mirror of
https://github.com/mozilla/gecko-dev.git
synced 2024-11-05 08:35:26 +00:00
151 lines
3.8 KiB
C++
151 lines
3.8 KiB
C++
/* -*- Mode: C++; tab-width: 2; indent-tabs-mode: nil; c-basic-offset: 2 -*-
|
|
*
|
|
* The contents of this file are subject to the Netscape Public
|
|
* License Version 1.1 (the "License"); you may not use this file
|
|
* except in compliance with the License. You may obtain a copy of
|
|
* the License at http://www.mozilla.org/NPL/
|
|
*
|
|
* Software distributed under the License is distributed on an "AS
|
|
* IS" basis, WITHOUT WARRANTY OF ANY KIND, either express or
|
|
* implied. See the License for the specific language governing
|
|
* rights and limitations under the License.
|
|
*
|
|
* The Original Code is Mozilla Communicator client code.
|
|
*
|
|
* The Initial Developer of the Original Code is Netscape Communications
|
|
* Corporation. Portions created by Netscape are
|
|
* Copyright (C) 1998 Netscape Communications Corporation. All
|
|
* Rights Reserved.
|
|
*
|
|
* Contributor(s):
|
|
*/
|
|
#ifndef nsWebCrawler_h___
|
|
#define nsWebCrawler_h___
|
|
|
|
#include "nsIBrowserWindow.h"
|
|
#include "nsVoidArray.h"
|
|
#include "nsString.h"
|
|
|
|
class nsIAtom;
|
|
class nsIContent;
|
|
class nsIDocument;
|
|
class nsITimer;
|
|
class nsIURL;
|
|
class nsIPresShell;
|
|
class nsViewerApp;
|
|
class AtomHashTable;
|
|
|
|
class nsWebCrawler : public nsISupports {
|
|
public:
|
|
nsWebCrawler(nsViewerApp* aViewer);
|
|
|
|
// nsISupports
|
|
NS_DECL_ISUPPORTS
|
|
|
|
// nsIStreamObserver
|
|
NS_IMETHOD OnStartBinding(nsIURL* aURL, const char *aContentType);
|
|
NS_IMETHOD OnProgress(nsIURL* aURL, PRInt32 aProgress, PRInt32 aProgressMax);
|
|
NS_IMETHOD OnStatus(nsIURL* aURL, const nsString& aMsg);
|
|
NS_IMETHOD OnStopBinding(nsIURL* aURL, PRInt32 status, const nsString& aMsg);
|
|
|
|
// Add a url to load
|
|
void AddURL(const nsString& aURL);
|
|
|
|
// Add a domain that is safe to load url's from
|
|
void AddSafeDomain(const nsString& aDomain);
|
|
|
|
// Add a domain that must be avoided
|
|
void AddAvoidDomain(const nsString& aDomain);
|
|
|
|
void SetBrowserWindow(nsIBrowserWindow* aWindow);
|
|
|
|
// Set the delay (by default, the timer is set to one second)
|
|
void SetDelay(PRInt32 aSeconds) {
|
|
mDelay = aSeconds;
|
|
}
|
|
|
|
/** Set the initial window width */
|
|
void SetWidth(PRInt32 aWidth) {
|
|
mWidth = aWidth;
|
|
}
|
|
|
|
/** Set the initial window width */
|
|
void SetHeight(PRInt32 aHeight) {
|
|
mHeight = aHeight;
|
|
}
|
|
|
|
void EnableJiggleLayout() {
|
|
mJiggleLayout = PR_TRUE;
|
|
}
|
|
|
|
// If set to TRUE the loader will post an exit message on exit
|
|
void SetExitOnDone(PRBool aPostExit) {
|
|
mPostExit = aPostExit;
|
|
}
|
|
|
|
// Start loading documents
|
|
void Start();
|
|
|
|
// Enable the crawler; when a document contains links to other
|
|
// documents the crawler will go to them subject to the limitations
|
|
// on the total crawl count and the domain name checks.
|
|
void EnableCrawler();
|
|
|
|
void SetRecordFile(FILE* aFile) {
|
|
mRecord = aFile;
|
|
}
|
|
|
|
void SetMaxPages(PRInt32 aMax) {
|
|
mMaxPages = aMax;
|
|
}
|
|
|
|
/** set the web crawler filter, used for automatical output of frames */
|
|
void SetFilter(const nsString& aFilter);
|
|
|
|
/** set the web crawler filter, used for automatical output of frames */
|
|
void SetOutputDir(const nsString& aOutputDir);
|
|
|
|
void LoadNextURL();
|
|
|
|
protected:
|
|
virtual ~nsWebCrawler();
|
|
|
|
void FindURLsIn(nsIDocument* aDocument, nsIContent* aNode);
|
|
|
|
void FindMoreURLs();
|
|
|
|
PRBool OkToLoad(const nsString& aURLSpec);
|
|
|
|
void RecordLoadedURL(const nsString& aURLSpec);
|
|
|
|
/** generate an output name from a URL */
|
|
FILE * GetOutputFile(nsIURL *aURL);
|
|
|
|
nsIPresShell* GetPresShell();
|
|
|
|
nsIBrowserWindow* mBrowser;
|
|
nsViewerApp* mViewer;
|
|
nsITimer* mTimer;
|
|
FILE* mRecord;
|
|
nsIAtom* mLinkTag;
|
|
nsIAtom* mFrameTag;
|
|
nsIAtom* mIFrameTag;
|
|
AtomHashTable* mVisited;
|
|
nsString* mFilter;
|
|
nsString* mOutputDir;
|
|
|
|
PRBool mCrawl;
|
|
PRBool mJiggleLayout;
|
|
PRBool mPostExit;
|
|
PRInt32 mDelay;
|
|
PRInt32 mWidth;
|
|
PRInt32 mHeight;
|
|
PRInt32 mMaxPages;
|
|
|
|
nsVoidArray mPendingURLs;
|
|
nsVoidArray mSafeDomains;
|
|
nsVoidArray mAvoidDomains;
|
|
};
|
|
|
|
#endif /* nsWebCrawler_h___ */
|