6 Commits

Author SHA1 Message Date
b0f8f31dcc feat: Add concurrency and headless options for downloads
This commit introduces new features for controlling the download process:

-   **Concurrency**: Users can now specify the number of concurrent volume downloads using the `--concurrency` flag. This significantly speeds up the download of entire novels.
-   **Headless Mode**: A `--headless` flag has been added to control whether the browser operates in headless mode (without a visible UI). This is useful for debugging or running in environments without a display.

**Changes include:**

-   Updated `download` command to accept `--concurrency` and `--headless` flags.
-   Refactored `bilinovel` downloader to support `BilinovelNewOption` for configuring headless mode and concurrency.
-   Implemented a page pool and concurrency control mechanism within the `bilinovel` downloader to manage concurrent browser page usage.
-   Added `DownloadNovel` and `DownloadVolume` methods to the `bilinovel` downloader, utilizing goroutines and wait groups for parallel processing.
-   Updated `.vscode/launch.json` with new configurations for testing novel and volume downloads with the new options.
2025-10-06 10:20:36 +11:00
6084386989 refactor(bilinovel): Migrate browser automation from Chromedp to Playwright
This commit replaces the `chromedp` library with `playwright-go` for browser automation within the Bilinovel downloader.

Changes include:
*   Updated `Bilinovel` struct to manage Playwright browser, context, and page instances.
*   Rewrote `initBrowser` and `Close` methods to use Playwright's API for browser lifecycle management.
*   Refactored `processContentWithChromedp` to `processContentWithPlaywright`, adapting the logic to use Playwright's page evaluation capabilities.
*   Removed unused `context` and `time` imports.
*   Added HTML cleanup in `getChapterByPage` to remove `class` attributes from images and `data-k` attributes from all elements, improving content consistency.
2025-10-06 07:58:31 +11:00
f1320cb978 Merge pull request #2 from sarymo/patch-3
fix: normalize path separators in wrapper.go
2025-09-03 13:02:07 +10:00
sarymo
434d5f54bd Update wrapper.go 2025-09-03 08:39:30 +08:00
b8cd053b00 refactor: improve network event handling and cleanup of hidden elements in Bilinovel processing 2025-08-24 20:51:09 +10:00
560cdfdec9 refactor: streamline download process and enhance browser handling in Bilinovel 2025-08-24 19:04:00 +10:00
11 changed files with 395 additions and 277 deletions

23
.vscode/launch.json vendored
View File

@@ -2,7 +2,7 @@
"version": "0.2.0", "version": "0.2.0",
"configurations": [ "configurations": [
{ {
"name": "download", "name": "novel",
"type": "go", "type": "go",
"request": "launch", "request": "launch",
"mode": "auto", "mode": "auto",
@@ -10,11 +10,22 @@
"args": [ "args": [
"download", "download",
"-n", "-n",
"1410", "2727",
"-v", "--concurrency",
"52748", "5"
"-t", ]
"epub" },
{
"name": "volume",
"type": "go",
"request": "launch",
"mode": "auto",
"program": "${workspaceFolder}",
"args": [
"download",
"-n=2727",
"-v=150098",
"--headless=false"
] ]
} }
] ]

