Focused Crawler

byAlex R. •August 25, 2009

לאחרונה קיבלתי דוא"ל מסטודנט ברזילאי שהתעניין בפרוייקט אותו עשיתי בתקופת הלימודים.

מדובר בתוכנה שהייתה צריכה לממש מושג שנקרא חיפוש ממוקד - כלומר בהינתן תוכן מסויים, חיפוש תוכן דומה עד כמה שניתן ואיחזור דפים בהתאם להגדרות המשתמש.

Hi, I'm using the Focused Crawler (http://softlab-pro-web.technion.ac.il/projects/FocusCrawler/html/index.html) developed by you. I'm using it in a Database Research course in Federal University of Amazonas.

I don't know if you still work with this crawler but I wanted to ask two questions:

The focused crawler uses a breadth first or depth first search?
Is there any paper publication in conferences or workshops about the focused crawler developed?

Thank you

Felipe Hummel
Federal University of Amazonas
Manaus, Amazonas, Brazil

הנה הלינק לפרוייקט הכתוב בג'אבה עם Swing.

Focused Crawler

Tags תכנות

<script type="text/javascript" src="https://www.blogger.com/static/v1/widgets/984859869-widgets.js"></script>
<script type='text/javascript'>
window['__wavt'] = 'AOuZoY6FzwmuRH8qHpSSpZA1mqACg9i1BQ:1731775215295';_WidgetManager._Init('//www.blogger.com/rearrange?blogID\x3d2139279071038304164','//alexrait.blogspot.com/2009/08/focused-crawler.html','2139279071038304164');
_WidgetManager._SetDataContext([{'name': 'blog', 'data': {'blogId': '2139279071038304164', 'title': 'Coding with Alex', 'url': 'https://alexrait.blogspot.com/2009/08/focused-crawler.html', 'canonicalUrl': 'https://alexrait.blogspot.com/2009/08/focused-crawler.html', 'homepageUrl': 'https://alexrait.blogspot.com/', 'searchUrl': 'https://alexrait.blogspot.com/search', 'canonicalHomepageUrl': 'https://alexrait.blogspot.com/', 'blogspotFaviconUrl': 'https://alexrait.blogspot.com/favicon.ico', 'bloggerUrl': 'https://www.blogger.com', 'hasCustomDomain': false, 'httpsEnabled': true, 'enabledCommentProfileImages': true, 'gPlusViewType': 'FILTERED_POSTMOD', 'adultContent': false, 'analyticsAccountNumber': 'UA-202988341-1', 'encoding': 'UTF-8', 'locale': 'en', 'localeUnderscoreDelimited': 'en', 'languageDirection': 'ltr', 'isPrivate': false, 'isMobile': false, 'isMobileRequest': false, 'mobileClass': '', 'isPrivateBlog': false, 'isDynamicViewsAvailable': true, 'feedLinks': '\x3clink rel\x3d\x22alternate\x22 type\x3d\x22application/atom+xml\x22 title\x3d\x22Coding with Alex - Atom\x22 href\x3d\x22https://alexrait.blogspot.com/feeds/posts/default\x22 /\x3e\n\x3clink rel\x3d\x22alternate\x22 type\x3d\x22application/rss+xml\x22 title\x3d\x22Coding with Alex - RSS\x22 href\x3d\x22https://alexrait.blogspot.com/feeds/posts/default?alt\x3drss\x22 /\x3e\n\x3clink rel\x3d\x22service.post\x22 type\x3d\x22application/atom+xml\x22 title\x3d\x22Coding with Alex - Atom\x22 href\x3d\x22https://www.blogger.com/feeds/2139279071038304164/posts/default\x22 /\x3e\n\n\x3clink rel\x3d\x22alternate\x22 type\x3d\x22application/atom+xml\x22 title\x3d\x22Coding with Alex - Atom\x22 href\x3d\x22https://alexrait.blogspot.com/feeds/4849563687524418676/comments/default\x22 /\x3e\n', 'meTag': '', 'adsenseClientId': 'ca-pub-9348007134072555', 'adsenseHostId': 'ca-host-pub-1556223355139109', 'adsenseHasAds': false, 'adsenseAutoAds': false, 'boqCommentIframeForm': true, 'loginRedirectParam': '', 'view': '', 'dynamicViewsCommentsSrc': '//www.blogblog.com/dynamicviews/4224c15c4e7c9321/js/comments.js', 'dynamicViewsScriptSrc': '//www.blogblog.com/dynamicviews/3d970d7188fc7945', 'plusOneApiSrc': 'https://apis.google.com/js/platform.js', 'disableGComments': true, 'interstitialAccepted': false, 'sharing': {'platforms': [{'name': 'Get link', 'key': 'link', 'shareMessage': 'Get link', 'target': ''}, {'name': 'Facebook', 'key': 'facebook', 'shareMessage': 'Share to Facebook', 'target': 'facebook'}, {'name': 'BlogThis!', 'key': 'blogThis', 'shareMessage': 'BlogThis!', 'target': 'blog'}, {'name': 'X', 'key': 'twitter', 'shareMessage': 'Share to X', 'target': 'twitter'}, {'name': 'Pinterest', 'key': 'pinterest', 'shareMessage': 'Share to Pinterest', 'target': 'pinterest'}, {'name': 'Email', 'key': 'email', 'shareMessage': 'Email', 'target': 'email'}], 'disableGooglePlus': true, 'googlePlusShareButtonWidth': 0, 'googlePlusBootstrap': '\x3cscript type\x3d\x22text/javascript\x22\x3ewindow.