| java.lang.Object
 websphinx.Region
websphinx.Element
websphinx.Link
All known Subclasses: websphinx.FormButton, websphinx.Form,
| Field Summary | |
| final public static int | GET
Use the HTTP GET method to download this link. | | final public static int | POST
Use the HTTP POST method to access this link. | | protected URL | url
|
| Constructor Summary | |
| public | Link(Tag startTag, Tag endTag, URL base)
Make a Link from a start tag and end tag and a base URL (for relative references). | | public | Link(URL url)
Make a Link from a URL. | | public | Link(File file)
Make a Link from a File. | | public | Link(String href)
Make a Link from a string URL. |
| Method Summary | |
| public static URL | FileToURL(File file)
Convert a local filename to a URL. | | public static File | URLToFile(URL url)
Convert a file: URL to a filename appropriate to the
current system platform. | | public void | discardContent()
Eliminate all references to page content. | | public void | disconnect()
Disconnect this link from its downloaded page (throwing away the page). | | public int | getDepth()
Get depth of link in crawl. | | public String | getDirectory()
Get the directory part of the link, like "/home/dir/". | | public URL | getDirectoryURL()
Get the URL of a page's directory. | | public static URL | getDirectoryURL(URL url)
Get the URL of a page's directory. | | public DownloadParameters | getDownloadParameters()
Get the download parameters used for this link. | | public String | getFile()
Get the filename part of the link, which includes the pathname
and query but not the anchor reference. | | public String | getFilename()
Get the filename part of the link, like "index.html". | | public String | getHost()
Get the hostname of the link, like "www.cs.cmu.edu". | | public int | getMethod()
Get the method used to access this link. | | public Page | getPage()
Get the downloaded page to which the link points. | | public URL | getPageURL()
Get the URL of a page, omitting any anchor reference (like #ref). | | public static URL | getPageURL(URL url)
Get the URL of a page, omitting any anchor reference (like #ref). | | public URL | getParentURL()
Get the URL of a page's parent directory. | | public static URL | getParentURL(URL url)
Get the URL of a page's parent directory. | | public int | getPort()
Get the port number of the link. | | public float | getPriority()
Get the priority of the link in the crawl. | | public String | getProtocol()
Get the network protocol of the link, like "ftp" or "http". | | public String | getQuery()
Get the query part of the link. | | public String | getRef()
Get the anchor reference of the link, like "#ref". | | public URL | getServiceURL()
Get the URL of a Web service, omitting any query or anchor reference. | | public static URL | getServiceURL(URL url)
Get the URL of a Web service, omitting any query or anchor reference. | | public int | getStatus()
Get the status of the link. | | public URL | getURL()
Get the URL. | | public static String | relativeTo(URL here, URL there)
| | public static String | relativeTo(URL here, String there)
| | public Tag | replaceHref(String newHref)
Copy the link's start tag, replacing the URL. | | public void | setDownloadParameters(DownloadParameters dp)
Set the download parameters used for this link. | | public void | setPage(Page page)
Set the page corresponding to this link. | | public void | setPriority(float priority)
Set the priority of the link in the crawl. | | public void | setStatus(int event)
Set the status of the link. | | public void | setText(String text)
Set the tagless-text representation of this region. | | public String | toDescription()
Generate a human-readable description of the link. | | public String | toText()
Convert the region to tagless text. | | public String | toURL()
| | public static String | toURLDelimiters(String path)
| | protected URL | urlFromHref(Tag tag, URL base)
Construct the URL for a link element, from its start tag and a base URL (for relative references). |
| GET | | final public static int GET(Code) | | Use the HTTP GET method to download this link.
|
| POST | | final public static int POST(Code) | | Use the HTTP POST method to access this link.
|
| Link | | public Link(Tag startTag, Tag endTag, URL base) throws MalformedURLException(Code) | | Make a Link from a start tag and end tag and a base URL (for relative references).
The tags must be on the same page.
Parameters:
startTag - Start tag of element
Parameters:
endTag - End tag of element
Parameters:
base - Base URL used for relative references |
| Link | | public Link(URL url)(Code) | | Make a Link from a URL.
|
| FileToURL | | public static URL FileToURL(File file) throws MalformedURLException(Code) | | Convert a local filename to a URL.
For example, if the filename is "C:\FOO\BAR\BAZ",
the resulting URL is "file:/C:/FOO/BAR/BAZ".
Parameters:
file - File to convert URL corresponding to file |
| URLToFile | | public static File URLToFile(URL url) throws MalformedURLException(Code) | | Convert a file: URL to a filename appropriate to the
current system platform. For example, on MS Windows,
if the URL is "file:/FOO/BAR/BAZ", the resulting
filename is "\FOO\BAR\BAZ".
Parameters:
url - URL to convert File corresponding to url
exception:
MalformedURLException - if url is not afile: URL. |
| discardContent | | public void discardContent()(Code) | | Eliminate all references to page content.
|
| disconnect | | public void disconnect()(Code) | | Disconnect this link from its downloaded page (throwing away the page).
|
| getDepth | | public int getDepth()(Code) | | Get depth of link in crawl.
depth of link from root (depth of roots is 0) |
| getDirectory | | public String getDirectory()(Code) | | Get the directory part of the link, like "/home/dir/".