View File

@@ -1,6 +1,7 @@
package cmd package cmd
import ( import (
"bilinovel-downloader/downloader"
"bilinovel-downloader/downloader/bilinovel" "bilinovel-downloader/downloader/bilinovel"
"bilinovel-downloader/epub" "bilinovel-downloader/epub"
"bilinovel-downloader/model" "bilinovel-downloader/model"
@@ -27,10 +28,12 @@ var downloadCmd = &cobra.Command{
} }
type downloadCmdArgs struct { type downloadCmdArgs struct {
NovelId int `validate:"required"` NovelId int `validate:"required"`
VolumeId int `validate:"required"` VolumeId int `validate:"required"`
outputPath string outputPath string
outputType string outputType string
headless bool
concurrency int
} }
var ( var (
@@ -42,43 +45,82 @@ func init() {
downloadCmd.Flags().IntVarP(&downloadArgs.VolumeId, "volume-id", "v", 0, "volume id") downloadCmd.Flags().IntVarP(&downloadArgs.VolumeId, "volume-id", "v", 0, "volume id")
downloadCmd.Flags().StringVarP(&downloadArgs.outputPath, "output-path", "o", "novels", "output path") downloadCmd.Flags().StringVarP(&downloadArgs.outputPath, "output-path", "o", "novels", "output path")
downloadCmd.Flags().StringVarP(&downloadArgs.outputType, "output-type", "t", "epub", "output type, epub or text") downloadCmd.Flags().StringVarP(&downloadArgs.outputType, "output-type", "t", "epub", "output type, epub or text")
downloadCmd.Flags().BoolVar(&downloadArgs.headless, "headless", true, "headless mode")
downloadCmd.Flags().IntVar(&downloadArgs.concurrency, "concurrency", 3, "concurrency of downloading volumes")
RootCmd.AddCommand(downloadCmd) RootCmd.AddCommand(downloadCmd)
} }
func runDownloadNovel() error { func runDownloadNovel() error {
downloader, err := bilinovel.New() downloader, err := bilinovel.New(bilinovel.BilinovelNewOption{
Headless: downloadArgs.headless,
Concurrency: downloadArgs.concurrency,
})
if err != nil { if err != nil {
return fmt.Errorf("failed to create downloader: %v", err) return fmt.Errorf("failed to create downloader: %v", err)
} }
// 确保在函数结束时关闭资源
defer func() {
if closeErr := downloader.Close(); closeErr != nil {
log.Printf("Failed to close downloader: %v", closeErr)
}
}()
if downloadArgs.NovelId == 0 { if downloadArgs.NovelId == 0 {
return fmt.Errorf("novel id is required") return fmt.Errorf("novel id is required")
} }
if downloadArgs.VolumeId == 0 { if downloadArgs.VolumeId == 0 {
novel, err := downloadNovel(downloader) // 下载整本小说
err := downloadNovel(downloader, downloadArgs.NovelId)
if err != nil { if err != nil {
return fmt.Errorf("failed to get novel: %v", err) return fmt.Errorf("failed to get novel: %v", err)
} }
switch downloadArgs.outputType {
case "epub":
for _, volume := range novel.Volumes {
err = epub.PackVolumeToEpub(volume, downloadArgs.outputPath, downloader.GetStyleCSS(), downloader.GetExtraFiles())
if err != nil {
return fmt.Errorf("failed to pack volume: %v", err)
}
}
case "text":
for _, volume := range novel.Volumes {
err = text.PackVolumeToText(volume, downloadArgs.outputPath)
if err != nil {
return fmt.Errorf("failed to pack volume: %v", err)
}
}
}
} else { } else {
// 下载单卷 // 下载单卷
volume, err := downloadVolume(downloader) err = downloadVolume(downloader, downloadArgs.VolumeId)
if err != nil { if err != nil {
return fmt.Errorf("failed to get volume: %v", err) return fmt.Errorf("failed to download volume: %v", err)
}
}
return nil
}
func downloadNovel(downloader downloader.Downloader, novelId int) error {
novelInfo, err := downloader.GetNovel(novelId, true, nil)
if err != nil {
return fmt.Errorf("failed to get novel info: %w", err)
}
skipVolumes := make([]int, 0)
for _, volume := range novelInfo.Volumes {
jsonPath := filepath.Join(downloadArgs.outputPath, fmt.Sprintf("volume-%d-%d.json", downloadArgs.NovelId, volume.Id))
err = os.MkdirAll(filepath.Dir(jsonPath), 0755)
if err != nil {
return fmt.Errorf("failed to create directory: %v", err)
}
_, err = os.Stat(jsonPath)
if err == nil {
// 已经下载
skipVolumes = append(skipVolumes, volume.Id)
}
}
novel, err := downloader.GetNovel(novelId, false, skipVolumes)
if err != nil {
return fmt.Errorf("failed to download novel: %w", err)
}
for _, volume := range novel.Volumes {
jsonPath := filepath.Join(downloadArgs.outputPath, fmt.Sprintf("volume-%d-%d.json", downloadArgs.NovelId, volume.Id))
err = os.MkdirAll(filepath.Dir(jsonPath), 0755)
if err != nil {
return fmt.Errorf("failed to create directory: %v", err)
}
jsonFile, err := os.Create(jsonPath)
if err != nil {
return fmt.Errorf("failed to create json file: %v", err)
}
err = json.NewEncoder(jsonFile).Encode(volume)
if err != nil {
return fmt.Errorf("failed to encode json file: %v", err)
} }
switch downloadArgs.outputType { switch downloadArgs.outputType {
case "epub": case "epub":
@@ -93,85 +135,57 @@ func runDownloadNovel() error {
} }
} }
} }
return nil return nil
} }
func downloadNovel(downloader model.Downloader) (*model.Novel, error) { func downloadVolume(downloader downloader.Downloader, volumeId int) error {
jsonPath := filepath.Join(downloadArgs.outputPath, fmt.Sprintf("novel-%d.json", downloadArgs.NovelId)) jsonPath := filepath.Join(downloadArgs.outputPath, fmt.Sprintf("volume-%d-%d.json", downloadArgs.NovelId, volumeId))
err := os.MkdirAll(filepath.Dir(jsonPath), 0755) err := os.MkdirAll(filepath.Dir(jsonPath), 0755)
if err != nil { if err != nil {
return nil, fmt.Errorf("failed to create directory: %v", err) return fmt.Errorf("failed to create directory: %v", err)
}
_, err = os.Stat(jsonPath)
novel := &model.Novel{}
if err != nil {
if os.IsNotExist(err) {
novel, err = downloader.GetNovel(downloadArgs.NovelId)
if err != nil {
return nil, fmt.Errorf("failed to get novel: %v", err)
}
jsonFile, err := os.Create(jsonPath)
if err != nil {
return nil, fmt.Errorf("failed to create json file: %v", err)
}
defer jsonFile.Close()
err = json.NewEncoder(jsonFile).Encode(novel)
if err != nil {
return nil, fmt.Errorf("failed to encode json file: %v", err)
}
} else {
return nil, fmt.Errorf("failed to get novel: %v", err)
}
} else {
jsonFile, err := os.Open(jsonPath)
if err != nil {
return nil, fmt.Errorf("failed to open json file: %v", err)
}
defer jsonFile.Close()
err = json.NewDecoder(jsonFile).Decode(novel)
if err != nil {
return nil, fmt.Errorf("failed to decode json file: %v", err)
}
}
return novel, nil
}
func downloadVolume(downloader model.Downloader) (*model.Volume, error) {
jsonPath := filepath.Join(downloadArgs.outputPath, fmt.Sprintf("volume-%d-%d.json", downloadArgs.NovelId, downloadArgs.VolumeId))
err := os.MkdirAll(filepath.Dir(jsonPath), 0755)
if err != nil {
return nil, fmt.Errorf("failed to create directory: %v", err)
} }
_, err = os.Stat(jsonPath) _, err = os.Stat(jsonPath)
volume := &model.Volume{} volume := &model.Volume{}
if err != nil { if err != nil {
if os.IsNotExist(err) { if os.IsNotExist(err) {
volume, err = downloader.GetVolume(downloadArgs.NovelId, downloadArgs.VolumeId) volume, err = downloader.GetVolume(downloadArgs.NovelId, volumeId, false)
if err != nil { if err != nil {
return nil, fmt.Errorf("failed to get volume: %v", err) return fmt.Errorf("failed to get volume: %v", err)
} }
jsonFile, err := os.Create(jsonPath) jsonFile, err := os.Create(jsonPath)
if err != nil { if err != nil {
return nil, fmt.Errorf("failed to create json file: %v", err) return fmt.Errorf("failed to create json file: %v", err)
} }
err = json.NewEncoder(jsonFile).Encode(volume) err = json.NewEncoder(jsonFile).Encode(volume)
if err != nil { if err != nil {
return nil, fmt.Errorf("failed to encode json file: %v", err) return fmt.Errorf("failed to encode json file: %v", err)
} }
} else { } else {
return nil, fmt.Errorf("failed to get volume: %v", err) return fmt.Errorf("failed to get volume: %v", err)
} }
} else { } else {
jsonFile, err := os.Open(jsonPath) jsonFile, err := os.Open(jsonPath)
if err != nil { if err != nil {
return nil, fmt.Errorf("failed to open json file: %v", err) return fmt.Errorf("failed to open json file: %v", err)
} }
defer jsonFile.Close() defer jsonFile.Close()
err = json.NewDecoder(jsonFile).Decode(volume) err = json.NewDecoder(jsonFile).Decode(volume)
if err != nil { if err != nil {
return nil, fmt.Errorf("failed to decode json file: %v", err) return fmt.Errorf("failed to decode json file: %v", err)
} }
} }
return volume, nil
switch downloadArgs.outputType {
case "epub":
err = epub.PackVolumeToEpub(volume, downloadArgs.outputPath, downloader.GetStyleCSS(), downloader.GetExtraFiles())
if err != nil {
return fmt.Errorf("failed to pack volume: %v", err)
}
case "text":
err = text.PackVolumeToText(volume, downloadArgs.outputPath)
if err != nil {
return fmt.Errorf("failed to pack volume: %v", err)
}
}
return nil
} }

