selector

package

v0.0.1-dev.4 Latest Latest Go to latest Published: Apr 3, 2023 License: Apache-2.0 Imports: 6 Imported by: 0

Details

Valid go.mod file

The Go module system was introduced in Go 1.11 and is the official dependency management solution for Go.
Redistributable license

Redistributable licenses place minimal restrictions on how software can be used, modified, and redistributed.
Tagged version

Modules with tagged versions give importers more predictable builds.
Stable version

When a project reaches major version v1 it is considered stable.
Learn more about best practices

Repository

github.com/gogodjzhu/gogoscrapy

Documentation ¶

Index ¶

Variables
type CssSelector
type HtmlNode
type LinkSelector
type NodeSelector
type PlainText
type RegexSelector
- func NewRegexSelector(regexStr string) (*RegexSelector, error)
- func (this RegexSelector) SelectString(src string) string
- func (this RegexSelector) SelectStringList(src string) []string
type ReplaceSelector
- func NewReplaceSelector(regexStr string, replacement string) (*ReplaceSelector, error)
- func (this ReplaceSelector) SelectString(text string) string
- func (this ReplaceSelector) SelectStringList(regexStr string) []string
type Selectable
type Selector

Constants ¶

This section is empty.

Variables ¶

View Source

var LOG = utils.NewLogger()

Functions ¶

This section is empty.

Types ¶

type CssSelector ¶

type CssSelector struct {
	SelectorText string
	AttrName     string
	Pretty       bool
}

func (CssSelector) Select ¶

func (this CssSelector) Select(node *html.Node) string

func (CssSelector) SelectList ¶

func (this CssSelector) SelectList(node *html.Node) []string

func (CssSelector) SelectNode ¶

func (this CssSelector) SelectNode(node *html.Node) *html.Node

func (CssSelector) SelectNodeList ¶

func (this CssSelector) SelectNodeList(node *html.Node) []*html.Node

type HtmlNode ¶

type HtmlNode struct {
	Elements []*html.Node
}

func (HtmlNode) Css ¶

func (this HtmlNode) Css(selectorText string) Selectable

func (HtmlNode) CssWithAttr ¶

func (this HtmlNode) CssWithAttr(selectorText string, attrName string) Selectable

has attribute, consider as plaintext

func (HtmlNode) Html ¶

func (this HtmlNode) Html() string

func (HtmlNode) Links ¶

func (this HtmlNode) Links() Selectable

func (HtmlNode) Match ¶

func (this HtmlNode) Match() bool

func (HtmlNode) Nodes ¶

func (this HtmlNode) Nodes() []Selectable

func (HtmlNode) Regex ¶

func (this HtmlNode) Regex(regex string) Selectable

func (HtmlNode) Replace ¶

func (this HtmlNode) Replace(src, replacement string) Selectable

func (HtmlNode) Text ¶

func (this HtmlNode) Text() string

type LinkSelector ¶

type LinkSelector struct{}

func (LinkSelector) Select ¶

func (LinkSelector) Select(node *html.Node) string

func (LinkSelector) SelectList ¶

func (LinkSelector) SelectList(node *html.Node) []string

func (LinkSelector) SelectNode ¶

func (LinkSelector) SelectNode(node *html.Node) *html.Node

func (LinkSelector) SelectNodeList ¶

func (LinkSelector) SelectNodeList(node *html.Node) []*html.Node

type NodeSelector ¶

type NodeSelector interface {
	Select(node *html.Node) string
	SelectList(node *html.Node) []string
	SelectNode(node *html.Node) *html.Node
	SelectNodeList(node *html.Node) []*html.Node
}

type PlainText ¶

type PlainText struct {
	SourceTexts []string
}

func (PlainText) Css ¶

func (this PlainText) Css(selector string) Selectable

func (PlainText) CssWithAttr ¶

func (this PlainText) CssWithAttr(selector string, attrName string) Selectable

func (PlainText) Html ¶

func (this PlainText) Html() string

func (PlainText) Links ¶

func (this PlainText) Links() Selectable

func (PlainText) Match ¶

func (this PlainText) Match() bool

func (PlainText) Nodes ¶

func (this PlainText) Nodes() []Selectable

func (PlainText) Regex ¶

func (this PlainText) Regex(regex string) Selectable

func (PlainText) Replace ¶

func (this PlainText) Replace(regexStr, replacement string) Selectable

func (PlainText) Text ¶

func (this PlainText) Text() string

type RegexSelector ¶

type RegexSelector struct {
	RegexStr string
	// contains filtered or unexported fields
}

func NewRegexSelector ¶

func NewRegexSelector(regexStr string) (*RegexSelector, error)

func (RegexSelector) SelectString ¶

func (this RegexSelector) SelectString(src string) string

func (RegexSelector) SelectStringList ¶

func (this RegexSelector) SelectStringList(src string) []string

type ReplaceSelector ¶

type ReplaceSelector struct {
	RegexStr string

	Replacement string
	// contains filtered or unexported fields
}

func NewReplaceSelector ¶

func NewReplaceSelector(regexStr string, replacement string) (*ReplaceSelector, error)

func (ReplaceSelector) SelectString ¶

func (this ReplaceSelector) SelectString(text string) string

func (ReplaceSelector) SelectStringList ¶

func (this ReplaceSelector) SelectStringList(regexStr string) []string

type Selectable ¶

type Selectable interface {
	Links() Selectable
	Regex(regex string) Selectable
	Html() string
	Text() string
	Match() bool
	Css(selectorText string) Selectable
	CssWithAttr(selectorText, attrName string) Selectable
	Replace(regex, replacement string) Selectable
	Nodes() []Selectable
}

type Selector ¶

type Selector interface {
	SelectString(src string) string
	SelectStringList(src string) []string
}

Source Files ¶

View all Source files

?	: This menu
/	: Search site
f or F	: Jump to
y or Y	: Canonical URL