildcard avoid patterns, must-match patterns, and outbound-link
+ * avoid patterns to control which URLs are crawled or collected.
+ *
+ * **Page metadata**
+ *
+ * Read the last fetched HTML, page title, meta description, meta keywords,
+ * final redirect URL, and last-modified timestamp.
+ *
+ * **Caching and redirects**
+ *
+ * Fetch pages from a Chilkat-managed cache, update the cache, detect when a
+ * page was redirected, and inspect whether the last page came from cache.
+ *
+ * **Network controls**
+ *
+ * Configure user-agent, proxy settings, connect/read timeouts, IPv6
+ * preference, maximum URL length, maximum response size, and abort support.
+ *
+ * **Common pattern:**
+ * Call `Initialize` with the target domain, add one or more starting
+ * URLs with `AddUnspidered`, optionally add filtering patterns, then
+ * repeatedly call `CrawlNext`. After each successful crawl, inspect
+ * `LastUrl`, `LastHtml`, page metadata, redirect state,
+ * and the URL-list counts to decide whether to continue, skip, recrawl, or
+ * process the page.
+ *
+ * **Scope note:**
+ * `Spider` is intended for controlled, domain-oriented crawling and
+ * link discovery. Use `Chilkat.Http` or `Chilkat.Rest`
+ * when the task is a single HTTP request, API call, form post, or download
+ * rather than a crawl of discovered links.
+ *
+ * Each `Spider` instance owns a native Chilkat object. It is released when the JavaScript object is
+ * garbage collected, or immediately by `dispose()`; any use after `dispose()` throws.
+ * Create one with `new Spider()`.
+ *
+ * Methods that can take a while (network, files, compression, key generation) also have an
+ * `...Async` form returning a `Promise`; it runs on a native worker thread so the UI keeps
+ * rendering. While such a call is pending, every other call on this object throws, except
+ * {@link Spider.abort} and assigning {@link Spider.onPercentDone} / {@link Spider.onProgressInfo}.
+ */
+export interface Spider extends HybridObject<{ ios: 'c++', android: 'c++' }> {
+  // ---- Properties ----
+
+  /**
+   * Provides HTML-formatted information about the last called method or property. If a method call
+   * fails or behaves unexpectedly, check this property for details. Note that information is
+   * available regardless of the method call's success.
+   *
+   * This property is read-only.
+   */
+  readonly lastErrorHtml: string
+
+  /**
+   * Provides plain text information about the last called method or property. If a method call
+   * fails or behaves unexpectedly, check this property for details. Note that information is
+   * available regardless of the method call's success.
+   *
+   * This property is read-only.
+   */
+  readonly lastErrorText: string
+
+  /**
+   * Provides XML-formatted information about the last called method or property. If a method call
+   * fails or behaves unexpectedly, check this property for details. Note that information is
+   * available regardless of the method call's success.
+   *
+   * This property is read-only.
+   */
+  readonly lastErrorXml: string
+
+  /**
+   * Version of the component/library, such as "10.1.0"
+   *
+   * This property is read-only.
+   */
+  readonly version: string
+
+  /**
+   * If set to a file path, this property logs the LastErrorText of each Chilkat method or property
+   * call to the specified file. This logging helps identify the context and history of Chilkat
+   * calls leading up to any crash or hang, aiding in debugging.
+   *
+   * Enabling the VerboseLogging property provides more detailed information.
+   *
+   * This property is mainly used for debugging rare instances where a Chilkat method call causes a
+   * hang or crash, which should generally not happen.
+   *
+   * Possible causes of hangs include:
+   *
+   * - A timeout property set to 0, indicating an infinite timeout.
+   *
+   * - A hang occurring within an event callback in the application code.
+   *
+   * - An internal bug in the Chilkat code causing the hang.
+   */
+  debugLogFilePath: string
+
+  /**
+   * If set to `true`, then the contents of LastErrorText (or LastErrorXml, or LastErrorHtml) may
+   * contain more verbose information. The default value is `false`. Verbose logging should only be
+   * used for debugging. The potentially large quantity of logged information may adversely affect
+   * peformance.