View File

@@ -4,7 +4,6 @@ import (
"bilinovel-downloader/model" "bilinovel-downloader/model"
"bilinovel-downloader/utils" "bilinovel-downloader/utils"
"bytes" "bytes"
"context"
"crypto/sha256" "crypto/sha256"
_ "embed" _ "embed"
"fmt" "fmt"
@@ -14,15 +13,14 @@ import (
"path" "path"
"path/filepath" "path/filepath"
"regexp" "regexp"
"slices"
"strconv" "strconv"
"strings" "strings"
"sync" "sync"
"time"
"github.com/PuerkitoBio/goquery" "github.com/PuerkitoBio/goquery"
mapper "github.com/bestnite/font-mapper" mapper "github.com/bestnite/font-mapper"
"github.com/chromedp/cdproto/network" "github.com/playwright-community/playwright-go"
"github.com/chromedp/chromedp"
) )
//go:embed read.ttf //go:embed read.ttf
@@ -35,31 +33,84 @@ type Bilinovel struct {
fontMapper *mapper.GlyphOutlineMapper fontMapper *mapper.GlyphOutlineMapper
textOnly bool textOnly bool
restyClient *utils.RestyClient restyClient *utils.RestyClient
debug bool
// 浏览器实例复用
browser playwright.Browser
browserContext playwright.BrowserContext
pages map[string]playwright.Page
concurrency int
concurrentChan chan any
} }
func New() (*Bilinovel, error) { type BilinovelNewOption struct {
Headless bool
Concurrency int
}
func New(option BilinovelNewOption) (*Bilinovel, error) {
fontMapper, err := mapper.NewGlyphOutlineMapper(readTTF, miLantingTTF) fontMapper, err := mapper.NewGlyphOutlineMapper(readTTF, miLantingTTF)
if err != nil { if err != nil {
return nil, fmt.Errorf("failed to create font mapper: %v", err) return nil, fmt.Errorf("failed to create font mapper: %v", err)
} }
restyClient := utils.NewRestyClient(10) restyClient := utils.NewRestyClient(50)
return &Bilinovel{
fontMapper: fontMapper, b := &Bilinovel{
textOnly: false, fontMapper: fontMapper,
restyClient: restyClient, textOnly: false,
}, nil restyClient: restyClient,
pages: make(map[string]playwright.Page),
concurrency: option.Concurrency,
concurrentChan: make(chan any, option.Concurrency),
}
// 初始化浏览器实例
err = b.initBrowser(option.Headless)
if err != nil {
return nil, fmt.Errorf("failed to init browser: %v", err)
}
return b, nil
} }
func (b *Bilinovel) SetTextOnly(textOnly bool) { func (b *Bilinovel) SetTextOnly(textOnly bool) {
b.textOnly = textOnly b.textOnly = textOnly
} }
func (b *Bilinovel) SetDebug(debug bool) { func (b *Bilinovel) GetExtraFiles() []model.ExtraFile {
b.debug = debug return nil
} }
func (b *Bilinovel) GetExtraFiles() []model.ExtraFile { // initBrowser 初始化浏览器实例
func (b *Bilinovel) initBrowser(headless bool) error {
pw, err := playwright.Run()
if err != nil {
return fmt.Errorf("could not start playwright: %w", err)
}
b.browser, err = pw.Chromium.Launch(playwright.BrowserTypeLaunchOptions{
Headless: playwright.Bool(headless),
})
if err != nil {
return fmt.Errorf("could not launch browser: %w", err)
}
b.browserContext, err = b.browser.NewContext()
if err != nil {
return fmt.Errorf("could not create browser context: %w", err)
}
log.Println("Browser initialized successfully")
return nil
}
// Close 清理资源
func (b *Bilinovel) Close() error {
if b.browser != nil {
if err := b.browser.Close(); err != nil {
log.Printf("could not close browser: %v", err)
}
b.browser = nil
b.browserContext = nil
}
return nil return nil
} }
@@ -70,10 +121,9 @@ func (b *Bilinovel) GetStyleCSS() string {
return string(styleCSS) return string(styleCSS)
} }
func (b *Bilinovel) GetNovel(novelId int) (*model.Novel, error) { func (b *Bilinovel) GetNovel(novelId int, skipChapterContent bool, skipVolumes []int) (*model.Novel, error) {
if b.debug { log.Printf("Getting novel %v\n", novelId)
log.Printf("Getting novel %v\n", novelId)
}
novelUrl := fmt.Sprintf("https://www.bilinovel.com/novel/%v.html", novelId) novelUrl := fmt.Sprintf("https://www.bilinovel.com/novel/%v.html", novelId)
resp, err := b.restyClient.R().Get(novelUrl) resp, err := b.restyClient.R().Get(novelUrl)
if err != nil { if err != nil {
@@ -101,7 +151,7 @@ func (b *Bilinovel) GetNovel(novelId int) (*model.Novel, error) {
novel.Authors = append(novel.Authors, strings.TrimSpace(s.Text())) novel.Authors = append(novel.Authors, strings.TrimSpace(s.Text()))
}) })
volumes, err := b.getAllVolumes(novelId) volumes, err := b.getAllVolumes(novelId, skipChapterContent, skipVolumes)
if err != nil { if err != nil {
return nil, fmt.Errorf("failed to get novel volumes: %v", err) return nil, fmt.Errorf("failed to get novel volumes: %v", err)
} }
@@ -110,10 +160,9 @@ func (b *Bilinovel) GetNovel(novelId int) (*model.Novel, error) {
return novel, nil return novel, nil
} }
func (b *Bilinovel) GetVolume(novelId int, volumeId int) (*model.Volume, error) { func (b *Bilinovel) GetVolume(novelId int, volumeId int, skipChapterContent bool) (*model.Volume, error) {
if b.debug { log.Printf("Getting volume %v of novel %v\n", volumeId, novelId)
log.Printf("Getting volume %v of novel %v\n", volumeId, novelId)
}
novelUrl := fmt.Sprintf("https://www.bilinovel.com/novel/%v/catalog", novelId) novelUrl := fmt.Sprintf("https://www.bilinovel.com/novel/%v/catalog", novelId)
resp, err := b.restyClient.R().Get(novelUrl) resp, err := b.restyClient.R().Get(novelUrl)
if err != nil { if err != nil {
@@ -185,48 +234,33 @@ func (b *Bilinovel) GetVolume(novelId int, volumeId int) (*model.Volume, error)
}) })
idRegexp := regexp.MustCompile(`/novel/(\d+)/(\d+).html`) idRegexp := regexp.MustCompile(`/novel/(\d+)/(\d+).html`)
wg := sync.WaitGroup{}
errChan := make(chan error, len(volume.Chapters)) if !skipChapterContent {
for i := range volume.Chapters { for i := range volume.Chapters {
wg.Add(1)
go func(i int) {
defer wg.Done()
matches := idRegexp.FindStringSubmatch(volume.Chapters[i].Url) matches := idRegexp.FindStringSubmatch(volume.Chapters[i].Url)
if len(matches) > 0 { if len(matches) > 0 {
chapterId, err := strconv.Atoi(matches[2]) chapterId, err := strconv.Atoi(matches[2])
if err != nil { if err != nil {
errChan <- fmt.Errorf("failed to convert chapter id: %v", err) return nil, fmt.Errorf("failed to convert chapter id: %v", err)
return
} }
chapter, err := b.GetChapter(novelId, volumeId, chapterId) chapter, err := b.GetChapter(novelId, volumeId, chapterId)
if err != nil { if err != nil {
errChan <- fmt.Errorf("failed to get chapter: %v", err) return nil, fmt.Errorf("failed to get chapter: %v", err)
return
} }
chapter.Id = chapterId chapter.Id = chapterId
volume.Chapters[i] = chapter volume.Chapters[i] = chapter
} else { } else {
errChan <- fmt.Errorf("failed to get chapter id: %v", volume.Chapters[i].Url) return nil, fmt.Errorf("failed to get chapter id: %v", volume.Chapters[i].Url)
return
} }
}(i)
}
wg.Wait()
close(errChan)
// 检查是否有错误
for err := range errChan {
if err != nil {
return nil, err
} }
} }
return volume, nil return volume, nil
} }
func (b *Bilinovel) getAllVolumes(novelId int) ([]*model.Volume, error) { func (b *Bilinovel) getAllVolumes(novelId int, skipChapterContent bool, skipVolumes []int) ([]*model.Volume, error) {
if b.debug { log.Printf("Getting all volumes of novel %v\n", novelId)
log.Printf("Getting all volumes of novel %v\n", novelId)
}
catelogUrl := fmt.Sprintf("https://www.bilinovel.com/novel/%v/catalog", novelId) catelogUrl := fmt.Sprintf("https://www.bilinovel.com/novel/%v/catalog", novelId)
resp, err := b.restyClient.R().Get(catelogUrl) resp, err := b.restyClient.R().Get(catelogUrl)
if err != nil { if err != nil {
@@ -252,28 +286,63 @@ func (b *Bilinovel) getAllVolumes(novelId int) ([]*model.Volume, error) {
} }
}) })
volumes := make([]*model.Volume, 0) volumes := make([]*model.Volume, len(volumeIds))
var wg sync.WaitGroup
var mu sync.Mutex // 保护 volumes 写入的互斥锁
for i, volumeIdStr := range volumeIds { for i, volumeIdStr := range volumeIds {
volumeId, err := strconv.Atoi(volumeIdStr) wg.Add(1)
if err != nil { b.concurrentChan <- struct{}{} // 获取一个并发槽
return nil, fmt.Errorf("failed to convert volume id: %v", err)
} go func(i int, volumeIdStr string) {
volume, err := b.GetVolume(novelId, volumeId) defer wg.Done()
if err != nil { defer func() { <-b.concurrentChan }() // 释放并发槽
return nil, fmt.Errorf("failed to get volume info: %v", err)
} volumeId, err := strconv.Atoi(volumeIdStr)
volume.SeriesIdx = i if err != nil {
volumes = append(volumes, volume) log.Printf("failed to convert volume id %s: %v", volumeIdStr, err)
return
}
if slices.Contains(skipVolumes, volumeId) {
return
}
volume, err := b.GetVolume(novelId, volumeId, skipChapterContent)
if err != nil {
log.Printf("failed to get volume info for novel %d, volume %d: %v", novelId, volumeId, err)
return
}
volume.SeriesIdx = i
// 关闭浏览器标签页
pwPageKey := fmt.Sprintf("%v-%v", novelId, volumeId)
if pwPage, ok := b.pages[pwPageKey]; ok {
_ = pwPage.Close()
delete(b.pages, pwPageKey)
}
mu.Lock()
volumes[i] = volume
mu.Unlock()
}(i, volumeIdStr)
} }
return volumes, nil wg.Wait()
// 过滤掉获取失败的 nil volume
filteredVolumes := make([]*model.Volume, 0, len(volumes))
for _, vol := range volumes {
if vol != nil {
filteredVolumes = append(filteredVolumes, vol)
