-
Notifications
You must be signed in to change notification settings - Fork 11
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
- Loading branch information
1 parent
58335e9
commit 886112c
Showing
5 changed files
with
267 additions
and
11 deletions.
There are no files selected for viewing
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,184 @@ | ||
| package iwara | ||
|
|
||
| import ( | ||
| "encoding/json" | ||
| "fmt" | ||
| "regexp" | ||
| "strings" | ||
|
|
||
| "github.com/gan-of-culture/go-hentai-scraper/config" | ||
| "github.com/gan-of-culture/go-hentai-scraper/request" | ||
| "github.com/gan-of-culture/go-hentai-scraper/static" | ||
| "github.com/gan-of-culture/go-hentai-scraper/utils" | ||
| ) | ||
|
|
||
| type stream struct { | ||
| Resolution string | ||
| URI string | ||
| Mime string | ||
| } | ||
|
|
||
| const site = "https://ecchi.iwara.tv/" | ||
| const videoAPI = "https://ecchi.iwara.tv/api/video/" | ||
|
|
||
| var reImgSource *regexp.Regexp = regexp.MustCompile(`([^"]+large/public/photos/[^"]+)"(?: width="([^"]*)[^=]+="([^"]*))`) | ||
| var reExt *regexp.Regexp = regexp.MustCompile(`(\w+)\?itok=[a-zA-Z\d]+$`) | ||
| var reTitle *regexp.Regexp = regexp.MustCompile(`<title>([^|]+)`) | ||
| var reVideoID *regexp.Regexp = regexp.MustCompile(`https://ecchi.iwara.tv/videos/(.+)`) | ||
|
|
||
| type extractor struct{} | ||
|
|
||
| // New returns a thehentaiworld extractor. | ||
| func New() static.Extractor { | ||
| return &extractor{} | ||
| } | ||
|
|
||
| func (e *extractor) Extract(URL string) ([]*static.Data, error) { | ||
| postIDs := parseURL(URL) | ||
| if len(postIDs) == 0 { | ||
| return nil, static.ErrURLParseFailed | ||
| } | ||
|
|
||
| data := []*static.Data{} | ||
| for _, pID := range postIDs { | ||
| d, err := extractData(pID) | ||
| if err != nil { | ||
| return nil, utils.Wrap(err, pID) | ||
| } | ||
| data = append(data, d...) | ||
| } | ||
|
|
||
| return data, nil | ||
| } | ||
|
|
||
| func parseURL(URL string) []string { | ||
| if ok, _ := regexp.MatchString(site+`(?:videos|images)/`, URL); ok { | ||
| return []string{URL} | ||
| } | ||
|
|
||
| tmpURL := regexp.MustCompile(`page=\d+`).ReplaceAllString(URL, "page=%d") | ||
| if !strings.Contains(tmpURL, "page=%d") { | ||
| tmpURL = URL + "&page=%d" | ||
| } | ||
|
|
||
| out := []string{} | ||
| count := 0 | ||
| for i := 0; ; { | ||
| htmlString, err := request.Get(fmt.Sprintf(tmpURL, i)) | ||
| if err != nil { | ||
| return nil | ||
| } | ||
| if config.Amount > 0 { | ||
| fmt.Println(count) | ||
| } | ||
|
|
||
| re := regexp.MustCompile(`/(?:videos|images)/[a-zA-Z0-9%=?-]+"`) | ||
| matchedURLs := re.FindAllString(htmlString, -1) | ||
|
|
||
| URLs := []string{} | ||
| for _, matchedURL := range utils.RemoveAdjDuplicates(matchedURLs) { | ||
| URLs = append(URLs, site+strings.Trim(matchedURL, `/"`)) | ||
| } | ||
| count += len(URLs) | ||
| i += 1 | ||
| out = append(out, URLs...) | ||
| if config.Amount == 0 || count >= config.Amount || len(URLs) == 0 { | ||
| break | ||
| } | ||
| } | ||
|
|
||
| if config.Amount > 0 && len(out) > config.Amount { | ||
| out = out[:config.Amount] | ||
| } | ||
|
|
||
| return out | ||
| } | ||
|
|
||
| func extractData(URL string) ([]*static.Data, error) { | ||
| resString, err := request.Get(URL) | ||
| if err != nil { | ||
| return nil, err | ||
| } | ||
|
|
||
| title := utils.GetLastItemString(reTitle.FindStringSubmatch(resString)) | ||
| title = title[:len(title)-1] | ||
|
|
||
| matchedImages := reImgSource.FindAllStringSubmatch(resString, -1) | ||
| if len(matchedImages) > 0 { | ||
| data := []*static.Data{} | ||
| for i, img := range matchedImages { | ||
| img[1] = "https:" + img[1] | ||
