Mirrors/stash
1
0
Fork 0
mirror of https://github.com/stashapp/stash.git synced 2025-12-17 04:14:39 +03:00
Code Issues Packages Projects Releases Wiki Activity

Scraper refactor middle (#2043)

Browse Source 
* Push scrapeByURL into scrapers

Replace ScrapePerfomerByURL, ScrapeMovie..., ... with ScrapeByURL in
the scraperActionImpl interface. This allows us to delete a lot of
repeated code in the scrapers and replace the central part with a
switch on the scraper type.

* Fold name scraping into one call

Follow up on scraper refactoring. Name scrapers use the same code path.
This allows us to restructure some code and kill some functions, adding
variance to the name scraping code. It allows us to remove some code
repetition as well.

* Do not export loop refs.

* Simplify fragment scraping

Generalize fragment scrapers into ScrapeByFragment. This simplifies
fragment code flows into a simpler pathing which should be easier
to handle in the future.

* Eliminate more context.TODO()

In a number of cases, we have a context now. Use the context rather than
TODO() for those cases in order to make those operations cancellable.

* Pass the context for the stashbox scraper

This removes all context.TODO() in the path of the stashbox scraper,
and replaces it with the context that's present on each of the paths.

* Pass the context into subscrapers

Mostly a mechanical update, where we pass in the context for
subscraping. This removes the final context.TODO() in the scraper
code.

* Warn on unknown fields from scripts

A common mistake for new script writers are that they return fields
not known to stash. For instance the name "description" is used rather
than "details".

Decode disallowing unknown fields. If this fails, use a tee-reader to
fall back to the old behavior, but print a warning for the user in this
case. Thus, we retain the old behavior, but print warnings for scripts
which fails the more strict unknown-fields detection.

* Nil-check before running the postprocessing chain

Fixes panics when scraping returns nil values.

* Lift nil-ness in post-postprocessing

If the struct we are trying to post-process is nil, we shouldn't
enter the postprocessing flow at all. Pass the struct as a value
rather than a pointer, eliminating nil-checks as we go. Use the
top-level postProcess call to make the nil-check and then abort there
if the object we are looking at is nil.

* Allow conversion routines to handle values

If we have a non-pointer type in the interface, we should also convert
those into ScrapedContent. Otherwise we get errors on deprecated
functions.
This commit is contained in:
SmallCoccinelle
2021-11-26 01:20:06 +01:00
committed by GitHub
parent 19e69f5310
commit 4089fcf1e2
20 changed files with 442 additions and 548 deletions
Download Patch File Download Diff File Expand all files Collapse all files

