accept several urls, fix tests, remove unused book struct

.github/workflows/test.yml

@@ -14,7 +14,7 @@ jobs:
     - name: Set up Go
       uses: actions/setup-go@v2
       with:
-        go-version: 1.17
+        go-version: 1.18
     - name: Install kindlegen
       run: |
         curl -L https://github.com/lapwat/papeer/releases/download/kindlegen/kindlegen_linux_2.6_i386_v2_9.tar.gz > kindlegen.tar.gz

Makefile

@@ -8,7 +8,6 @@ install:
 	go install
 
 clean:
-	find . -maxdepth 1 -not -name 'README.md' -name '*.md' -delete
+	find . -maxdepth 1 -name '*.md' -not -name 'README.md' -delete
 	find . -maxdepth 1 -name '*.epub' -delete
 	find . -maxdepth 1 -name '*.mobi' -delete
-	find . -maxdepth 1 -name 'papeer-v*' -delete

README.md

@@ -141,7 +141,7 @@ go install github.com/lapwat/papeer@latest
 ```sh
 # use platform=darwin for MacOS
 platform=linux
-release=0.5.6
+release=0.6.0
 
 # download and extract
 curl -L https://github.com/lapwat/papeer/releases/download/v$release/papeer-v$release-$platform-amd64.tar.gz > papeer.tar.gz
@@ -154,7 +154,7 @@ sudo mv papeer /usr/local/bin
 
 ### Windows
 
-Download [latest release](https://github.com/lapwat/papeer/releases/download/v0.5.6/papeer-v0.5.6-windows-amd64.zip).
+Download [latest release](https://github.com/lapwat/papeer/releases/download/v0.6.0/papeer-v0.6.0-windows-amd64.zip).
 
 ## MOBI support
 

book/book.go

@@ -1,27 +0,0 @@
-package book
-
-type book struct {
-	name     string
-	author   string
-	chapters []chapter
-}
-
-func New(name, author string) book {
-	return book{name, author, []chapter{}}
-}
-
-func (b *book) AddChapter(c chapter) {
-	b.chapters = append(b.chapters, c)
-}
-
-func (b book) Name() string {
-	return b.name
-}
-
-func (b book) Author() string {
-	return b.name
-}
-
-func (b *book) Chapters() []chapter {
-	return b.chapters
-}

book/chapter.go

@@ -9,6 +9,10 @@ type chapter struct {
 	config      *ScrapeConfig
 }
 
+func NewEmptyChapter() chapter {
+	return chapter{"", "", "", "", []chapter{}, NewScrapeConfigNoInclude()}
+}
+
 func NewChapter(body, name, author, content string, subChapters []chapter, config *ScrapeConfig) chapter {
 	return chapter{body, name, author, content, subChapters, config}
 }
@@ -21,6 +25,10 @@ func (c chapter) Name() string {
 	return c.name
 }
 
+func (c *chapter) SetName(name string) {
+	c.name = name
+}
+
 func (c chapter) Author() string {
 	return c.author
 }
@@ -32,3 +40,7 @@ func (c chapter) Content() string {
 func (c chapter) SubChapters() []chapter {
 	return c.subChapters
 }
+
+func (c *chapter) AddSubChapter(newChapter chapter) {
+	c.subChapters = append(c.subChapters, newChapter)
+}

book/scraper.go

@@ -36,6 +36,10 @@ func NewScrapeConfig() *ScrapeConfig {
 	return &ScrapeConfig{0, "", false, -1, 0, false, -1, -1, true, false, false}