+   */
+  verboseLogging: boolean
+
+  /**
+   * Indicates the success or failure of the most recent method call: `true` means success, `false`
+   * means failure. This property remains unchanged by property setters or getters. This method is
+   * present to address challenges in checking for null or Nothing returns in certain programming
+   * languages. Note: This property does not apply to methods that return integer values or to
+   * boolean-returning methods where the boolean does not indicate success or failure.
+   */
+  lastMethodSuccess: boolean
+
+  /**
+   * If set the 1 (true) the spider will avoid all HTTPS URLs.  The default is 0 (false).
+   */
+  avoidHttps: boolean
+
+  /**
+   * Specifies a cache directory to use for spidering. If either of the FetchFromCache or
+   * UpdateCache properties are true, this is the location of the cache to be used. Note: the
+   * Internet Explorer, Netscape, and FireFox caches are completely separate from the Chilkat Spider
+   * cache directory. You should specify a new and empty directory.
+   */
+  cacheDir: string
+
+  /**
+   * If equal to 1 (true), then the query portion of all URLs are automatically removed when adding
+   * to the unspidered list. The default value is 0 (false).
+   */
+  chopAtQuery: boolean
+
+  /**
+   * The maximum number of seconds to wait while connecting to an HTTP server.
+   */
+  connectTimeout: number
+
+  /**
+   * The domain name that is being spidered. This is the domain previously set in the Initialize
+   * method.
+   *
+   * This property is read-only.
+   */
+  readonly domain: string
+
+  /**
+   * If equal to 1 (true) then pages are fetched from cache when possible. If 0, the cache is
+   * ignored. The default value is 1. Regardless, if no CacheDir is set then the cache is not used.
+   */
+  fetchFromCache: boolean
+
+  /**
+   * The interval in milliseconds between each `AbortCheck` event callback, which enables an
+   * application to abort certain method calls before they complete. **By default, HeartbeatMs is
+   * set to **`0`**, meaning no AbortCheck event callbacks will trigger.**
+   */
+  heartbeatMs: number
+
+  /**
+   * Equal to 1 if the last page spidered was fetched from the cache.  Otherwise equal to 0.
+   *
+   * This property is read-only.
+   */
+  readonly lastFromCache: boolean
+
+  /**
+   * The HTML text of the last paged fetched by the spider.
+   *
+   * This property is read-only.
+   */
+  readonly lastHtml: string
+
+  /**
+   * The HTML META description from the last page fetched by the spider.
+   *
+   * This property is read-only.
+   */
+  readonly lastHtmlDescription: string
+
+  /**
+   * The HTML META keywords from the last page fetched by the spider.
+   *
+   * This property is read-only.
+   */
+  readonly lastHtmlKeywords: string
+
+  /**
+   * The HTML title from the last page fetched by the spider.
+   *
+   * This property is read-only.
+   */
+  readonly lastHtmlTitle: string
+
+  /**
+   * The last modification date/time (RFC822 format) from the last page fetched by the spider.
+   *
+   * This property is read-only.
+   */
+  readonly lastModDateStr: string
+
+  /**
+   * The URL of the last page spidered.
+   *
+   * This property is read-only.
+   */
+  readonly lastUrl: string
+
+  /**
+   * The maximum HTTP response size allowed. The spider will automatically fail any pages larger
+   * than this size. The default value is 250,000 bytes.
+   */
+  maxResponseSize: number
+
+  /**
+   * The maximum URL length allowed. URLs longer than this are not added to the unspidered list. The
+   * default value is 200.
+   */
+  maxUrlLen: number
+
+  /**
+   * The number of avoid patterns previously set by calling AddAvoidPattern.
+   *
+   * This property is read-only.
+   */
+  readonly numAvoidPatterns: number
+
+  /**
+   * The number of URLs in the object's failed URL list.
+   *
+   * This property is read-only.
+   */
+  readonly numFailed: number
+
+  /**
+   * The number of URLs in the object's outbound links URL list.
+   *
+   * This property is read-only.
+   */
+  readonly numOutboundLinks: number
+
+  /**
+   * The number of URLs in the object's already-spidered URL list.
+   *
+   * This property is read-only.
+   */
+  readonly numSpidered: number
+
+  /**
+   * The number of URLs in the object's unspidered URL list.
+   *
+   * This property is read-only.
