Constant Field Values

Contents

• com.norconex.*

com.norconex.*

com.norconex.collector.http.client.impl.GenericHttpClientFactory

Modifier and Type	Constant Field	Value
public static final String	AUTH_METHOD_BASIC	"basic"
public static final String	AUTH_METHOD_DIGEST	"digest"
public static final String	AUTH_METHOD_FORM	"form"
public static final String	AUTH_METHOD_KERBEROS	"Kerberos"
public static final String	AUTH_METHOD_NTLM	"ntlm"
public static final String	AUTH_METHOD_SPNEGO	"SPNEGO"
public static final int	DEFAULT_MAX_CONNECTIONS	200
public static final int	DEFAULT_MAX_CONNECTIONS_PER_ROUTE	20
public static final int	DEFAULT_MAX_IDLE_TIME	10000
public static final int	DEFAULT_MAX_REDIRECT	50
public static final int	DEFAULT_TIMEOUT	30000

com.norconex.collector.http.crawler.HttpCrawlerEvent

Modifier and Type	Constant Field	Value
public static final String	CREATED_ROBOTS_META	"CREATED_ROBOTS_META"
public static final String	REJECTED_CANONICAL	"REJECTED_NONCANONICAL"
public static final String	REJECTED_NONCANONICAL	"REJECTED_NONCANONICAL"
public static final String	REJECTED_REDIRECTED	"REJECTED_REDIRECTED"
public static final String	REJECTED_ROBOTS_META_NOINDEX	"REJECTED_ROBOTS_META_NOINDEX"
public static final String	REJECTED_ROBOTS_TXT	"REJECTED_ROBOTS_TXT"
public static final String	REJECTED_TOO_DEEP	"REJECTED_TOO_DEEP"
public static final String	URLS_EXTRACTED	"URLS_EXTRACTED"

com.norconex.collector.http.crawler.event.impl.URLStatusCrawlerEventListener

Modifier and Type	Constant Field	Value
public static final String	DEFAULT_FILENAME_PREFIX	"urlstatuses-"

com.norconex.collector.http.data.store.impl.jdbc.JDBCCrawlDataSerializer

Modifier and Type	Constant Field	Value
protected static final String	ALL_FIELDS	"reference, parentRootReference, isRootParentReference, state, metaChecksum, contentChecksum, contentType, crawlDate, depth, sitemapLastMod, sitemapChangeFreq, sitemapPriority, originalReference, referrerReference, referrerLinkTag, referrerLinkText, referrerLinkTitle, referencedUrls, redirectTrail "

com.norconex.collector.http.delay.impl.AbstractDelay

Modifier and Type	Constant Field	Value
protected static final int	TINY_SLEEP_MS	10

com.norconex.collector.http.delay.impl.AbstractDelayResolver

Modifier and Type	Constant Field	Value
public static final long	DEFAULT_DELAY	3000L
public static final String	SCOPE_CRAWLER	"crawler"
public static final String	SCOPE_SITE	"site"
public static final String	SCOPE_THREAD	"thread"

com.norconex.collector.http.doc.HttpMetadata

Modifier and Type	Constant Field	Value
public static final String	COLLECTOR_DEPTH	"collector.depth"
public static final String	COLLECTOR_REDIRECT_TRAIL	"collector.redirect-trail"
public static final String	COLLECTOR_REFERENCED_URLS	"collector.referenced-urls"
public static final String	COLLECTOR_REFERENCED_URLS_OUT_OF_SCOPE	"collector.referenced-urls-out-of-scope"
public static final String	COLLECTOR_REFERRER_LINK_TAG	"collector.referrer-link-tag"
public static final String	COLLECTOR_REFERRER_LINK_TEXT	"collector.referrer-link-text"
public static final String	COLLECTOR_REFERRER_LINK_TITLE	"collector.referrer-link-title"
public static final String	COLLECTOR_REFERRER_REFERENCE	"collector.referrer-reference"
public static final String	COLLECTOR_SM_CHANGE_FREQ	"collector.sitemap-changefreq"
public static final String	COLLECTOR_SM_LASTMOD	"collector.sitemap-lastmod"
public static final String	COLLECTOR_SM_PRORITY	"collector.sitemap-priority"
public static final String	COLLECTOR_URL	"collector.url"
public static final String	HTTP_CONTENT_LENGTH	"Content-Length"
public static final String	HTTP_CONTENT_TYPE	"Content-Type"