 }
 
+func NewScrapeConfigNoInclude() *ScrapeConfig {
+	return &ScrapeConfig{0, "", false, -1, 0, false, -1, -1, false, false, false}
+}
+
 func NewScrapeConfigs(selectors []string) []*ScrapeConfig {
 	configs := []*ScrapeConfig{}
 
@@ -93,46 +97,6 @@ func NewScrapeConfigFake() *ScrapeConfig {
 	return config
 }
 
-func NewBookFromURL(url string, selector []string, name, author string, include, ImagesOnly, useLinkName, quiet bool, limit, offset, delay, threads int) book {
-	config1 := NewScrapeConfig()
-	config1.ImagesOnly = ImagesOnly
-	config1.UseLinkName = useLinkName
-
-	var chapters []chapter
-	var home chapter
-
-	if len(selector) > 0 {
-		config2 := NewScrapeConfig()
-		config2.Selector = selector[0]
-		config2.Limit = limit
-		config2.Offset = offset
-		config2.Delay = delay
-		config2.Threads = threads
-		config2.Include = include
-		config2.ImagesOnly = ImagesOnly
-		config2.UseLinkName = useLinkName
-		chapters, home = tableOfContent(url, config2, config1, quiet)
-	} else {
-		chapters = []chapter{NewChapterFromURL(url, "", []*ScrapeConfig{config1}, 0, func(index int, name string) {})}
-		home = chapters[0]
-	}
-
-	if len(name) == 0 {
-		name = home.Name()
-	}
-
-	if len(author) == 0 {
-		author = home.Author()
-	}
-
-	b := New(name, author)
-	for _, c := range chapters {
-		b.AddChapter(c)
-	}
-
-	return b
-}
-
 func NewChapterFromURL(url, linkName string, configs []*ScrapeConfig, index int, updateProgressBarName func(index int, name string)) chapter {
 	config := configs[0]
 
@@ -397,6 +361,8 @@ func GetLinks(url *urllib.URL, selector string, limit, offset int, reverse, incl
 	parser := gofeed.NewParser()
 	feed, err := parser.ParseURL(url.String())
 
+	fmt.Println(feed, url.String(), err)
+
 	if err == nil {
 		// RSS feed
 

cmd/get.go

@@ -132,7 +132,6 @@ var getCmd = &cobra.Command{
 		return nil
 	},
 	Run: func(cmd *cobra.Command, args []string) {
-		url := args[0]
 
 		// generate config for each level
 		configs := make([]*book.ScrapeConfig, len(getOpts.Selector))
@@ -162,7 +161,13 @@ var getCmd = &cobra.Command{
 			configs[index] = config
 		}
 
-		c := book.NewChapterFromURL(url, "", configs, 0, func(index int, name string) {})
+		// dummy root chapter to contain all subchapters
+		c := book.NewEmptyChapter()
+		for _, u := range args {
+			newChapter := book.NewChapterFromURL(u, "", configs, 0, func(index int, name string) {})
+			c.AddSubChapter(newChapter)
+		}
+		c.SetName(c.SubChapters()[0].Name())
 
 		if getOpts.Format == "md" {
 			filename := book.ToMarkdown(c, getOpts.output)

cmd/version.go

@@ -14,6 +14,6 @@ var versionCmd = &cobra.Command{
 	Use:   "version",
 	Short: "Print the version number of papeer",
 	Run: func(cmd *cobra.Command, args []string) {