|
|
||
| quality := "" | ||
| if len(img) > 2 { | ||
| quality = fmt.Sprintf("%s x %s", img[2], img[3]) | ||
| } | ||
|
|
||
| size, _ := request.Size(img[1], site) | ||
|
|
||
| data = append(data, &static.Data{ | ||
| Site: site, | ||
| Type: "image", | ||
| Title: fmt.Sprintf("%s_%d", title, i+1), | ||
| Streams: map[string]*static.Stream{ | ||
| "0": { | ||
| URLs: []*static.URL{ | ||
| { | ||
| URL: img[1], | ||
| Ext: reExt.FindStringSubmatch(img[1])[1], | ||
| }, | ||
| }, | ||
| Quality: quality, | ||
| Size: size, | ||
| }, | ||
| }, | ||
| Url: URL, | ||
| }) | ||
| } | ||
| return data, nil | ||
| } | ||
|
|
||
| videoID := utils.GetLastItemString(reVideoID.FindStringSubmatch(URL)) | ||
| if videoID == "" { | ||
| return nil, static.ErrURLParseFailed | ||
| } | ||
|
|
||
| jsonString, err := request.Get(videoAPI + videoID) | ||
| if err != nil { | ||
| return nil, err | ||
| } | ||
|
|
||
| vStreams := []stream{} | ||
| err = json.Unmarshal([]byte(jsonString), &vStreams) | ||
| if err != nil { | ||
| return nil, err | ||
| } | ||
|
|
||
| streams := map[string]*static.Stream{} | ||
| for i, stream := range vStreams { | ||
| stream.URI = "https:" + stream.URI | ||
|
|
||
| size, _ := request.Size(stream.URI, site) | ||
|
|
||
| streams[fmt.Sprint(i)] = &static.Stream{ | ||
| URLs: []*static.URL{ | ||
| { | ||
| URL: stream.URI, | ||
| Ext: utils.GetLastItemString(strings.Split(stream.Mime, "/")), | ||
| }, | ||
| }, | ||
| Quality: stream.Resolution, | ||
| Size: size, | ||
| } | ||
| } | ||
|
|
||
| return []*static.Data{ | ||
| { | ||
| Site: site, | ||
| Title: title, | ||
| Type: static.DataTypeVideo, | ||
| Streams: streams, | ||
| Url: URL, | ||
| }, | ||
| }, nil | ||
| } |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,70 @@ | ||
| package iwara | ||
|
|
||
| import ( | ||
| "testing" | ||
|
|
||
| "github.com/gan-of-culture/go-hentai-scraper/config" | ||
| ) | ||
|
|
||
| func TestParseURL(t *testing.T) { | ||
| tests := []struct { | ||
| name string | ||
| url string | ||
| want int | ||
| }{ | ||
| { | ||
| name: "Single video", | ||
| url: "https://ecchi.iwara.tv/videos/kmnzvsa75uzbaw36?language=en", | ||
| want: 1, | ||
| }, { | ||
| name: "Single images", | ||
| url: "https://ecchi.iwara.tv/images/%E6%B9%AF%E4%B8%8A%E3%81%8C%E3%82%8A%E3%82%86%E3%81%84%E3%81%A1%E3%82%83%E3%82%93?language=en", | ||
| want: 2, | ||
| }, { | ||
| name: "Mass", | ||
| url: "https://ecchi.iwara.tv/images?language=en&f%5B0%5D=field_image_categories%3A5&page=1", | ||
| want: 40, | ||
| }, | ||
| } | ||
| for _, tt := range tests { | ||
| t.Run(tt.name, func(t *testing.T) { | ||
| if tt.name == "Mass" { | ||
| config.Amount = 40 | ||
| } | ||
|
|
||
| urls := parseURL(tt.url) | ||
| if len(urls) > tt.want || len(urls) == 0 { | ||
| t.Errorf("Got: %v - want: %v", len(urls), tt.want) | ||
| } | ||
| }) | ||
| } | ||
| } | ||
|
|
||
| func TestExtract(t *testing.T) { | ||
| tests := []struct { | ||
| name string | ||
| url string | ||
| want int | ||
| }{ | ||
| { | ||
| name: "Single video", | ||
| url: "https://ecchi.iwara.tv/videos/kmnzvsa75uzbaw36?language=en", | ||
| want: 1, | ||
| }, { | ||
| name: "Single images", | ||
| url: "https://ecchi.iwara.tv/images/%E6%B9%AF%E4%B8%8A%E3%81%8C%E3%82%8A%E3%82%86%E3%81%84%E3%81%A1%E3%82%83%E3%82%93?language=en", | ||
| want: 2, | ||
| }, | ||
| } | ||
| for _, tt := range tests { | ||
| t.Run(tt.name, func(t *testing.T) { | ||
| data, err := New().Extract(tt.url) | ||
| if err != nil { | ||
| t.Error(err) | ||
| } | ||
| if len(data) > tt.want || len(data) == 0 { | ||
| t.Errorf("Got: %v - want: %v", len(data), tt.want) | ||
| } | ||
| }) | ||
| } | ||
| } |