Versions in this module Expand all Collapse all v2 v2.0.26 Jun 2, 2026 Changes in this version + var AssetsRegex = `(?i)\b(?:src|href)=["']([^"']+\.(?:css|js|png|jpg|jpeg|gif|svg|webp|woff|woff2|ttf|eot))["']` + var LinkRegex = regexp.MustCompile(`(?i)https?://[^<>'",\s/]+\.[^<>'",\s/]+(?:/[^<>'",\s]*)?`) + var LinkRegexStrict = MustStrictHTTPOnly() + var ObjectStorageServers = func() (s []string) { ... }() + func AddAtImportLinksToItemChild(item *models.Item, atImportLinks []*models.URL) + func ExtractFromStringCSS(css string, inline bool) (links []string, atImportLinks []string) + func ExtractFromURLCSS(URL *models.URL) (links []*models.URL, atImportLinks []*models.URL, err error) + func GetEmbeddedCSSJump(item *models.Item) int + func GetURLsFromJSON(decoder *json.Decoder) (assets, outlinks []string, err error) + func HTMLAssets(item *models.Item) (assets []*models.URL, err error) + func IsCSS(URL *models.URL) bool + func IsEmbeddedCSS(item *models.Item) bool + func IsHTML(URL *models.URL) bool + func IsJSON(URL *models.URL) bool + func IsM3U8(URL *models.URL) bool + func IsSitemapXML(URL *models.URL) bool + func IsXML(URL *models.URL) bool + func JSON(URL *models.URL) (assets, outlinks []*models.URL, err error) + func M3U8(URL *models.URL) (assets []*models.URL, err error) + func MustStrictHTTPOnly() *regexp.Regexp + func QuotedLinkRegexFindAll(s string) []string + func TransformDocument(u *models.URL) (doc *goquery.Document, err error) + func XML(URL *models.URL) (assets, outlinks []*models.URL, err error) + type AzureBlob struct + LastModified string + Name string + Size int64 + type AzureBlobEnumerationResults struct + Blobs []AzureBlob + Marker string + NextMarker string + Prefix string + XMLName xml.Name + type CommonPrefix struct + Prefix []string + type HTMLOutlinkExtractor struct + func (HTMLOutlinkExtractor) Extract(URL *models.URL) (outlinks []*models.URL, err error) + func (HTMLOutlinkExtractor) Match(URL *models.URL) bool + func (HTMLOutlinkExtractor) Support(m Mode) bool + type LinkHeaderExtractor struct + func (l LinkHeaderExtractor) ExtractLink(URL *models.URL) (URLs []*models.URL) + func (l LinkHeaderExtractor) Match(URL *models.URL) bool + func (l LinkHeaderExtractor) Support(m Mode) bool + type Mode int + const ModeGeneral + const ModeHeadless + type ObjectStorageOutlinkExtractor struct + func (ObjectStorageOutlinkExtractor) Extract(URL *models.URL) ([]*models.URL, error) + func (ObjectStorageOutlinkExtractor) Match(URL *models.URL) bool + func (ObjectStorageOutlinkExtractor) Support(m Mode) bool + type PDFOutlinkExtractor struct + func (PDFOutlinkExtractor) Extract(URL *models.URL) (outlinks []*models.URL, err error) + func (PDFOutlinkExtractor) Match(URL *models.URL) bool + func (PDFOutlinkExtractor) Support(m Mode) bool + type S3ListBucketResult struct + CommonPrefixes []CommonPrefix + Contents []S3Object + IsTruncated bool + Marker string + Name string + NextContinuationToken string + Prefix string + XMLName xml.Name + type S3Object struct + Key string + LastModified string + Size int64 + type SitemapXMLOutlinkExtractor struct + func (SitemapXMLOutlinkExtractor) Extract(URL *models.URL) ([]*models.URL, error) + func (SitemapXMLOutlinkExtractor) Match(URL *models.URL) bool + func (SitemapXMLOutlinkExtractor) Support(m Mode) bool
Go to main page