___gcfg \x3d {\x27lang\x27: \x27en\x27};\x3c/script\x3e'}, 'hasCustomJumpLinkMessage': true, 'jumpLinkMessage': 'Blog Posts', 'pageType': 'item', 'postId': '4849563687524418676', 'pageName': 'Focused Crawler', 'pageTitle': 'Coding with Alex: Focused Crawler', 'metaDescription': ''}}, {'name': 'features', 'data': {}}, {'name': 'messages', 'data': {'edit': 'Edit', 'linkCopiedToClipboard': 'Link copied to clipboard!', 'ok': 'Ok', 'postLink': 'Post Link'}}, {'name': 'template', 'data': {'name': 'custom', 'localizedName': 'Custom', 'isResponsive': true, 'isAlternateRendering': false, 'isCustom': true}}, {'name': 'view', 'data': {'classic': {'name': 'classic', 'url': '?view\x3dclassic'}, 'flipcard': {'name': 'flipcard', 'url': '?view\x3dflipcard'}, 'magazine': {'name': 'magazine', 'url': '?view\x3dmagazine'}, 'mosaic': {'name': 'mosaic', 'url': '?view\x3dmosaic'}, 'sidebar': {'name': 'sidebar', 'url': '?view\x3dsidebar'}, 'snapshot': {'name': 'snapshot', 'url': '?view\x3dsnapshot'}, 'timeslide': {'name': 'timeslide', 'url': '?view\x3dtimeslide'}, 'isMobile': false, 'title': 'Focused Crawler', 'description': 'A collection of interesting software articles, tips and code snippets, mostly in .NET and JavaScript.', 'url': 'https://alexrait.blogspot.com/2009/08/focused-crawler.html', 'type': 'item', 'isSingleItem': true, 'isMultipleItems': false, 'isError': false, 'isPage': false, 'isPost': true, 'isHomepage': false, 'isArchive': false, 'isLabelSearch': false, 'postId': 4849563687524418676}}, {'name': 'widgets', 'data': [{'title': 'Default Thumbnail', 'type': 'Image', 'sectionId': 'pbt-panel', 'id': 'Image52'}, {'title': 'JSON Variables', 'type': 'HTML', 'sectionId': 'pbt-panel', 'id': 'HTML50'}, {'title': 'Coding with Alex', 'type': 'Image', 'sectionId': 'main-logo', 'id': 'Image50'}, {'title': '', 'type': 'LinkList', 'sectionId': 'xdfcb-main-menu', 'id': 'LinkList200'}, {'title': 'Links', 'type': 'LinkList', 'sectionId': 'headerbar', 'id': 'LinkList201'}, {'title': 'Follow Us', 'type': 'LinkList', 'sectionId': 'headerbar', 'id': 'LinkList202'}, {'title': 'Blog Posts', 'type': 'Blog', 'sectionId': 'main', 'id': 'Blog1', 'posts': [{'id': '4849563687524418676', 'title': 'Focused Crawler', 'showInlineAds': false}], 'headerByline': {'regionName': 'header1', 'items': [{'name': 'share', 'label': ''}, {'name': 'author', 'label': 'by'}, {'name': 'timestamp', 'label': '\u2022'}]}, 'footerBylines': [{'regionName': 'footer1', 'items': [{'name': 'comments', 'label': '$type\x3d{blogger}'}, {'name': 'icons', 'label': ''}]}, {'regionName': 'footer2', 'items': [{'name': 'labels', 'label': 'Tags'}]}], 'allBylineItems': [{'name': 'share', 'label': ''}, {'name': 'author', 'label': 'by'}, {'name': 'timestamp', 'label': '\u2022'}, {'name': 'comments', 'label': '$type\x3d{blogger}'}, {'name': 'icons', 'label': ''}, {'name': 'labels', 'label': 'Tags'}]}, {'title': 'You might like', 'type': 'HTML', 'sectionId': 'xdfcb-related-posts', 'id': 'HTML51'}, {'title': 'Coding with Alex (Header)', 'type': 'Header', 'sectionId': 'sidebar', 'id': 'Header1'}, {'title': 'Main Tags', 'type': 'Label', 'sectionId': 'sidebar', 'id': 'Label2'}, {'title': 'Total Pageviews', 'type': 'Stats', 'sectionId': 'sidebar', 'id': 'Stats1'}, {'title': 'Popular Posts', 'type': 'PopularPosts', 'sectionId': 