}
}
return filteredVolumes, nil
} }
func (b *Bilinovel) GetChapter(novelId int, volumeId int, chapterId int) (*model.Chapter, error) { func (b *Bilinovel) GetChapter(novelId int, volumeId int, chapterId int) (*model.Chapter, error) {
if b.debug { log.Printf("Getting chapter %v of novel %v\n", chapterId, novelId)
log.Printf("Getting chapter %v of novel %v\n", chapterId, novelId)
} pageNum := 1
page := 1
chapter := &model.Chapter{ chapter := &model.Chapter{
Id: chapterId, Id: chapterId,
NovelId: novelId, NovelId: novelId,
@@ -281,24 +350,30 @@ func (b *Bilinovel) GetChapter(novelId int, volumeId int, chapterId int) (*model
Url: fmt.Sprintf("https://www.bilinovel.com/novel/%v/%v.html", novelId, chapterId), Url: fmt.Sprintf("https://www.bilinovel.com/novel/%v/%v.html", novelId, chapterId),
} }
for { for {
hasNext, err := b.getChapterByPage(chapter, page) pwPageKey := fmt.Sprintf("%v-%v", novelId, volumeId)
if _, ok := b.pages[pwPageKey]; !ok {
pwPage, err := b.browserContext.NewPage()
if err != nil {
return nil, fmt.Errorf("failed to create browser page: %w", err)
}
b.pages[pwPageKey] = pwPage
}
hasNext, err := b.getChapterByPage(b.pages[pwPageKey], chapter, pageNum)
if err != nil { if err != nil {
return nil, fmt.Errorf("failed to download chapter: %w", err) return nil, fmt.Errorf("failed to download chapter: %w", err)
} }
if !hasNext { if !hasNext {
break break
} }
page++ pageNum++
} }
return chapter, nil return chapter, nil
} }
func (b *Bilinovel) getChapterByPage(chapter *model.Chapter, page int) (bool, error) { func (b *Bilinovel) getChapterByPage(pwPage playwright.Page, chapter *model.Chapter, pageNum int) (bool, error) {
if b.debug { log.Printf("Getting chapter %v by page %v\n", chapter.Id, pageNum)
log.Printf("Getting chapter %v by page %v\n", chapter.Id, page)
}
Url := strings.TrimSuffix(chapter.Url, ".html") + fmt.Sprintf("_%v.html", page) Url := strings.TrimSuffix(chapter.Url, ".html") + fmt.Sprintf("_%v.html", pageNum)
hasNext := false hasNext := false
headers := map[string]string{ headers := map[string]string{
@@ -319,8 +394,9 @@ func (b *Bilinovel) getChapterByPage(chapter *model.Chapter, page int) (bool, er
} }
html := resp.Body() html := resp.Body()
// 解决乱序问题 // 解决乱序问题
resortedHtml, err := ProcessContentWithChromedp(string(html)) resortedHtml, err := b.processContentWithPlaywright(pwPage, string(html))
if err != nil { if err != nil {
return false, fmt.Errorf("failed to process html: %w", err) return false, fmt.Errorf("failed to process html: %w", err)
} }
@@ -329,7 +405,7 @@ func (b *Bilinovel) getChapterByPage(chapter *model.Chapter, page int) (bool, er
return false, fmt.Errorf("failed to parse html: %w", err) return false, fmt.Errorf("failed to parse html: %w", err)
} }
if page == 1 { if pageNum == 1 {
chapter.Title = doc.Find("#atitle").Text() chapter.Title = doc.Find("#atitle").Text()
} }
content := doc.Find("#acontent").First() content := doc.Find("#acontent").First()
@@ -368,6 +444,7 @@ func (b *Bilinovel) getChapterByPage(chapter *model.Chapter, page int) (bool, er
imageFilename := fmt.Sprintf("%x%s", string(imageHash[:]), path.Ext(imgUrl)) imageFilename := fmt.Sprintf("%x%s", string(imageHash[:]), path.Ext(imgUrl))
s.SetAttr("src", imageFilename) s.SetAttr("src", imageFilename)
s.SetAttr("alt", imgUrl) s.SetAttr("alt", imgUrl)
s.RemoveAttr("class")
img, err := b.getImg(imgUrl) img, err := b.getImg(imgUrl)
if err != nil { if err != nil {
return return
@@ -382,6 +459,19 @@ func (b *Bilinovel) getChapterByPage(chapter *model.Chapter, page int) (bool, er
}) })
} }
doc.Find("*").Each(func(i int, s *goquery.Selection) {
if len(s.Nodes) > 0 && len(s.Nodes[0].Attr) > 0 {
// 遍历元素的所有属性
for _, attr := range s.Nodes[0].Attr {
// 3. 检查属性名是否以 "data-k" 开头,且属性值是否为空
if strings.HasPrefix(attr.Key, "data-k") {
// 4. 如果满足条件,就移除这个属性
s.RemoveAttr(attr.Key)
}
}
}
})
htmlStr, err := content.Html() htmlStr, err := content.Html()
if err != nil { if err != nil {
return false, fmt.Errorf("failed to get html: %v", err) return false, fmt.Errorf("failed to get html: %v", err)
@@ -396,9 +486,7 @@ func (b *Bilinovel) getChapterByPage(chapter *model.Chapter, page int) (bool, er
} }
func (b *Bilinovel) getImg(url string) ([]byte, error) { func (b *Bilinovel) getImg(url string) ([]byte, error) {
if b.debug { log.Printf("Getting img %v\n", url)
log.Printf("Getting img %v\n", url)
}
resp, err := b.restyClient.R().SetHeader("Referer", "https://www.bilinovel.com").Get(url) resp, err := b.restyClient.R().SetHeader("Referer", "https://www.bilinovel.com").Get(url)
if err != nil { if err != nil {
return nil, err return nil, err
@@ -407,12 +495,14 @@ func (b *Bilinovel) getImg(url string) ([]byte, error) {
return resp.Body(), nil return resp.Body(), nil
} }
func ProcessContentWithChromedp(htmlContent string) (string, error) { // processContentWithPlaywright 使用复用的浏览器实例处理内容
func (b *Bilinovel) processContentWithPlaywright(page playwright.Page, htmlContent string) (string, error) {
tempFile, err := os.CreateTemp("", "bilinovel-temp-*.html") tempFile, err := os.CreateTemp("", "bilinovel-temp-*.html")
if err != nil { if err != nil {
return "", fmt.Errorf("failed to create temp file: %w", err) return "", fmt.Errorf("failed to create temp file: %w", err)
} }
defer os.Remove(tempFile.Name()) defer os.Remove(tempFile.Name())
_, err = tempFile.WriteString(htmlContent) _, err = tempFile.WriteString(htmlContent)
if err != nil { if err != nil {
return "", fmt.Errorf("failed to write temp file: %w", err) return "", fmt.Errorf("failed to write temp file: %w", err)
@@ -420,70 +510,63 @@ func ProcessContentWithChromedp(htmlContent string) (string, error) {
tempFile.Close() tempFile.Close()
tempFilePath := tempFile.Name() tempFilePath := tempFile.Name()
// 创建chromedp选项 _, err = page.ExpectResponse(func(url string) bool {
opts := append(chromedp.DefaultExecAllocatorOptions[:], return strings.Contains(url, "chapterlog.js")
chromedp.Flag("headless", true), }, func() error {
chromedp.Flag("disable-gpu", true), _, err = page.Goto("file://" + filepath.ToSlash(tempFilePath))
chromedp.Flag("disable-dev-shm-usage", true), if err != nil {
chromedp.Flag("disable-extensions", true), return fmt.Errorf("could not navigate to file: %w", err)
chromedp.Flag("no-sandbox", true), }
) return nil
}, playwright.PageExpectResponseOptions{
Timeout: playwright.Float(5000),
})
if err != nil {
return "", fmt.Errorf("failed to wait for network request finish")
}
allocCtx, cancel := chromedp.NewExecAllocator(context.Background(), opts...) err = page.Locator("#acontent").WaitFor(playwright.LocatorWaitForOptions{
defer cancel() State: playwright.WaitForSelectorStateVisible,
})
if err != nil {
return "", fmt.Errorf("could not wait for #acontent: %w", err)
}
ctx, cancel := chromedp.NewContext(allocCtx) // 遍历所有 #acontent 的子元素, 通过 window.getComputedStyle().display 检测是否是 none, 如果是 none 则从页面删除这个元素
defer cancel() result, err := page.Evaluate(`
(function() {
const acontent = document.getElementById('acontent');
if (!acontent) {
return 'acontent element not found';
}
// 设置超时 let removedCount = 0;
ctx, cancel = context.WithTimeout(ctx, 30*time.Second) const elements = acontent.querySelectorAll('*');
defer cancel()
var processedHTML string // 从后往前遍历,避免删除元素时影响索引
for (let i = elements.length - 1; i >= 0; i--) {
const element = elements[i];
const computedStyle = window.getComputedStyle(element);
// 3. 执行chromedp任务并获取页面代码 if (computedStyle.display === 'none' || computedStyle.transform == 'matrix(0, 0, 0, 0, 0, 0)') {
err = chromedp.Run(ctx, element.remove();
network.Enable(), removedCount++;
// 等待JavaScript执行完成
chromedp.ActionFunc(func(ctx context.Context) error {
// 监听网络事件
networkEventChan := make(chan bool, 1)
requestID := ""
chromedp.ListenTarget(ctx, func(ev interface{}) {
switch ev := ev.(type) {
case *network.EventRequestWillBeSent:
if strings.Contains(ev.Request.URL, "chapterlog.js") {
requestID = ev.RequestID.String()
}
case *network.EventLoadingFinished:
if ev.RequestID.String() == requestID {
networkEventChan <- true
}
} }
}) }
go func() { return 'Removed ' + removedCount + ' hidden elements';
select { })()
case <-networkEventChan: `)
case <-time.After(30 * time.Second):
log.Println("Timeout waiting for external script")
case <-ctx.Done():
log.Println("Context cancelled")
}
}()
return nil
}),
// 导航到本地文件
chromedp.Navigate("file://"+filepath.ToSlash(tempFilePath)),
// 等待页面加载完成
chromedp.WaitVisible(`#acontent`, chromedp.ByID),
// 获取页面的HTML代码
chromedp.OuterHTML("html", &processedHTML, chromedp.ByQuery),
)
if err != nil { if err != nil {
return "", fmt.Errorf("chromedp execution failed: %w", err) return "", fmt.Errorf("failed to remove hidden elements: %w", err)
}
log.Printf("Hidden elements removal result: %s", result)
processedHTML, err := page.Content()
if err != nil {
return "", fmt.Errorf("could not get page content: %w", err)
} }
return processedHTML, nil return processedHTML, nil