com.norconex.collector.http.fetch.impl.PhantomJSDocumentFetcher

Modifier and Type	Constant Field	Value
public static final String	COLLECTOR_PHANTOMJS_SCREENSHOT_INLINE	"collector.phantomjs-screenshot-inline"
public static final String	COLLECTOR_PHANTOMJS_SCREENSHOT_PATH	"collector.phantomjs-screenshot-path"
public static final String	DEFAULT_CONTENT_TYPE_PATTERN	"^(text/html|application/xhtml\\+xml|vnd.wap.xhtml\\+xml|x-asp)$"
public static final int	DEFAULT_RENDER_WAIT_TIME	3000
public static final String	DEFAULT_SCREENSHOT_IMAGE_FORMAT	"png"
public static final String	DEFAULT_SCREENSHOT_STORAGE_DISK_DIR	"./screenshots"
public static final float	DEFAULT_SCREENSHOT_ZOOM_FACTOR	1.0f
public static final String	DEFAULT_SCRIPT_PATH	"scripts/phantom.js"

com.norconex.collector.http.filter.impl.SegmentCountURLFilter

Modifier and Type	Constant Field	Value
public static final int	DEFAULT_SEGMENT_COUNT	10
public static final String	DEFAULT_SEGMENT_SEPARATOR_PATTERN	"/"

com.norconex.collector.http.processor.impl.FeaturedImageProcessor

Modifier and Type	Constant Field	Value
public static final String	COLLECTOR_FEATURED_IMAGE_INLINE	"collector.featured-image-inline"
public static final String	COLLECTOR_FEATURED_IMAGE_PATH	"collector.featured-image-path"
public static final String	COLLECTOR_FEATURED_IMAGE_URL	"collector.featured-image-url"
public static final String	DEFAULT_IMAGE_CACHE_DIR	"./featuredImageCache"
public static final int	DEFAULT_IMAGE_CACHE_SIZE	1000
public static final String	DEFAULT_IMAGE_FORMAT	"png"
public static final String	DEFAULT_PAGE_CONTENT_TYPE_PATTERN	"text/html|application/(xhtml\\+xml|vnd\\.wap.xhtml\\+xml|x-asp)"
public static final String	DEFAULT_STORAGE_DISK_DIR	"./featuredImages"

com.norconex.collector.http.robot.RobotsTxt

Modifier and Type	Constant Field	Value
public static final float	UNSPECIFIED_CRAWL_DELAY	-1.0f

com.norconex.collector.http.url.impl.GenericLinkExtractor

Modifier and Type	Constant Field	Value
public static final int	DEFAULT_MAX_URL_LENGTH	2048
public static final int	MAX_BUFFER_SIZE	1048576
public static final int	OVERLAP_SIZE	8192

com.norconex.collector.http.url.impl.RegexLinkExtractor

Modifier and Type	Constant Field	Value
public static final String	DEFAULT_CONTENT_TYPE_PATTERN	"text/.*"
public static final int	DEFAULT_MAX_URL_LENGTH	2048
public static final int	MAX_BUFFER_SIZE	1048576
public static final int	OVERLAP_SIZE	8192

com.norconex.collector.http.url.impl.XMLFeedLinkExtractor

Modifier and Type	Constant Field	Value
public static final String	DEFAULT_CONTENT_TYPE_PATTERN	"application/(rss\\+|rdf\\+|atom\\+){0,1}xml|text/xml"