+   */
+  readonly numUnspidered: number
+
+  /**
+   * If `true`, then use IPv6 over IPv4 when both are supported for a particular domain. The default
+   * value of this property is `false`, which will choose IPv4 over IPv6.
+   */
+  preferIpv6: boolean
+
+  /**
+   * The domain name of a proxy host if an HTTP proxy is used.
+   */
+  proxyDomain: string
+
+  /**
+   * If an HTTP proxy is used and it requires authentication, this property specifies the HTTP proxy
+   * login.
+   */
+  proxyLogin: string
+
+  /**
+   * If an HTTP proxy is used and it requires authentication, this property specifies the HTTP proxy
+   * password.
+   */
+  proxyPassword: string
+
+  /**
+   * The port number of a proxy server if an HTTP proxy is used.
+   */
+  proxyPort: number
+
+  /**
+   * The maximum number of seconds to wait when reading from an HTTP server.
+   */
+  readTimeout: number
+
+  /**
+   * If equal to 1 (true) then pages saved to the cache. If 0, the cache is ignored. The default
+   * value is 1. Regardless, if no CacheDir is set then the cache is not used.
+   */
+  updateCache: boolean
+
+  /**
+   * The value of the HTTP user-agent header field to be sent with HTTP requests. This can be set to
+   * any desired value, but be aware that some websites may reject requests from unknown user
+   * agents.
+   */
+  userAgent: string
+
+  /**
+   * The `wind-down` phase begins when this number of URLs has been spidered. When in the wind-down
+   * phase, no new URLs are added to the unspidered list. The default value is 0 which means that
+   * there is NO wind-down phase.
+   */
+  windDownCount: number
+
+  /**
+   * When set to `true`, causes the currently running method to abort. Methods that always finish
+   * quickly (i.e.have no length file operations or network communications) are not affected. If no
+   * method is running, then this property is automatically reset to `false` when the next method is
+   * called. When the abort occurs, this property is reset to `false`. Both synchronous and
+   * asynchronous method calls can be aborted. (A synchronous method call could be aborted by
+   * setting this property from a separate thread.)
+   */
+  abortCurrent: boolean
+
+  /**
+   * Indicates whether the last URL crawled was redirected.  (`true` = yes, `false` = no)
+   *
+   * This property is read-only.
+   */
+  readonly wasRedirected: boolean
+
+  /**
+   * If the last URL crawled was redirected (as indicated by the WasRedirected property), this
+   * property will contain the final redirect URL.
+   *
+   * This property is read-only.
+   */
+  readonly finalRedirectUrl: string
+
+  // ---- Methods ----
+
+  /**
+   * Adds a wildcarded pattern to prevent collecting matching outbound link URLs. For example, if
+   * `*google*` is added, then any outbound links containing the word `google` will be ignored. The
+   * `*` character matches zero or more of any character.
+   */
+  addAvoidOutboundLinkPattern(pattern: string): void
+
+  /**
+   * Adds a wildcarded pattern to prevent spidering matching URLs. For example, if `*register*` is
+   * added, then any url containing the word `register` is not spidered. The `*` character matches
+   * zero or more of any character.
+   */
+  addAvoidPattern(pattern: string): void
+
+  /**
+   * Adds a wildcarded pattern to limit spidering to only URLs that match the pattern. For example,
+   * if `*\/products/*` is added, then only URLs containing `/products/` are spidered. This is
+   * helpful for only spidering a portion of a website. The `*` character matches zero or more of
+   * any character.
+   */
+  addMustMatchPattern(pattern: string): void
+
+  /**
+   * To begin spidering you must call this method one or more times to provide starting points. It
+   * adds a single URL to the object's internal queue of URLs to be spidered.
+   */
+  addUnspidered(url: string): void
+
+  /**
+   * Canonicalizes a URL by doing the following:
+   *
+   * -  Drops username/password if present.
+   *
+   * - Drops fragment if present.
+   *
+   * - Converts domain to lowercase.
+   *
+   * - Removes port 80 or 443
+   *
+   * - Remove default.asp, index.html, index.htm, default.html, index.htm, default.htm,
+   *   index.php, index.asp, default.php, .cfm, .aspx, ,php3, .pl, .cgi, .txt, .shtml, .phtml
+   *
+   * -  Remove www. from the domain if present.
