parsers

Documentation

Overview

parsers is an interface that Colibri can use to parse the content of responses.

Index

• Constants
• Variables
• func Set[T colibri.Node](parsers *Parsers, expr string, parserFunc func(colibri.Response) (T, error)) error
• type HTMLNode
  • func ParseHTML(resp colibri.Response) (*HTMLNode, error)
  • func (html *HTMLNode) CSSFind(expr string) (colibri.Node, error)
  • func (html *HTMLNode) CSSFindAll(expr string) ([]colibri.Node, error)
  • func (html *HTMLNode) Find(selector *colibri.Selector) (colibri.Node, error)
  • func (html *HTMLNode) FindAll(selector *colibri.Selector) ([]colibri.Node, error)
  • func (html *HTMLNode) Value() any
  • func (html *HTMLNode) XPathFind(expr string) (colibri.Node, error)
  • func (html *HTMLNode) XPathFindAll(expr string) ([]colibri.Node, error)
• type JSONode
  • func ParseJSON(resp colibri.Response) (*JSONode, error)
  • func (json *JSONode) Find(selector *colibri.Selector) (colibri.Node, error)
  • func (json *JSONode) FindAll(selector *colibri.Selector) ([]colibri.Node, error)
  • func (json *JSONode) Value() any
• type Parsers
  • func New() (*Parsers, error)
  • func (parsers *Parsers) Clear()
  • func (parsers *Parsers) Match(contentType string) bool
  • func (parsers *Parsers) Parse(rules *colibri.Rules, resp colibri.Response) (colibri.Node, error)
• type TextNode
  • func ParseText(resp colibri.Response) (*TextNode, error)
  • func (text *TextNode) Find(selector *colibri.Selector) (colibri.Node, error)
  • func (text *TextNode) FindAll(selector *colibri.Selector) ([]colibri.Node, error)
  • func (text *TextNode) Value() any
• type XMLNode
  • func ParseXML(resp colibri.Response) (*XMLNode, error)
  • func (xml *XMLNode) Find(selector *colibri.Selector) (colibri.Node, error)
  • func (xml *XMLNode) FindAll(selector *colibri.Selector) ([]colibri.Node, error)
  • func (xml *XMLNode) Value() any

Constants

const (
	XPathExpr = "xpath"

	CSSelector = "css"

	RegularExpr = "regular"
)

const HTMLRegexp = `^text\/html`

HTMLRegexp contains a regular expression that matches the HTML MIME type.

const JSONRegexp = `^application\/(json|x-json|([a-z]+\+json))`

JSONRegexp contains a regular expression that matches the JSON MIME type.

const TextRegexp = `^text\/plain`

TextRegexp contains a regular expression that matches the MIME type plain text.

const XMLRegexp = `(?i)((application|image|message|model)/((\w|\.|-)+\+?)?|text/)(wb)?xml`

XMLRegexp contains a regular expression that matches the XML MIME type.

Variables

var (
	// ErrNotMatch is returned when Content-Tyepe does not match Paser.
	ErrNotMatch = errors.New("Content-Type does not match")

	// ErrExprType is returned when the expression type is not supported by the node.
	ErrExprType = errors.New("ExprType not compatible with node")
)

Functions

func Set

func Set[T colibri.Node](parsers *Parsers, expr string, parserFunc func(colibri.Response) (T, error)) error

Set adds a parser with its regular expression corresponding to the parsers.

Types

type HTMLNode

type HTMLNode struct {
	// contains filtered or unexported fields
}

func ParseHTML

func ParseHTML(resp colibri.Response) (*HTMLNode, error)

func (*HTMLNode) CSSFind

func (html *HTMLNode) CSSFind(expr string) (colibri.Node, error)

func (*HTMLNode) CSSFindAll

func (html *HTMLNode) CSSFindAll(expr string) ([]colibri.Node, error)

func (*HTMLNode) Find

func (html *HTMLNode) Find(selector *colibri.Selector) (colibri.Node, error)

func (*HTMLNode) FindAll

func (html *HTMLNode) FindAll(selector *colibri.Selector) ([]colibri.Node, error)

func (*HTMLNode) Value

func (html *HTMLNode) Value() any

func (*HTMLNode) XPathFind

func (html *HTMLNode) XPathFind(expr string) (colibri.Node, error)

func (*HTMLNode) XPathFindAll

func (html *HTMLNode) XPathFindAll(expr string) ([]colibri.Node, error)

type JSONode

type JSONode struct {
	// contains filtered or unexported fields
}

func ParseJSON

func ParseJSON(resp colibri.Response) (*JSONode, error)

func (*JSONode) Find

func (json *JSONode) Find(selector *colibri.Selector) (colibri.Node, error)

func (*JSONode) FindAll

func (json *JSONode) FindAll(selector *colibri.Selector) ([]colibri.Node, error)

func (*JSONode) Value

func (json *JSONode) Value() any

type Parsers

type Parsers struct {
	// contains filtered or unexported fields
}

Parsers is used to parse the content of the answers. When a regular expression matches the content type of the response, the content of the response is parsed with the parser corresponding to the regular expression.

func New

func New() (*Parsers, error)

New returns a new default parser to parse HTML, XHML, JSON, and plain text. See the colibri.Parser interface.

func (*Parsers) Clear

func (parsers *Parsers) Clear()

func (*Parsers) Match

func (parsers *Parsers) Match(contentType string) bool

Match returns true if the content-type is supported.

func (*Parsers) Parse

func (parsers *Parsers) Parse(rules *colibri.Rules, resp colibri.Response) (colibri.Node, error)

Parse parses the response based on the rules.

type TextNode

type TextNode struct {
	// contains filtered or unexported fields
}

func ParseText

func ParseText(resp colibri.Response) (*TextNode, error)

func (*TextNode) Find

func (text *TextNode) Find(selector *colibri.Selector) (colibri.Node, error)

func (*TextNode) FindAll

func (text *TextNode) FindAll(selector *colibri.Selector) ([]colibri.Node, error)

func (*TextNode) Value

func (text *TextNode) Value() any

type XMLNode

type XMLNode struct {
	// contains filtered or unexported fields
}

func ParseXML

func ParseXML(resp colibri.Response) (*XMLNode, error)

func (*XMLNode) Find

func (xml *XMLNode) Find(selector *colibri.Selector) (colibri.Node, error)

func (*XMLNode) FindAll

func (xml *XMLNode) FindAll(selector *colibri.Selector) ([]colibri.Node, error)

func (*XMLNode) Value

func (xml *XMLNode) Value() any