12
downloader/downloader.go Normal file
View File

@@ -0,0 +1,12 @@
package downloader
import "bilinovel-downloader/model"
type Downloader interface {
GetNovel(novelId int, skipChapterContent bool, skipVolumes []int) (*model.Novel, error)
GetVolume(novelId int, volumeId int, skipChapterContent bool) (*model.Volume, error)
GetChapter(novelId int, volumeId int, chapterId int) (*model.Chapter, error)
GetStyleCSS() string
GetExtraFiles() []model.ExtraFile
Close() error
}

View File

@@ -339,6 +339,8 @@ func addDirContentToZip(zipWriter *zip.Writer, dirPath string, method uint16) er
return err return err
} }
relPath = filepath.ToSlash(relPath)
file, err := os.Open(filePath) file, err := os.Open(filePath)
if err != nil { if err != nil {
return err return err

12
go.mod
View File

@@ -6,24 +6,20 @@ require (
github.com/PuerkitoBio/goquery v1.10.3 github.com/PuerkitoBio/goquery v1.10.3
github.com/a-h/templ v0.3.943 github.com/a-h/templ v0.3.943
github.com/bestnite/font-mapper v0.0.0-20250823155658-56c76d820267 github.com/bestnite/font-mapper v0.0.0-20250823155658-56c76d820267
github.com/chromedp/cdproto v0.0.0-20250803210736-d308e07a266d
github.com/chromedp/chromedp v0.14.1
github.com/go-resty/resty/v2 v2.16.5 github.com/go-resty/resty/v2 v2.16.5
github.com/google/uuid v1.6.0 github.com/google/uuid v1.6.0
github.com/playwright-community/playwright-go v0.5200.1
github.com/spf13/cobra v1.9.1 github.com/spf13/cobra v1.9.1
) )
require ( require (
github.com/andybalholm/cascadia v1.3.3 // indirect github.com/andybalholm/cascadia v1.3.3 // indirect
github.com/chromedp/sysutil v1.1.0 // indirect github.com/deckarep/golang-set/v2 v2.8.0 // indirect
github.com/go-json-experiment/json v0.0.0-20250813233538-9b1f9ea2e11b // indirect github.com/go-jose/go-jose/v3 v3.0.4 // indirect
github.com/gobwas/httphead v0.1.0 // indirect github.com/go-stack/stack v1.8.1 // indirect
github.com/gobwas/pool v0.2.1 // indirect
github.com/gobwas/ws v1.4.0 // indirect
github.com/golang/freetype v0.0.0-20170609003504-e2365dfdc4a0 // indirect github.com/golang/freetype v0.0.0-20170609003504-e2365dfdc4a0 // indirect
github.com/inconshreveable/mousetrap v1.1.0 // indirect github.com/inconshreveable/mousetrap v1.1.0 // indirect
github.com/spf13/pflag v1.0.7 // indirect github.com/spf13/pflag v1.0.7 // indirect
golang.org/x/image v0.30.0 // indirect golang.org/x/image v0.30.0 // indirect
golang.org/x/net v0.43.0 // indirect golang.org/x/net v0.43.0 // indirect
golang.org/x/sys v0.35.0 // indirect
) )