135
pkg/scraper/json.go
View File

@@ -75,84 +75,33 @@ func (s *jsonScraper) loadURL(ctx context.Context, url string) (string, error) {
return docStr, err
}
func (s *jsonScraper) scrapePerformerByURL(ctx context.Context, url string) (*models.ScrapedPerformer, error) {
u := replaceURL(url, s.scraper) // allow a URL Replace for performer by URL queries
func (s *jsonScraper) scrapeByURL(ctx context.Context, url string, ty models.ScrapeContentType) (models.ScrapedContent, error) {
u := replaceURL(url, s.scraper) // allow a URL Replace for url-queries
doc, scraper, err := s.scrapeURL(ctx, u)
if err != nil {
return nil, err
}
q := s.getJsonQuery(doc)
return scraper.scrapePerformer(q)
}
func (s *jsonScraper) scrapeSceneByURL(ctx context.Context, url string) (*models.ScrapedScene, error) {
u := replaceURL(url, s.scraper) // allow a URL Replace for scene by URL queries
doc, scraper, err := s.scrapeURL(ctx, u)
if err != nil {
return nil, err
switch ty {
case models.ScrapeContentTypePerformer:
return scraper.scrapePerformer(ctx, q)
case models.ScrapeContentTypeScene:
return scraper.scrapeScene(ctx, q)
case models.ScrapeContentTypeGallery:
return scraper.scrapeGallery(ctx, q)
case models.ScrapeContentTypeMovie:
return scraper.scrapeMovie(ctx, q)
}
q := s.getJsonQuery(doc)
return scraper.scrapeScene(q)
return nil, ErrNotSupported
}
func (s *jsonScraper) scrapeGalleryByURL(ctx context.Context, url string) (*models.ScrapedGallery, error) {
u := replaceURL(url, s.scraper) // allow a URL Replace for gallery by URL queries
doc, scraper, err := s.scrapeURL(ctx, u)
if err != nil {
return nil, err
}
q := s.getJsonQuery(doc)
return scraper.scrapeGallery(q)
}
func (s *jsonScraper) scrapeMovieByURL(ctx context.Context, url string) (*models.ScrapedMovie, error) {
u := replaceURL(url, s.scraper) // allow a URL Replace for movie by URL queries
doc, scraper, err := s.scrapeURL(ctx, u)
if err != nil {
return nil, err
}
q := s.getJsonQuery(doc)
return scraper.scrapeMovie(q)
}
func (s *jsonScraper) scrapePerformersByName(ctx context.Context, name string) ([]*models.ScrapedPerformer, error) {
func (s *jsonScraper) scrapeByName(ctx context.Context, name string, ty models.ScrapeContentType) ([]models.ScrapedContent, error) {
scraper := s.getJsonScraper()
if scraper == nil {
return nil, errors.New("json scraper with name " + s.scraper.Scraper + " not found in config")
}
const placeholder = "{}"
// replace the placeholder string with the URL-escaped name
escapedName := url.QueryEscape(name)
url := s.scraper.QueryURL
url = strings.ReplaceAll(url, placeholder, escapedName)
doc, err := s.loadURL(context.TODO(), url)
if err != nil {
return nil, err
}
q := s.getJsonQuery(doc)
return scraper.scrapePerformers(q)
}
func (s *jsonScraper) scrapePerformerByFragment(scrapedPerformer models.ScrapedPerformerInput) (*models.ScrapedPerformer, error) {
return nil, errors.New("scrapePerformerByFragment not supported for json scraper")
}
func (s *jsonScraper) scrapeScenesByName(ctx context.Context, name string) ([]*models.ScrapedScene, error) {
scraper := s.getJsonScraper()
if scraper == nil {
return nil, errors.New("json scraper with name " + s.scraper.Scraper + " not found in config")
return nil, fmt.Errorf("%w: name %v", ErrNotFound, s.scraper.Scraper)
}
const placeholder = "{}"
@@ -170,7 +119,34 @@ func (s *jsonScraper) scrapeScenesByName(ctx context.Context, name string) ([]*m
}
q := s.getJsonQuery(doc)
return scraper.scrapeScenes(q)
var content []models.ScrapedContent
switch ty {
case models.ScrapeContentTypePerformer:
performers, err := scraper.scrapePerformers(ctx, q)
if err != nil {
return nil, err
}
for _, p := range performers {
content = append(content, p)
}
return content, nil
case models.ScrapeContentTypeScene:
scenes, err := scraper.scrapeScenes(ctx, q)
if err != nil {
return nil, err
}
for _, s := range scenes {
content = append(content, s)
}
return content, nil
}
return nil, ErrNotSupported
}
func (s *jsonScraper) scrapeSceneByScene(ctx context.Context, scene *models.Scene) (*models.ScrapedScene, error) {
@@ -194,10 +170,21 @@ func (s *jsonScraper) scrapeSceneByScene(ctx context.Context, scene *models.Scen
}
q := s.getJsonQuery(doc)
return scraper.scrapeScene(q)
return scraper.scrapeScene(ctx, q)
}
func (s *jsonScraper) scrapeSceneByFragment(ctx context.Context, scene models.ScrapedSceneInput) (*models.ScrapedScene, error) {
func (s *jsonScraper) scrapeByFragment(ctx context.Context, input Input) (models.ScrapedContent, error) {
switch {
case input.Gallery != nil:
return nil, fmt.Errorf("%w: cannot use a json scraper as a gallery fragment scraper", ErrNotSupported)
case input.Performer != nil:
return nil, fmt.Errorf("%w: cannot use a json scraper as a performer fragment scraper", ErrNotSupported)
case input.Scene == nil:
return nil, fmt.Errorf("%w: scene input is nil", ErrNotSupported)
}
scene := *input.Scene
// construct the URL
queryURL := queryURLParametersFromScrapedScene(scene)
if s.scraper.QueryURLReplacements != nil {
@@ -218,7 +205,7 @@ func (s *jsonScraper) scrapeSceneByFragment(ctx context.Context, scene models.Sc
}
q := s.getJsonQuery(doc)
return scraper.scrapeScene(q)
return scraper.scrapeScene(ctx, q)
}
func (s *jsonScraper) scrapeGalleryByGallery(ctx context.Context, gallery *models.Gallery) (*models.ScrapedGallery, error) {
@@ -242,11 +229,7 @@ func (s *jsonScraper) scrapeGalleryByGallery(ctx context.Context, gallery *model
}
q := s.getJsonQuery(doc)
return scraper.scrapeGallery(q)
}
func (s *jsonScraper) scrapeGalleryByFragment(gallery models.ScrapedGalleryInput) (*models.ScrapedGallery, error) {
return nil, errors.New("scrapeGalleryByFragment not supported for json scraper")
return scraper.scrapeGallery(ctx, q)
}
func (s *jsonScraper) getJsonQuery(doc string) *jsonQuery {
@@ -281,8 +264,8 @@ func (q *jsonQuery) runQuery(selector string) ([]string, error) {
return ret, nil
}
func (q *jsonQuery) subScrape(value string) mappedQuery {
doc, err := q.scraper.loadURL(context.TODO(), value)
func (q *jsonQuery) subScrape(ctx context.Context, value string) mappedQuery {
doc, err := q.scraper.loadURL(ctx, value)
if err != nil {
logger.Warnf("Error getting URL '%s' for sub-scraper: %s", value, err.Error())