config

Documentation

Index

• type Asset
• type Assets
• type Chapter
• type ChapterContent
• type CleanupOptions
• type General
• type NovelConfig
  • func (s *NovelConfig) DoURLReplacements(checkedURL string) (chapterUrl string, changed bool)
  • func (s *NovelConfig) GetSiteConfigFromURL(url *url.URL) *SiteConfiguration
  • func (s *NovelConfig) IsURLBlacklisted(checkedURL string) bool
• type Pagination
• type Parser
  • func NewParser() *Parser
  • func (p *Parser) ReadConfigurationFile(fileName string) (novelConfig *NovelConfig, err error)
• type Replacement
• type SiteConfiguration
• type Source
• type SourceContent
• type TemplateChapter
• type TemplateToC
• type Templates
• type TitleContent
• type Toc
• type Translator
• type WaybackMachine

Types

type Asset

type Asset struct {
	HostPath     string `yaml:"path"`
	InternalPath string
}

Asset contains the path on the host system and after being added the internal path of the epub

type Assets

type Assets struct {
	CSS  Asset `yaml:"css"`
	Font Asset `yaml:"fonts"`
}

Assets contains the included assets in each added section

type Chapter

type Chapter struct {
	URL           string `yaml:"url"`
	SourceContent `yaml:",inline"`
}

Chapter is the struct for a single chapter, requires on the URL also implements the ChapterContent struct

type ChapterContent

type ChapterContent struct {
	ContentSelector *string `yaml:"content-selector"`
	CleanupOptions  `yaml:",inline"`
}

ChapterContent contains the content selector the content cleanup options

type CleanupOptions

type CleanupOptions struct {
	PrefixSelectors *[]string `yaml:"prefix-selectors"`
	SuffixSelectors *[]string `yaml:"suffix-selectors"`
	StripRegex      string    `yaml:"strip-regex"`
	CleanupRegex    string    `yaml:"cleanup-regex"`
}

CleanupOptions are all options related to cleaning up the extracted content of titles and chapters

type General

type General struct {
	Title       string        `yaml:"title"`
	AltTitle    string        `yaml:"alt-title"`
	Author      string        `yaml:"author"`
	Description string        `yaml:"description"`
	Cover       string        `yaml:"cover"`
	Language    string        `yaml:"language"`
	Raw         string        `yaml:"raw"`
	Translators []*Translator `yaml:"translators"`
}

General contains the general information about the novel

type NovelConfig

type NovelConfig struct {
	BaseDirectory string
	General       General             `yaml:"general"`
	Sites         []SiteConfiguration `yaml:"sites"`
	Chapters      []Source            `yaml:"chapters"`
	Assets        Assets              `yaml:"assets"`
	BackList      []string            `yaml:"blacklist"`
	Replacements  []Replacement       `yaml:"replacements"`
	Templates     Templates           `yaml:"templates"`
}

NovelConfig contains the configuration of the novel scraper

func (*NovelConfig) DoURLReplacements

func (s *NovelConfig) DoURLReplacements(checkedURL string) (chapterUrl string, changed bool)

DoURLReplacements checks if the passed URL is getting replaced through the configuration

func (*NovelConfig) GetSiteConfigFromURL

func (s *NovelConfig) GetSiteConfigFromURL(url *url.URL) *SiteConfiguration

GetSiteConfigFromURL retrieves the site configuration for the passed URL will return an empty site configuration with nil values if no site configuration for host exists

func (*NovelConfig) IsURLBlacklisted

func (s *NovelConfig) IsURLBlacklisted(checkedURL string) bool

IsURLBlacklisted checks if the passed URL is blacklisted it parses the passed URL and the blacklisted URLs to ignore minor differences like f.e. trailing slash

type Pagination

type Pagination struct {
	ReversePosts     *bool   `yaml:"reverse-posts"`
	NextPageSelector *string `yaml:"next-page-selector"`
}

Pagination contains all implemented options for paginations of websites

type Parser

type Parser struct{}

Parser is a struct solely to prevent expose functions without setting up first

func NewParser

func NewParser() *Parser

NewParser returns a pointer to an initialized parser struct

func (*Parser) ReadConfigurationFile

func (p *Parser) ReadConfigurationFile(fileName string) (novelConfig *NovelConfig, err error)

ReadConfigurationFile tries to read the passed configuration file and parse it into a NovelConfig struct

type Replacement

type Replacement struct {
	Url            string `yaml:"url"`
	ReplacementURL string `yaml:"replacement"`
}

Replacement contains the replaced URL and their replacement

type SiteConfiguration

type SiteConfiguration struct {
	Host           string     `yaml:"host"`
	Pagination     Pagination `yaml:"pagination"`
	SourceContent  `yaml:",inline"`
	Redirects      []string       `yaml:"redirects"`
	WaybackMachine WaybackMachine `yaml:"wayback-machine"`
}

SiteConfiguration is an optional configuration to extract the Pagination struct and the ChapterContent struct into one Configuration object, allowing multiple sources of the same Host to reuse them Source options have a higher priority than the SiteConfiguration options

type Source

type Source struct {
	Toc     *Toc     `yaml:"toc"`
	Chapter *Chapter `yaml:"chapter"`
}

Source is the option to define the source of the chapter content, table of content or single chapter

type SourceContent

type SourceContent struct {
	TitleContent   `yaml:"title-content"`
	ChapterContent `yaml:"chapter-content"`
}

SourceContent contains all configurations required for any type of source

type TemplateChapter

type TemplateChapter struct {
	Content string `yaml:"content"`
	Title   string `yaml:"title"`
}

TemplateChapter contains all templates related to the chapter pages

type TemplateToC

type TemplateToC struct {
	Content    string `yaml:"content"`
	AltTitle   string `yaml:"alt-title"`
	Translator string `yaml:"translator"`
}

TemplateToC contains all templates related to the table of content page

type Templates

type Templates struct {
	ToC     TemplateToC     `yaml:"toc"`
	Chapter TemplateChapter `yaml:"chapter"`
}

Templates contains a collection of templates to style the generated epub file

type TitleContent

type TitleContent struct {
	AddPrefix      *bool   `yaml:"add-prefix"`
	TitleSelector  *string `yaml:"title-selector"`
	CleanupOptions `yaml:",inline"`
}

TitleContent contains the title selector and the title cleanup options

type Toc

type Toc struct {
	URL             string `yaml:"url"`
	ChapterSelector string `yaml:"chapter-selector"`
	Pagination      `yaml:"pagination"`
	SourceContent   `yaml:",inline"`
}

Toc is the struct for a table of content, requires the URL and the ChapterSelectors and implements the Pagination struct and the ChapterContent struct

type Translator

type Translator struct {
	Name string `yaml:"name"`
	URL  string `yaml:"url"`
}

Translator contains the name and website of the translators

type WaybackMachine

type WaybackMachine struct {
	Use     bool        `yaml:"use"`
	Version json.Number `yaml:"version"`
}

WaybackMachine contains the usage and version option of a site