parse

package

v1.0.0 Latest Latest Go to latest Published: Jan 19, 2022 License: AGPL-3.0 Imports: 12 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/smallsung/gocrawler

Links

Open Source Insights

Documentation ¶

Index ¶

func NewNotExpectValueError(got interface{}) error
type Document
- func Dom(b []byte) (dom *Document, err error)
- func NewDocumentFromBytes(b []byte) (dom *Document, err error)
type DocumentError
type DomEachFunc
type JsonUnmarshalError
type NotExpectValueError
type Parser
- func Parse(b []byte, mode ParserMode) (*Parser, error)
- func (receiver *Parser) DebugStoreTestDir()
type ParserMode
type RegexpNotMatchError
type RegexpWrapper
- func Regexp(regexp *regexp.Regexp) *RegexpWrapper

Constants ¶

This section is empty.

Variables ¶

This section is empty.

Functions ¶

func NewNotExpectValueError ¶

func NewNotExpectValueError(got interface{}) error

Types ¶

type Document ¶

type Document struct {
	Selection *goquery.Selection
}

func Dom ¶

func Dom(b []byte) (dom *Document, err error)

func NewDocumentFromBytes ¶

func NewDocumentFromBytes(b []byte) (dom *Document, err error)

func (*Document) Attr ¶

func (dom *Document) Attr(attrName string) (string, error)

func (*Document) Each ¶

func (dom *Document) Each(fn DomEachFunc) error

Each 返回最后一次错误

func (*Document) EachWithBreak ¶

func (dom *Document) EachWithBreak(fn DomEachFunc) error

func (*Document) Eq ¶

func (dom *Document) Eq(index int) *Document

func (*Document) Find ¶

func (dom *Document) Find(selector string) *Document

func (*Document) InnerHTML ¶

func (dom *Document) InnerHTML() (innerHTML string, err error)

func (*Document) InnerHTMLWithoutError ¶

func (dom *Document) InnerHTMLWithoutError() string

func (*Document) InnerText ¶

func (dom *Document) InnerText() string

func (*Document) Length ¶

func (dom *Document) Length() int

func (*Document) MustFind ¶

func (dom *Document) MustFind(selector string) (*Document, error)

func (*Document) OuterHtml ¶

func (dom *Document) OuterHtml() (outerHtml string, err error)

func (*Document) Text ¶

func (dom *Document) Text() string

func (*Document) TrimSpaceInnerText ¶

func (dom *Document) TrimSpaceInnerText() string

func (*Document) TrimSpaceText ¶

func (dom *Document) TrimSpaceText() string

type DocumentError ¶

type DocumentError struct {
	errors.LocatorError
}

type DomEachFunc ¶

type DomEachFunc func(i int, dom *Document) error

type JsonUnmarshalError ¶

type JsonUnmarshalError struct {
	errors.Err
}

type NotExpectValueError ¶

type NotExpectValueError struct {
	errors.Err
}

type Parser ¶

type Parser struct {
	Json   *_json
	Regexp *_regexp

	Dom *Document
	// contains filtered or unexported fields
}

func Parse ¶

func Parse(b []byte, mode ParserMode) (*Parser, error)

func (*Parser) DebugStoreTestDir ¶

func (receiver *Parser) DebugStoreTestDir()

type ParserMode ¶

type ParserMode uint8

const (
	ModeEnableJson ParserMode = 1 << iota
	ModeEnableDom
	ModeEnableRegexp
)

type RegexpNotMatchError ¶

type RegexpNotMatchError struct {
	errors.Err
}

type RegexpWrapper ¶

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

func Regexp ¶

func Regexp(regexp *regexp.Regexp) *RegexpWrapper

func (*RegexpWrapper) FindAllStringSubMatch ¶

func (receiver *RegexpWrapper) FindAllStringSubMatch(s string, n int) ([][]string, error)

func (*RegexpWrapper) FindStringSubMatch ¶

func (receiver *RegexpWrapper) FindStringSubMatch(s string) ([]string, error)

func (*RegexpWrapper) FindSubMatch ¶

func (receiver *RegexpWrapper) FindSubMatch(b []byte) ([][]byte, error)

Source Files ¶

View all Source files

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