48
go.sum
View File

@@ -1,49 +1,48 @@
github.com/PuerkitoBio/goquery v1.10.3 h1:pFYcNSqHxBD06Fpj/KsbStFRsgRATgnf3LeXiUkhzPo= github.com/PuerkitoBio/goquery v1.10.3 h1:pFYcNSqHxBD06Fpj/KsbStFRsgRATgnf3LeXiUkhzPo=
github.com/PuerkitoBio/goquery v1.10.3/go.mod h1:tMUX0zDMHXYlAQk6p35XxQMqMweEKB7iK7iLNd4RH4Y= github.com/PuerkitoBio/goquery v1.10.3/go.mod h1:tMUX0zDMHXYlAQk6p35XxQMqMweEKB7iK7iLNd4RH4Y=
github.com/a-h/templ v0.3.906 h1:ZUThc8Q9n04UATaCwaG60pB1AqbulLmYEAMnWV63svg=
github.com/a-h/templ v0.3.906/go.mod h1:FFAu4dI//ESmEN7PQkJ7E7QfnSEMdcnu7QrAY8Dn334=
github.com/a-h/templ v0.3.943 h1:o+mT/4yqhZ33F3ootBiHwaY4HM5EVaOJfIshvd5UNTY= github.com/a-h/templ v0.3.943 h1:o+mT/4yqhZ33F3ootBiHwaY4HM5EVaOJfIshvd5UNTY=
github.com/a-h/templ v0.3.943/go.mod h1:oCZcnKRf5jjsGpf2yELzQfodLphd2mwecwG4Crk5HBo= github.com/a-h/templ v0.3.943/go.mod h1:oCZcnKRf5jjsGpf2yELzQfodLphd2mwecwG4Crk5HBo=
github.com/andybalholm/cascadia v1.3.3 h1:AG2YHrzJIm4BZ19iwJ/DAua6Btl3IwJX+VI4kktS1LM= github.com/andybalholm/cascadia v1.3.3 h1:AG2YHrzJIm4BZ19iwJ/DAua6Btl3IwJX+VI4kktS1LM=
github.com/andybalholm/cascadia v1.3.3/go.mod h1:xNd9bqTn98Ln4DwST8/nG+H0yuB8Hmgu1YHNnWw0GeA= github.com/andybalholm/cascadia v1.3.3/go.mod h1:xNd9bqTn98Ln4DwST8/nG+H0yuB8Hmgu1YHNnWw0GeA=
github.com/bestnite/font-mapper v0.0.0-20250823155658-56c76d820267 h1:nmUTJV2u/0XmVjQ++VIy/Hu+MtxdpQvOevvcSZtUATA= github.com/bestnite/font-mapper v0.0.0-20250823155658-56c76d820267 h1:nmUTJV2u/0XmVjQ++VIy/Hu+MtxdpQvOevvcSZtUATA=
github.com/bestnite/font-mapper v0.0.0-20250823155658-56c76d820267/go.mod h1:cfB1e9YhoI/QWrXPp3h6QVAKU6iCI2ifbjRPHP3xf/0= github.com/bestnite/font-mapper v0.0.0-20250823155658-56c76d820267/go.mod h1:cfB1e9YhoI/QWrXPp3h6QVAKU6iCI2ifbjRPHP3xf/0=
github.com/chromedp/cdproto v0.0.0-20250803210736-d308e07a266d h1:ZtA1sedVbEW7EW80Iz2GR3Ye6PwbJAJXjv7D74xG6HU=
github.com/chromedp/cdproto v0.0.0-20250803210736-d308e07a266d/go.mod h1:NItd7aLkcfOA/dcMXvl8p1u+lQqioRMq/SqDp71Pb/k=
github.com/chromedp/chromedp v0.14.1 h1:0uAbnxewy/Q+Bg7oafVePE/6EXEho9hnaC38f+TTENg=
github.com/chromedp/chromedp v0.14.1/go.mod h1:rHzAv60xDE7VNy/MYtTUrYreSc0ujt2O1/C3bzctYBo=
github.com/chromedp/sysutil v1.1.0 h1:PUFNv5EcprjqXZD9nJb9b/c9ibAbxiYo4exNWZyipwM=
github.com/chromedp/sysutil v1.1.0/go.mod h1:WiThHUdltqCNKGc4gaU50XgYjwjYIhKWoHGPTUfWTJ8=
github.com/cpuguy83/go-md2man/v2 v2.0.6/go.mod h1:oOW0eioCTA6cOiMLiUPZOpcVxMig6NIQQ7OS05n1F4g= github.com/cpuguy83/go-md2man/v2 v2.0.6/go.mod h1:oOW0eioCTA6cOiMLiUPZOpcVxMig6NIQQ7OS05n1F4g=
github.com/go-json-experiment/json v0.0.0-20250813233538-9b1f9ea2e11b h1:6Q4zRHXS/YLOl9Ng1b1OOOBWMidAQZR3Gel0UKPC/KU= github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/go-json-experiment/json v0.0.0-20250813233538-9b1f9ea2e11b/go.mod h1:TiCD2a1pcmjd7YnhGH0f/zKNcCD06B029pHhzV23c2M= github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
github.com/deckarep/golang-set/v2 v2.8.0 h1:swm0rlPCmdWn9mESxKOjWk8hXSqoxOp+ZlfuyaAdFlQ=
github.com/deckarep/golang-set/v2 v2.8.0/go.mod h1:VAky9rY/yGXJOLEDv3OMci+7wtDpOF4IN+y82NBOac4=
github.com/go-jose/go-jose/v3 v3.0.4 h1:Wp5HA7bLQcKnf6YYao/4kpRpVMp/yf6+pJKV8WFSaNY=
github.com/go-jose/go-jose/v3 v3.0.4/go.mod h1:5b+7YgP7ZICgJDBdfjZaIt+H/9L9T/YQrVfLAMboGkQ=
github.com/go-resty/resty/v2 v2.16.5 h1:hBKqmWrr7uRc3euHVqmh1HTHcKn99Smr7o5spptdhTM= github.com/go-resty/resty/v2 v2.16.5 h1:hBKqmWrr7uRc3euHVqmh1HTHcKn99Smr7o5spptdhTM=
github.com/go-resty/resty/v2 v2.16.5/go.mod h1:hkJtXbA2iKHzJheXYvQ8snQES5ZLGKMwQ07xAwp/fiA= github.com/go-resty/resty/v2 v2.16.5/go.mod h1:hkJtXbA2iKHzJheXYvQ8snQES5ZLGKMwQ07xAwp/fiA=
github.com/gobwas/httphead v0.1.0 h1:exrUm0f4YX0L7EBwZHuCF4GDp8aJfVeBrlLQrs6NqWU= github.com/go-stack/stack v1.8.1 h1:ntEHSVwIt7PNXNpgPmVfMrNhLtgjlmnZha2kOpuRiDw=
github.com/gobwas/httphead v0.1.0/go.mod h1:O/RXo79gxV8G+RqlR/otEwx4Q36zl9rqC5u12GKvMCM= github.com/go-stack/stack v1.8.1/go.mod h1:dcoOX6HbPZSZptuspn9bctJ+N/CnF5gGygcUP3XYfe4=
github.com/gobwas/pool v0.2.1 h1:xfeeEhW7pwmX8nuLVlqbzVc7udMDrwetjEv+TZIz1og=
github.com/gobwas/pool v0.2.1/go.mod h1:q8bcK0KcYlCgd9e7WYLm9LpyS+YeLd8JVDW6WezmKEw=
github.com/gobwas/ws v1.4.0 h1:CTaoG1tojrh4ucGPcoJFiAQUAsEWekEWvLy7GsVNqGs=
github.com/gobwas/ws v1.4.0/go.mod h1:G3gNqMNtPppf5XUz7O4shetPpcZ1VJ7zt18dlUeakrc=
github.com/golang/freetype v0.0.0-20170609003504-e2365dfdc4a0 h1:DACJavvAHhabrF08vX0COfcOBJRhZ8lUbR+ZWIs0Y5g= github.com/golang/freetype v0.0.0-20170609003504-e2365dfdc4a0 h1:DACJavvAHhabrF08vX0COfcOBJRhZ8lUbR+ZWIs0Y5g=
github.com/golang/freetype v0.0.0-20170609003504-e2365dfdc4a0/go.mod h1:E/TSTwGwJL78qG/PmXZO1EjYhfJinVAhrmmHX6Z8B9k= github.com/golang/freetype v0.0.0-20170609003504-e2365dfdc4a0/go.mod h1:E/TSTwGwJL78qG/PmXZO1EjYhfJinVAhrmmHX6Z8B9k=
github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI= github.com/google/go-cmp v0.6.0 h1:ofyhxvXcZhMsU5ulbFiLKl/XBFqE1GSq7atu8tAmTRI=
github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY= github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0= github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo= github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8= github.com/inconshreveable/mousetrap v1.1.0 h1:wN+x4NVGpMsO7ErUn/mUI3vEoE6Jt13X2s0bqwp9tc8=