-		fmt.Println("papeer v0.5.6")
+		fmt.Println("papeer v0.6.0")
 	},
 }

go.mod

@@ -6,7 +6,7 @@ require (
 	github.com/JohannesKaufmann/html-to-markdown v1.3.5
 	github.com/bmaupin/go-epub v1.0.1
 	github.com/go-shiori/go-readability v0.0.0-20220215145315-dd6828d2f09b
-	github.com/jedib0t/go-pretty/v6 v6.3.5
+	github.com/jedib0t/go-pretty/v6 v6.3.6
 	github.com/mmcdole/gofeed v1.1.3
 	github.com/spf13/cobra v1.5.0
 )
@@ -21,7 +21,7 @@ require (
 require (
 	github.com/andybalholm/cascadia v1.3.1 // indirect
 	github.com/antchfx/htmlquery v1.2.5 // indirect
-	github.com/antchfx/xmlquery v1.3.11 // indirect
+	github.com/antchfx/xmlquery v1.3.12 // indirect
 	github.com/antchfx/xpath v1.2.1 // indirect
 	github.com/gabriel-vasile/mimetype v1.4.1 // indirect
 	github.com/go-shiori/dom v0.0.0-20210627111528-4e4722cd0d65 // indirect
@@ -30,7 +30,7 @@ require (
 	github.com/gogs/chardet v0.0.0-20211120154057-b7413eaefb8f // indirect
 	github.com/golang/groupcache v0.0.0-20210331224755-41bb18bfe9da // indirect
 	github.com/golang/protobuf v1.5.2 // indirect
-	github.com/inconshreveable/mousetrap v1.0.0 // indirect
+	github.com/inconshreveable/mousetrap v1.0.1 // indirect
 	github.com/json-iterator/go v1.1.12 // indirect
 	github.com/kennygrant/sanitize v1.2.4 // indirect
 	github.com/mattn/go-isatty v0.0.14 // indirect
@@ -38,15 +38,15 @@ require (
 	github.com/mmcdole/goxpp v0.0.0-20200921145534-2f3784f67354 // indirect
 	github.com/modern-go/concurrent v0.0.0-20180306012644-bacd9c7ef1dd // indirect
 	github.com/modern-go/reflect2 v1.0.2 // indirect
-	github.com/rivo/uniseg v0.3.0 // indirect
+	github.com/rivo/uniseg v0.3.4 // indirect
 	github.com/saintfish/chardet v0.0.0-20120816061221-3af4cd4741ca // indirect
 	github.com/sirupsen/logrus v1.9.0 // indirect
 	github.com/spf13/pflag v1.0.5 // indirect
 	github.com/temoto/robotstxt v1.1.2 // indirect
 	github.com/vincent-petithory/dataurl v1.0.0 // indirect
-	golang.org/x/net v0.0.0-20220726230323-06994584191e // indirect
+	golang.org/x/net v0.0.0-20220809012201-f428fae20770 // indirect
-	golang.org/x/sys v0.0.0-20220727055044-e65921a090b8 // indirect
+	golang.org/x/sys v0.0.0-20220808155132-1c4a2a72c664 // indirect
 	golang.org/x/text v0.3.7 // indirect
 	google.golang.org/appengine v1.6.7 // indirect
-	google.golang.org/protobuf v1.28.0 // indirect
+	google.golang.org/protobuf v1.28.1 // indirect
 )

go.sum

@@ -24,6 +24,8 @@ github.com/antchfx/xmlquery v1.3.10 h1:U2yMwr8U0KmGM2iDG2Ky/3LfxNsiK4uw1bSBkeMO9
 github.com/antchfx/xmlquery v1.3.10/go.mod h1:wojC/BxjEkjJt6dPiAqUzoXO5nIMWtxHS8PD8TmN4ks=
 github.com/antchfx/xmlquery v1.3.11 h1:8aRK7l3+dJjL8ZmwgVzG5AXysrP7Mss2424tfntKWKY=
 github.com/antchfx/xmlquery v1.3.11/go.mod h1:ywPcYkN0GvURUxXpUujaMVvuLSOYQBzoSfHKfAYezCE=