+   *
+   * @throws Error if the call fails (the message names the reason); the full log is in
+   * {@link Spider.lastErrorText}.
+   */
+  canonicalizeUrl(url: string): string
+
+  /**
+   * Clears the object's internal list of URLs that could not be downloaded.
+   */
+  clearFailedUrls(): void
+
+  /**
+   * Clears the object's internal list of outbound URLs that will automatically accumulate while
+   * spidering.
+   */
+  clearOutboundLinks(): void
+
+  /**
+   * Clears the object's internal list of already-spidered URLs that will automatically accumulate
+   * while spidering.
+   */
+  clearSpideredUrls(): void
+
+  /**
+   * Crawls the next URL in the internal list of unspidered URLs. The URL is moved from the
+   * unspidered list to the spidered list. Any new links within the same domain and not yet spidered
+   * are added to the unspidered list. (providing that they do not match `avoid` patterns, etc.) Any
+   * new outbound links are added to the outbound URL list.
+   *
+   * If successful, the HTML of the downloaded page is available in the LastHtml property. If there
+   * are no more URLs left unspidered, the method returns `false`. Information about the URL crawled
+   * is available in the properties LastUrl, LastFromCache, and LastModDate.
+   *
+   * This call blocks the JavaScript thread until Chilkat returns; from UI code prefer
+   * {@link Spider.crawlNextAsync}.
+   *
+   * @throws Error if the call fails (the message names the reason); the full log is in
+   * {@link Spider.lastErrorText}.
+   */
+  crawlNext(): void
+
+  /**
+   * Asynchronous form of {@link Spider.crawlNext}: the same call on a native worker thread,
+   * settling on the JavaScript thread. While it is pending, other calls on this object throw,
+   * except {@link Spider.abort} (which cancels it) and the {@link Spider.onPercentDone} /
+   * {@link Spider.onProgressInfo} callbacks, which report progress while it runs.
+   *
+   * The promise rejects with an Error if the call fails; the full log is in
+   * {@link Spider.lastErrorText}.
+   */
+  crawlNextAsync(): Promise<void>
+
+  /**
+   * Returns the contents of the robots.txt file from the domain being crawled. This spider object
+   * will not crawl URLs excluded by robots.txt. If you believe the spider is not behaving
+   * correctly, please notify us at support@chilkatsoft.com and provide information detailing a case
+   * that allows us to reproduce the problem.
+   *
+   * This call blocks the JavaScript thread until Chilkat returns; from UI code prefer
+   * {@link Spider.fetchRobotsTextAsync}.
+   *
+   * @throws Error if the call fails (the message names the reason); the full log is in
+   * {@link Spider.lastErrorText}.
+   */
+  fetchRobotsText(): string
+
+  /**
+   * Asynchronous form of {@link Spider.fetchRobotsText}: the same call on a native worker thread,
+   * settling on the JavaScript thread. While it is pending, other calls on this object throw,
+   * except {@link Spider.abort} (which cancels it) and the {@link Spider.onPercentDone} /
+   * {@link Spider.onProgressInfo} callbacks, which report progress while it runs.
+   *
+   * The promise rejects with an Error if the call fails; the full log is in
+   * {@link Spider.lastErrorText}.
+   */
+  fetchRobotsTextAsync(): Promise<string>
+
+  /**
+   * Returns the Nth avoid pattern previously added by calling AddAvoidPattern. Indexing begins at
+   * 0.
+   *
+   * @throws Error if the call fails (the message names the reason); the full log is in
+   * {@link Spider.lastErrorText}.
+   */
+  getAvoidPattern(index: number): string
+
+  /**
+   * Returns the second-level + top-level domain of the `domain`. For example, if `domain` is
+   * `xyz.example.com`, this returns `example.com`. For some domains, such as `xyz.example.co.uk`,
+   * the top 3 levels are returned, such as `example.co.uk`.
+   *
+   * @throws Error if the call fails (the message names the reason); the full log is in
+   * {@link Spider.lastErrorText}.
+   */
+  getBaseDomain(domain: string): string
+
+  /**
+   * Returns the Nth URL in the failed URL list.  Indexing begins at 0.