github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw= github.com/inconshreveable/mousetrap v1.1.0/go.mod h1:vpF70FUmC8bwa3OWnCshd2FqLfsEA9PFc4w1p2J65bw=
github.com/ledongthuc/pdf v0.0.0-20220302134840-0c2507a12d80 h1:6Yzfa6GP0rIo/kULo2bwGEkFvCePZ3qHDDTC3/J9Swo= github.com/mitchellh/go-ps v1.0.0 h1:i6ampVEEF4wQFF+bkYfwYgY+F/uYJDktmvLPf7qIgjc=
github.com/ledongthuc/pdf v0.0.0-20220302134840-0c2507a12d80/go.mod h1:imJHygn/1yfhB7XSJJKlFZKl/J+dCPAknuiaGOshXAs= github.com/mitchellh/go-ps v1.0.0/go.mod h1:J4lOc8z8yJs6vUwklHw2XEIiT4z4C40KtWVN3nvg8Pg=
github.com/orisano/pixelmatch v0.0.0-20220722002657-fb0b55479cde h1:x0TT0RDC7UhAVbbWWBzr41ElhJx5tXPWkIHA2HWPRuw= github.com/playwright-community/playwright-go v0.5200.1 h1:Sm2oOuhqt0M5Y4kUi/Qh9w4cyyi3ZIWTBeGKImc2UVo=
github.com/orisano/pixelmatch v0.0.0-20220722002657-fb0b55479cde/go.mod h1:nZgzbfBr3hhjoZnS66nKrHmduYNpc34ny7RK4z5/HM0= github.com/playwright-community/playwright-go v0.5200.1/go.mod h1:UnnyQZaqUOO5ywAZu60+N4EiWReUqX1MQBBA3Oofvf8=
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM= github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
github.com/spf13/cobra v1.9.1 h1:CXSaggrXdbHK9CF+8ywj8Amf7PBRmPCOJugH954Nnlo= github.com/spf13/cobra v1.9.1 h1:CXSaggrXdbHK9CF+8ywj8Amf7PBRmPCOJugH954Nnlo=
github.com/spf13/cobra v1.9.1/go.mod h1:nDyEzZ8ogv936Cinf6g1RU9MRY64Ir93oCnqb9wxYW0= github.com/spf13/cobra v1.9.1/go.mod h1:nDyEzZ8ogv936Cinf6g1RU9MRY64Ir93oCnqb9wxYW0=
github.com/spf13/pflag v1.0.6 h1:jFzHGLGAlb3ruxLB8MhbI6A8+AQX/2eW4qeyNZXNp2o=
github.com/spf13/pflag v1.0.6/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg= github.com/spf13/pflag v1.0.6/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
github.com/spf13/pflag v1.0.7 h1:vN6T9TfwStFPFM5XzjsvmzZkLuaLX+HS+0SeFLRgU6M= github.com/spf13/pflag v1.0.7 h1:vN6T9TfwStFPFM5XzjsvmzZkLuaLX+HS+0SeFLRgU6M=
github.com/spf13/pflag v1.0.7/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg= github.com/spf13/pflag v1.0.7/go.mod h1:McXfInJRrz4CZXVZOBLb0bTZqETkiAhM9Iw0y3An2Bg=
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
github.com/stretchr/testify v1.10.0 h1:Xv5erBjTwe/5IxqUQTdXv5kgmIvbHo3QQyRwhJsOfJA=
github.com/stretchr/testify v1.10.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY= github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w= golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc= golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
@@ -67,8 +66,6 @@ golang.org/x/net v0.15.0/go.mod h1:idbUs1IY1+zTqbi8yxTbhexhEEk5ur9LInksu6HrEpk=
golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44= golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44=
golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM= golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=
golang.org/x/net v0.33.0/go.mod h1:HXLR5J+9DxmrqMwG9qjGCxZ+zKXxBru04zlTvWlWuN4= golang.org/x/net v0.33.0/go.mod h1:HXLR5J+9DxmrqMwG9qjGCxZ+zKXxBru04zlTvWlWuN4=
golang.org/x/net v0.39.0 h1:ZCu7HMWDxpXpaiKdhzIfaltL9Lp31x/3fCP11bc6/fY=
golang.org/x/net v0.39.0/go.mod h1:X7NRbYVEA+ewNkCNyJ513WmMdQ3BineSwVtN2zD/d+E=
golang.org/x/net v0.43.0 h1:lat02VYK2j4aLzMzecihNvTlJNQUq316m2Mr9rnM6YE= golang.org/x/net v0.43.0 h1:lat02VYK2j4aLzMzecihNvTlJNQUq316m2Mr9rnM6YE=
golang.org/x/net v0.43.0/go.mod h1:vhO1fvI4dGsIjh73sWfUVjj3N7CA9WkKJNQm2svM6Jg= golang.org/x/net v0.43.0/go.mod h1:vhO1fvI4dGsIjh73sWfUVjj3N7CA9WkKJNQm2svM6Jg=
golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
@@ -84,14 +81,11 @@ golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBc
golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg= golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
golang.org/x/sys v0.17.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= golang.org/x/sys v0.17.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA= golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
golang.org/x/sys v0.35.0 h1:vz1N37gP5bs89s7He8XuIYXpyY0+QlsKmzipCbUtyxI=
golang.org/x/sys v0.35.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
golang.org/x/telemetry v0.0.0-20240228155512-f48c80bd79b2/go.mod h1:TeRTkGYfJXctD9OcfyVLyj2J3IxLnKwHJR8f4D8a3YE= golang.org/x/telemetry v0.0.0-20240228155512-f48c80bd79b2/go.mod h1:TeRTkGYfJXctD9OcfyVLyj2J3IxLnKwHJR8f4D8a3YE=
golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo= 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/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
@@ -120,4 +114,6 @@ golang.org/x/tools v0.13.0/go.mod h1:HvlwmtVNQAhOuCjW7xxvovg8wbNq7LwfXh/k7wXUl58
golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d/go.mod h1:aiJjzUbINMkxbQROHiO6hDPo2LHcIPhhQsa9DLh0yGk= golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d/go.mod h1:aiJjzUbINMkxbQROHiO6hDPo2LHcIPhhQsa9DLh0yGk=
golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0= gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM= gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=