'sidebar', 'id': 'PopularPosts2', 'posts': [{'title': 'The mystery behind file extensions', 'id': 3638078121481613638}, {'title': 'SHA256 support in windows XP', 'id': 3238970205216479489}, {'title': 'A skeleton for a .NET console application with dependency injection', 'id': 3036110136314605278}, {'title': 'Configure Log4Net in a .NET core application', 'id': 5202891952012580662}]}, {'title': 'Most Popular Posts', 'type': 'PopularPosts', 'sectionId': 'sidebar', 'id': 'PopularPosts1', 'posts': [{'title': 'The mystery behind file extensions', 'id': '3638078121481613638'}, {'title': 'SHA256 support in windows XP', 'id': '3238970205216479489'}, {'title': 'A skeleton for a .NET console application with dependency injection', 'id': '3036110136314605278'}, {'title': 'Configure Log4Net in a .NET core application', 'id': '5202891952012580662'}, {'title': 'Angular - display Enum in select', 'id': '5812690694279128850'}, {'title': 'Sign precomputed hash with bouncycastle (c#)', 'id': '6817314065043168772'}]}, {'title': 'About Us', 'type': 'Image', 'sectionId': 'xdfcb-about-section', 'id': 'Image51'}]}]);
_WidgetManager._RegisterWidget('_ImageView', new _WidgetInfo('Image52', 'pbt-panel', document.getElementById('Image52'), {'resize': true}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_HTMLView', new _WidgetInfo('HTML50', 'pbt-panel', document.getElementById('HTML50'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_ImageView', new _WidgetInfo('Image50', 'main-logo', document.getElementById('Image50'), {'resize': true}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_LinkListView', new _WidgetInfo('LinkList200', 'xdfcb-main-menu', document.getElementById('LinkList200'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_LinkListView', new _WidgetInfo('LinkList201', 'headerbar', document.getElementById('LinkList201'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_LinkListView', new _WidgetInfo('LinkList202', 'headerbar', document.getElementById('LinkList202'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_BlogView', new _WidgetInfo('Blog1', 'main', document.getElementById('Blog1'), {'cmtInteractionsEnabled': false, 'lightboxEnabled': true, 'lightboxModuleUrl': 'https://www.blogger.com/static/v1/jsbin/2784278825-lbx.js', 'lightboxCssUrl': 'https://www.blogger.com/static/v1/v-css/1964470060-lightbox_bundle.css'}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_HTMLView', new _WidgetInfo('HTML51', 'xdfcb-related-posts', document.getElementById('HTML51'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_HeaderView', new _WidgetInfo('Header1', 'sidebar', document.getElementById('Header1'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_LabelView', new _WidgetInfo('Label2', 'sidebar', document.getElementById('Label2'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_StatsView', new _WidgetInfo('Stats1', 'sidebar', document.getElementById('Stats1'), {'title': 'Total Pageviews', 'showGraphicalCounter': false, 'showAnimatedCounter': false, 'showSparkline': true, 'statsUrl': '//alexrait.blogspot.com/b/stats?style\x3dBLACK_TRANSPARENT\x26timeRange\x3dALL_TIME\x26token\x3dAPq4FmCWUbsQAeeFp-y79FxPcGfeqkVIAkRj_7sXPLh3d6wnEqkow-2GqDfAoiTDrw1d2_QM5FpibIYr3fl_BB_orFsczXsekw'}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_PopularPostsView', new _WidgetInfo('PopularPosts2', 'sidebar', document.getElementById('PopularPosts2'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_PopularPostsView', new _WidgetInfo('PopularPosts1', 'sidebar', document.getElementById('PopularPosts1'), {}, 'displayModeFull'));
_WidgetManager._RegisterWidget('_ImageView', new _WidgetInfo('Image51', 'xdfcb-about-section', document.getElementById('Image51'), {'resize': true}, 'displayModeFull'));
</script>
</body>