+   *
+   * @throws Error if the call fails (the message names the reason); the full log is in
+   * {@link Spider.lastErrorText}.
+   */
+  getFailedUrl(index: number): string
+
+  /**
+   * Returns the Nth URL in the outbound link URL list.  Indexing begins at 0.
+   *
+   * @throws Error if the call fails (the message names the reason); the full log is in
+   * {@link Spider.lastErrorText}.
+   */
+  getOutboundLink(index: number): string
+
+  /**
+   * Returns the Nth URL in the already-spidered URL list.  Indexing begins at 0.
+   *
+   * @throws Error if the call fails (the message names the reason); the full log is in
+   * {@link Spider.lastErrorText}.
+   */
+  getSpideredUrl(index: number): string
+
+  /**
+   * Returns the Nth URL in the unspidered URL list.  Indexing begins at 0.
+   *
+   * @throws Error if the call fails (the message names the reason); the full log is in
+   * {@link Spider.lastErrorText}.
+   */
+  getUnspideredUrl(index: number): string
+
+  /**
+   * Returns the domain name part of a URL. For example, if the URL is
+   * `https://www.chilkatsoft.com/test.asp`, then `www.chilkatsoft.com` is returned.
+   *
+   * @throws Error if the call fails (the message names the reason); the full log is in
+   * {@link Spider.lastErrorText}.
+   */
+  getUrlDomain(url: string): string
+
+  /**
+   * Initializes the object to begin spidering a domain. Calling Initialize clears any patterns
+   * added via the AddAvoidOutboundLinkPattern, AddAvoidPattern, and AddMustMatchPattern methods.
+   * The domain name passed to this method is what is returned by the Domain property. The spider
+   * only crawls URLs within the same domain.
+   */
+  initialize(domain: string): void
+
+  /**
+   * Re-crawls the last URL spidered. This helpful when cookies set in a previous page load cause
+   * the page to be loaded differently the next time.
+   *
+   * This call blocks the JavaScript thread until Chilkat returns; from UI code prefer
+   * {@link Spider.recrawlLastAsync}.
+   *
+   * @throws Error if the call fails (the message names the reason); the full log is in
+   * {@link Spider.lastErrorText}.
+   */
+  recrawlLast(): void
+
+  /**
+   * Asynchronous form of {@link Spider.recrawlLast}: the same call on a native worker thread,
+   * settling on the JavaScript thread. While it is pending, other calls on this object throw,
+   * except {@link Spider.abort} (which cancels it) and the {@link Spider.onPercentDone} /
+   * {@link Spider.onProgressInfo} callbacks, which report progress while it runs.
+   *
+   * The promise rejects with an Error if the call fails; the full log is in
+   * {@link Spider.lastErrorText}.
+   */
+  recrawlLastAsync(): Promise<void>
+
+  /**
+   * Moves a URL from the unspidered list to the spidered list. This allows an application to skip a
+   * specific URL.
+   */
+  skipUnspidered(index: number): void
+
+  /**
+   * Suspends the execution of the current thread until the time-out interval elapses.
+   */
+  sleepMs(numMilliseconds: number): void
+
+  // ---- Events (ReactNativeGen_DESIGN.md §6) ----
+
+  /**
+   * Called with the percent completed (0..100) while a long-running method runs, when Chilkat
+   * can measure progress. Runs on the JavaScript thread, so it is only useful with the
+   * `...Async` methods (during a synchronous call the thread is busy and the events arrive
+   * after it returns). Assign `undefined` to remove.
+   */
+  onPercentDone?: (pctDone: number) => void
+
+  /**
+   * Called with a name/value pair of progress information while a long-running method runs
+   * (what is reported depends on the class and method). Runs on the JavaScript thread; see
+   * {@link Spider.onPercentDone}. Assign `undefined` to remove.
+   */
+  onProgressInfo?: (name: string, value: string) => void
+
+  /**
+   * Requests that the pending `...Async` call on this object stop at its next progress check.
+   * The promise then rejects with Chilkat's abort error. Chilkat checks at least every
+   * `heartbeatMs` milliseconds on the classes that have that property, so set it (e.g. 250)
+   * for a responsive cancel. Harmless when nothing is pending.
+   */
+  abort(): void
+}