Text.HTML.CrawlChain.HtmlFiltering

Documentation

extractTagsContent :: String -> [TagContent]

Content of the tags up to the first child tag (as simplification) - with attributes.

findAttributes :: String -> [TagContent] -> [String]

extractLinks :: String -> [CrawlAction]

extractLinksMatching :: (String -> Bool) -> String -> [CrawlAction]

extractLinksWithAttributes :: AttrFilter -> String -> [CrawlAction]

extractLinksFilteringUrlAttrs :: (String -> Bool) -> AttrFilter -> String -> [CrawlAction]

extractLinksFilteringAll :: (String -> Bool) -> AttrFilter -> ContainedTextFilter -> String -> [CrawlAction]

unevaluated :: a -> Bool

findAllUrlsEndingWith :: String -> String -> [CrawlAction]

findFirstLinkAfter :: String -> [(String, String)] -> String -> [CrawlAction]

extractFirstForm :: [String] -> String -> Maybe Method -> String -> String -> Maybe CrawlAction

data Method

Constructors

POST

GET

noUrlFilter :: String -> Bool

type AttrFilter = [(String, String)] -> Bool

noAttrFilter :: AttrFilter

type ContainedTextFilter = [String] -> Bool

noTextFilter :: ContainedTextFilter