+github.com/antchfx/xmlquery v1.3.12 h1:6TMGpdjpO/P8VhjnaYPXuqT3qyJ/VsqoyNTmJzNBTQ4=
+github.com/antchfx/xmlquery v1.3.12/go.mod h1:3w2RvQvTz+DaT5fSgsELkSJcdNgkmg6vuXDEuhdwsPQ=
 github.com/antchfx/xpath v1.1.6/go.mod h1:Yee4kTMuNiPYJ7nSNorELQMr1J33uOpXDMByNYhvtNk=
 github.com/antchfx/xpath v1.1.8/go.mod h1:Yee4kTMuNiPYJ7nSNorELQMr1J33uOpXDMByNYhvtNk=
 github.com/antchfx/xpath v1.2.0 h1:mbwv7co+x0RwgeGAOHdrKy89GvHaGvxxBtPK0uF9Zr8=
@@ -123,11 +125,15 @@ github.com/grpc-ecosystem/grpc-gateway v1.9.0/go.mod h1:vNeuVxBJEsws4ogUvrchl83t
 github.com/hashicorp/hcl v1.0.0/go.mod h1:E5yfLk+7swimpb2L/Alb/PJmXilQ/rhwaUYs4T20WEQ=
 github.com/inconshreveable/mousetrap v1.0.0 h1:Z8tu5sraLXCXIcARxBp/8cbvlwVa7Z1NHg9XEKhtSvM=
 github.com/inconshreveable/mousetrap v1.0.0/go.mod h1:PxqpIevigyE2G7u3NXJIT2ANytuPF1OarO4DADm73n8=
+github.com/inconshreveable/mousetrap v1.0.1 h1:U3uMjPSQEBMNp1lFxmllqCPM6P5u/Xq7Pgzkat/bFNc=
+github.com/inconshreveable/mousetrap v1.0.1/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
 github.com/jawher/mow.cli v1.1.0/go.mod h1:aNaQlc7ozF3vw6IJ2dHjp2ZFiA4ozMIYY6PyuRJwlUg=
 github.com/jedib0t/go-pretty/v6 v6.3.1 h1:aOXiD9oqiuLH8btPQW6SfgtQN5zwhyfzZls8a6sPJ/I=
 github.com/jedib0t/go-pretty/v6 v6.3.1/go.mod h1:FMkOpgGD3EZ91cW8g/96RfxoV7bdeJyzXPYgz1L1ln0=
 github.com/jedib0t/go-pretty/v6 v6.3.5 h1:B6RuZT3Gz0NvFwADctw+gZn3cSA+jIHykXyd72zPgOY=
 github.com/jedib0t/go-pretty/v6 v6.3.5/go.mod h1:MgmISkTWDSFu0xOqiZ0mKNntMQ2mDgOcwOkwBEkMDJI=
+github.com/jedib0t/go-pretty/v6 v6.3.6 h1:A6w2BuyPMtf7M82BGRBys9bAba2C26ZX9lrlrZ7uH6U=
+github.com/jedib0t/go-pretty/v6 v6.3.6/go.mod h1:MgmISkTWDSFu0xOqiZ0mKNntMQ2mDgOcwOkwBEkMDJI=
 github.com/jonboulle/clockwork v0.1.0/go.mod h1:Ii8DK3G1RaLaWxj9trq07+26W01tbo22gdxWY5EU2bo=
 github.com/json-iterator/go v1.1.10/go.mod h1:KdQUCv79m/52Kvf8AW2vK1V8akMuk1QjK/uOdHXbAo4=
 github.com/json-iterator/go v1.1.12 h1:PV8peI4a0ysnczrg+LtxykD8LfKY9ML6u2jnxaEnrnM=
@@ -183,6 +189,8 @@ github.com/rivo/uniseg v0.2.0 h1:S1pD9weZBuJdFmowNwbpi7BJ8TNftyUImj/0WQi72jY=
 github.com/rivo/uniseg v0.2.0/go.mod h1:J6wj4VEh+S6ZtnVlnTBMWIodfgj8LQOQFoIToxlJtxc=
 github.com/rivo/uniseg v0.3.0 h1:eyC18g7xB83Dv/xlJXLgNkRidVoR7nqFZBJvqo/K188=
 github.com/rivo/uniseg v0.3.0/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUcx88=
+github.com/rivo/uniseg v0.3.4 h1:3Z3Eu6FGHZWSfNKJTOUiPatWwfc7DzJRU04jFUqJODw=
+github.com/rivo/uniseg v0.3.4/go.mod h1:FN3SvrM+Zdj16jyLfmOkMNblXMcoc8DfTHruCPUcx88=
 github.com/rogpeppe/fastuuid v0.0.0-20150106093220-6724a57986af/go.mod h1:XWv6SoW27p1b0cqNHllgS5HIMJraePCO15w5zCzIWYg=
 github.com/russross/blackfriday/v2 v2.0.1/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
 github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
@@ -270,6 +278,7 @@ golang.org/x/net v0.0.0-20210505024714-0287a6fb4125/go.mod h1:9nx3DQGgdP8bBQD5qx