12
main.go
View File

@@ -2,8 +2,20 @@ package main
import ( import (
"bilinovel-downloader/cmd" "bilinovel-downloader/cmd"
"io"
"log"
"github.com/playwright-community/playwright-go"
) )
func main() { func main() {
log.Println("Installing playwright")
err := playwright.Install(&playwright.RunOptions{
Browsers: []string{"chromium"},
Stdout: io.Discard,
})
if err != nil {
log.Panicf("failed to install playwright")
}
_ = cmd.RootCmd.Execute() _ = cmd.RootCmd.Execute()
} }

View File

@@ -1,15 +0,0 @@
package model
type ExtraFile struct {
Data []byte
Path string
ManifestItem ManifestItem
}
type Downloader interface {
GetNovel(novelId int) (*Novel, error)
GetVolume(novelId int, volumeId int) (*Volume, error)
GetChapter(novelId int, volumeId int, chapterId int) (*Chapter, error)
GetStyleCSS() string
GetExtraFiles() []ExtraFile
}

View File

@@ -1,6 +1,14 @@
package model package model
import "encoding/xml" import (
"encoding/xml"
)
type ExtraFile struct {
Data []byte
Path string
ManifestItem ManifestItem
}
type DublinCoreMetadata struct { type DublinCoreMetadata struct {
XMLName xml.Name `xml:"metadata"` XMLName xml.Name `xml:"metadata"`

View File

@@ -8,13 +8,12 @@ import (
) )
func TestBilinovel_GetNovel(t *testing.T) { func TestBilinovel_GetNovel(t *testing.T) {
bilinovel, err := bilinovel.New() bilinovel, err := bilinovel.New(bilinovel.BilinovelNewOption{Headless: false, Concurrency: 5})
bilinovel.SetTextOnly(true) bilinovel.SetTextOnly(true)
bilinovel.SetDebug(true)
if err != nil { if err != nil {
t.Fatalf("failed to create bilinovel: %v", err) t.Fatalf("failed to create bilinovel: %v", err)
} }
novel, err := bilinovel.GetNovel(4519) novel, err := bilinovel.GetNovel(2727, false, nil)
if err != nil { if err != nil {
t.Fatalf("failed to get novel: %v", err) t.Fatalf("failed to get novel: %v", err)
} }
@@ -26,12 +25,12 @@ func TestBilinovel_GetNovel(t *testing.T) {
} }
func TestBilinovel_GetVolume(t *testing.T) { func TestBilinovel_GetVolume(t *testing.T) {
bilinovel, err := bilinovel.New() bilinovel, err := bilinovel.New(bilinovel.BilinovelNewOption{Headless: false, Concurrency: 1})
bilinovel.SetTextOnly(true) bilinovel.SetTextOnly(true)
if err != nil { if err != nil {
t.Fatalf("failed to create bilinovel: %v", err) t.Fatalf("failed to create bilinovel: %v", err)
} }
volume, err := bilinovel.GetVolume(1410, 52748) volume, err := bilinovel.GetVolume(2727, 129092, false)
if err != nil { if err != nil {
t.Fatalf("failed to get volume: %v", err) t.Fatalf("failed to get volume: %v", err)
} }
@@ -43,12 +42,12 @@ func TestBilinovel_GetVolume(t *testing.T) {
} }
func TestBilinovel_GetChapter(t *testing.T) { func TestBilinovel_GetChapter(t *testing.T) {
bilinovel, err := bilinovel.New() bilinovel, err := bilinovel.New(bilinovel.BilinovelNewOption{Headless: false, Concurrency: 1})
bilinovel.SetTextOnly(true)
if err != nil { if err != nil {
t.Fatalf("failed to create bilinovel: %v", err) t.Fatalf("failed to create bilinovel: %v", err)
} }
bilinovel.SetDebug(true) chapter, err := bilinovel.GetChapter(2727, 129092, 129094)
chapter, err := bilinovel.GetChapter(1410, 52748, 52752)
if err != nil { if err != nil {
t.Fatalf("failed to get chapter: %v", err) t.Fatalf("failed to get chapter: %v", err)
} }