Safe Haskell	None
Language	Haskell2010

Follow.Fetchers.WebScraping.Internal

Description

This module contains the inner wiring for the scraping fetching strategy.

Synopsis

data Selector = Selector {
- selURI :: Maybe SelectorItem
- selGUID :: Maybe SelectorItem
- selTitle :: Maybe SelectorItem
- selDescription :: Maybe SelectorItem
- selAuthor :: Maybe SelectorItem
- selPublishDate :: Maybe SelectorItem
}
data SelectorItem
- = InnerText CSSSelector
- | Attr CSSSelector HTMLAttribute
type CSSSelector = Text
type HTMLAttribute = Text
htmlToEntries :: ByteString -> Selector -> IO [Entry]

Documentation

data Selector Source #

Data type with the selectors to use when scraping each Entry item.

Constructors

Selector
Fields selURI :: Maybe SelectorItem selGUID :: Maybe SelectorItem selTitle :: Maybe SelectorItem selDescription :: Maybe SelectorItem selAuthor :: Maybe SelectorItem selPublishDate :: Maybe SelectorItem

Instances

Eq Selector Source #
Instance details Defined in Follow.Fetchers.WebScraping.Internal Methods (==) :: Selector -> Selector -> Bool # (/=) :: Selector -> Selector -> Bool #
Show Selector Source #
Instance details Defined in Follow.Fetchers.WebScraping.Internal Methods showsPrec :: Int -> Selector -> ShowS # show :: Selector -> String # showList :: [Selector] -> ShowS #
FromJSON Selector #	uri: # See `SelectorItem` instance title: null description: null guid: null author: null publish_date: null
Instance details Defined in Follow.Parser Methods parseJSON :: Value -> Parser Selector # parseJSONList :: Value -> Parser [Selector] #

data SelectorItem Source #

Selector to use when scraping an Entry item.

Constructors

InnerText CSSSelector	This selector will take the inner text immediately descendant of a tag selected with given css selector.
Attr CSSSelector HTMLAttribute	This selector will take the value of given argument in the tag matched by given css selector.

Instances

Eq SelectorItem Source #
Instance details Defined in Follow.Fetchers.WebScraping.Internal Methods (==) :: SelectorItem -> SelectorItem -> Bool # (/=) :: SelectorItem -> SelectorItem -> Bool #
Show SelectorItem Source #
Instance details Defined in Follow.Fetchers.WebScraping.Internal Methods showsPrec :: Int -> SelectorItem -> ShowS # show :: SelectorItem -> String # showList :: [SelectorItem] -> ShowS #
FromJSON SelectorItem #	type: text options: css: .selector or type: attr options: css: .link name: href
Instance details Defined in Follow.Parser Methods parseJSON :: Value -> Parser SelectorItem # parseJSONList :: Value -> Parser [SelectorItem] #

type CSSSelector = Text Source #

A CSS2 selector.

type HTMLAttribute = Text Source #

An HTML attribute name.

htmlToEntries :: ByteString -> Selector -> IO [Entry] Source #

Converts a bytestring with HTML content to a list of entries, scraping entry items using given selector. The return type is wrapped within an IO because of the underlying vendor API.