 golang.org/x/net v0.0.0-20210505214959-0714010a04ed/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
 golang.org/x/net v0.0.0-20210614182718-04defd469f4e/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
 golang.org/x/net v0.0.0-20210916014120-12bc252f5db8/go.mod h1:9nx3DQGgdP8bBQD5qxJ1jj9UTztislL4KSBs9R2vV5Y=
+golang.org/x/net v0.0.0-20220127200216-cd36cc0744dd/go.mod h1:CfG3xpIq0wQ8r1q4Su4UZFWDARRcnwPjda9FqA0JpMk=
 golang.org/x/net v0.0.0-20220425223048-2871e0cb64e4 h1:HVyaeDAYux4pnY+D/SiwmLOR36ewZ4iGQIIrtnuCjFA=
 golang.org/x/net v0.0.0-20220425223048-2871e0cb64e4/go.mod h1:CfG3xpIq0wQ8r1q4Su4UZFWDARRcnwPjda9FqA0JpMk=
 golang.org/x/net v0.0.0-20220624214902-1bab6f366d9e/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
@@ -277,6 +286,8 @@ golang.org/x/net v0.0.0-20220725212005-46097bf591d3 h1:2yWTtPWWRcISTw3/o+s/Y4UOM
 golang.org/x/net v0.0.0-20220725212005-46097bf591d3/go.mod h1:AaygXjzTFtRAg2ttMY5RMuhpJ3cNnI0XpyFJD1iQRSM=
 golang.org/x/net v0.0.0-20220726230323-06994584191e h1:wOQNKh1uuDGRnmgF0jDxh7ctgGy/3P4rYWQRVJD4/Yg=
 golang.org/x/net v0.0.0-20220726230323-06994584191e/go.mod h1:AaygXjzTFtRAg2ttMY5RMuhpJ3cNnI0XpyFJD1iQRSM=
+golang.org/x/net v0.0.0-20220809012201-f428fae20770 h1:dIi4qVdvjZEjiMDv7vhokAZNGnz3kepwuXqFKYDdDMs=
+golang.org/x/net v0.0.0-20220809012201-f428fae20770/go.mod h1:YDH+HFinaLZZlnHAfSS6ZXJJ9M9t4Dl22yv3iI2vPwk=
 golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U=
 golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20181108010431-42b317875d0f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
@@ -305,6 +316,8 @@ golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f h1:v4INt8xihDGvnrfjMDVXGxw9w
 golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220727055044-e65921a090b8 h1:dyU22nBWzrmTQxtNrr4dzVOvaw35nUYE279vF9UmsI8=
 golang.org/x/sys v0.0.0-20220727055044-e65921a090b8/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220808155132-1c4a2a72c664 h1:v1W7bwXHsnLLloWYTVEdvGvA7BHMeBYsPcF0GLDxIRs=
+golang.org/x/sys v0.0.0-20220808155132-1c4a2a72c664/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
@@ -347,6 +360,8 @@ google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp0
 google.golang.org/protobuf v1.26.0/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
 google.golang.org/protobuf v1.28.0 h1:w43yiav+6bVFTBQFZX0r7ipe9JQ1QsbMgHwbBziscLw=
 google.golang.org/protobuf v1.28.0/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
+google.golang.org/protobuf v1.28.1 h1:d0NfwRgPtno5B1Wa6L2DAG+KivqkdutMf1UhdNx175w=
+google.golang.org/protobuf v1.28.1/go.mod h1:HV8QOd/L58Z+nl8r43ehVNZIU/HEI6OcFqwMG9pJV4I=
 gopkg.in/alecthomas/kingpin.v2 v2.2.6/go.mod h1:FMv+mEhP44yOT+4EoQTLFTRgOQ1FBLkstjWtayDeSgw=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=