Always starts and ends with '/'.
the directory portion of the link's URL |
| getDirectoryURL | | public URL getDirectoryURL()(Code) | | Get the URL of a page's directory.
the URL sans filename, query and anchor reference |
| getDirectoryURL | | public static URL getDirectoryURL(URL url)(Code) | | Get the URL of a page's directory.
the URL sans filename, query and anchor reference |
| getDownloadParameters | | public DownloadParameters getDownloadParameters()(Code) | | Get the download parameters used for this link. Default is null.
|
| getFile | | public String getFile()(Code) | | Get the filename part of the link, which includes the pathname
and query but not the anchor reference.
Equivalent to getURL().getFile().
the filename portion of the link's URL |
| getFilename | | public String getFilename()(Code) | | Get the filename part of the link, like "index.html".
Never contains '/'; may be the empty string.
the filename portion of the link's URL |
| getHost | | public String getHost()(Code) | | Get the hostname of the link, like "www.cs.cmu.edu".
the hostname portion of the link's URL |
| getMethod | | public int getMethod()(Code) | | Get the method used to access this link.
GET or POST. |
| getPage | | public Page getPage()(Code) | | Get the downloaded page to which the link points.
the Page object, or null if the page hasn't been downloaded. |
| getPageURL | | public URL getPageURL()(Code) | | Get the URL of a page, omitting any anchor reference (like #ref).
the URL sans anchor reference |
| getPageURL | | public static URL getPageURL(URL url)(Code) | | Get the URL of a page, omitting any anchor reference (like #ref).
the URL sans anchor reference |
| getParentURL | | public URL getParentURL()(Code) | | Get the URL of a page's parent directory.
the URL sans filename, query and anchor reference |
| getParentURL | | public static URL getParentURL(URL url)(Code) | | Get the URL of a page's parent directory.
the URL sans filename, query and anchor reference |
| getPort | | public int getPort()(Code) | | Get the port number of the link.
the port number of the link's URL, or -1 if no port numberis explicitly specified in the URL |
| getPriority | | public float getPriority()(Code) | | Get the priority of the link in the crawl.
|
| getProtocol | | public String getProtocol()(Code) | | Get the network protocol of the link, like "ftp" or "http".
the protocol portion of the link's URL |
| getQuery | | public String getQuery()(Code) | | Get the query part of the link.
Either starts with a '?', or is empty.
the query portion of the link's URL |
| getRef | | public String getRef()(Code) | | Get the anchor reference of the link, like "#ref".
Either starts with '#', or is empty.
the anchor reference portion of the link's URL |
| getServiceURL | | public URL getServiceURL()(Code) | | Get the URL of a Web service, omitting any query or anchor reference.
the URL sans query and anchor reference |
| getServiceURL | | public static URL getServiceURL(URL url)(Code) | | Get the URL of a Web service, omitting any query or anchor reference.
the URL sans query and anchor reference |
| getStatus | | public int getStatus()(Code) | | Get the status of the link. Possible values are defined in LinkEvent.
last event that happened to this link |
| getURL | | public URL getURL()(Code) | | Get the URL.
the URL of the link |
| replaceHref | | public Tag replaceHref(String newHref)(Code) | | Copy the link's start tag, replacing the URL. Note that the name of the attribute containing the URL
varies from tag to tag: sometimes it is called HREF, sometimes SRC, sometimes CODE, etc.
This method changes the appropriate attribute for this tag.
Parameters:
newHref - New URL or relative reference; e.g. "http://www.cs.cmu.edu/" or "/foo/index.html". copy of this link's start tag with its URL attribute replaced. The copy is a region of a fresh page containing only the tag. |
| setDownloadParameters | | public void setDownloadParameters(DownloadParameters dp)(Code) | | Set the download parameters used for this link.
|
| setPage | | public void setPage(Page page)(Code) | | Set the page corresponding to this link.
Parameters:
page - Page to which this link points |
| setPriority | | public void setPriority(float priority)(Code) | | Set the priority of the link in the crawl.
|
| setStatus | | public void setStatus(int event)(Code) | | Set the status of the link. Possible values are defined in LinkEvent.
Parameters:
event - the event that just happened to this link |
| setText | | public void setText(String text)(Code) | | Set the tagless-text representation of this region.
Parameters:
text - a string consisting of the text in the page contained by this region |
| toDescription | | public String toDescription()(Code) | | Generate a human-readable description of the link.
a description of the link, in the form "[url]". |
| toText | | public String toText()(Code) | | Convert the region to tagless text.
a string consisting of the text in the page contained by this region |
| toURL | | public String toURL()(Code) | | Convert the link's URL to a String
the URL represented as a string |
| urlFromHref | | protected URL urlFromHref(Tag tag, URL base) throws MalformedURLException(Code) | | Construct the URL for a link element, from its start tag and a base URL (for relative references).
Parameters:
tag - Start tag of link, such as <A HREF="/foo/index.html">.
Parameters:
base - Base URL used for relative references URL to which the link points |
|
|