mirror of
https://github.com/stashapp/stash.git
synced 2025-12-06 16:34:02 +01:00
* 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.
276 lines
6.5 KiB
Go
276 lines
6.5 KiB
Go
package scraper
|
|
|
|
import (
|
|
"context"
|
|
"errors"
|
|
"fmt"
|
|
"io"
|
|
"net/http"
|
|
"net/url"
|
|
"strings"
|
|
|
|
"github.com/stashapp/stash/pkg/logger"
|
|
"github.com/stashapp/stash/pkg/models"
|
|
"github.com/tidwall/gjson"
|
|
)
|
|
|
|
type jsonScraper struct {
|
|
scraper scraperTypeConfig
|
|
config config
|
|
globalConfig GlobalConfig
|
|
client *http.Client
|
|
txnManager models.TransactionManager
|
|
}
|
|
|
|
func newJsonScraper(scraper scraperTypeConfig, client *http.Client, txnManager models.TransactionManager, config config, globalConfig GlobalConfig) *jsonScraper {
|
|
return &jsonScraper{
|
|
scraper: scraper,
|
|
config: config,
|
|
client: client,
|
|
globalConfig: globalConfig,
|
|
txnManager: txnManager,
|
|
}
|
|
}
|
|
|
|
func (s *jsonScraper) getJsonScraper() *mappedScraper {
|
|
return s.config.JsonScrapers[s.scraper.Scraper]
|
|
}
|
|
|
|
func (s *jsonScraper) scrapeURL(ctx context.Context, url string) (string, *mappedScraper, error) {
|
|
scraper := s.getJsonScraper()
|
|
|
|
if scraper == nil {
|
|
return "", nil, errors.New("json scraper with name " + s.scraper.Scraper + " not found in config")
|
|
}
|
|
|
|
doc, err := s.loadURL(ctx, url)
|
|
|
|
if err != nil {
|
|
return "", nil, err
|
|
}
|
|
|
|
return doc, scraper, nil
|
|
}
|
|
|
|
func (s *jsonScraper) loadURL(ctx context.Context, url string) (string, error) {
|
|
r, err := loadURL(ctx, url, s.client, s.config, s.globalConfig)
|
|
if err != nil {
|
|
return "", err
|
|
}
|
|
logger.Infof("loadURL (%s)\n", url)
|
|
doc, err := io.ReadAll(r)
|
|
if err != nil {
|
|
return "", err
|
|
}
|
|
|
|
docStr := string(doc)
|
|
if !gjson.Valid(docStr) {
|
|
return "", errors.New("not valid json")
|
|
}
|
|
|
|
if err == nil && s.config.DebugOptions != nil && s.config.DebugOptions.PrintHTML {
|
|
logger.Infof("loadURL (%s) response: \n%s", url, docStr)
|
|
}
|
|
|
|
return docStr, err
|
|
}
|
|
|
|
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)
|
|
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)
|
|
}
|
|
|
|
return nil, ErrNotSupported
|
|
}
|
|
|
|
func (s *jsonScraper) scrapeByName(ctx context.Context, name string, ty models.ScrapeContentType) ([]models.ScrapedContent, error) {
|
|
scraper := s.getJsonScraper()
|
|
|
|
if scraper == nil {
|
|
return nil, fmt.Errorf("%w: name %v", ErrNotFound, s.scraper.Scraper)
|
|
}
|
|
|
|
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(ctx, url)
|
|
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
q := s.getJsonQuery(doc)
|
|
|
|
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) {
|
|
// construct the URL
|
|
queryURL := queryURLParametersFromScene(scene)
|
|
if s.scraper.QueryURLReplacements != nil {
|
|
queryURL.applyReplacements(s.scraper.QueryURLReplacements)
|
|
}
|
|
url := queryURL.constructURL(s.scraper.QueryURL)
|
|
|
|
scraper := s.getJsonScraper()
|
|
|
|
if scraper == nil {
|
|
return nil, errors.New("json scraper with name " + s.scraper.Scraper + " not found in config")
|
|
}
|
|
|
|
doc, err := s.loadURL(ctx, url)
|
|
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
q := s.getJsonQuery(doc)
|
|
return scraper.scrapeScene(ctx, q)
|
|
}
|
|
|
|
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 {
|
|
queryURL.applyReplacements(s.scraper.QueryURLReplacements)
|
|
}
|
|
url := queryURL.constructURL(s.scraper.QueryURL)
|
|
|
|
scraper := s.getJsonScraper()
|
|
|
|
if scraper == nil {
|
|
return nil, errors.New("xpath scraper with name " + s.scraper.Scraper + " not found in config")
|
|
}
|
|
|
|
doc, err := s.loadURL(ctx, url)
|
|
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
q := s.getJsonQuery(doc)
|
|
return scraper.scrapeScene(ctx, q)
|
|
}
|
|
|
|
func (s *jsonScraper) scrapeGalleryByGallery(ctx context.Context, gallery *models.Gallery) (*models.ScrapedGallery, error) {
|
|
// construct the URL
|
|
queryURL := queryURLParametersFromGallery(gallery)
|
|
if s.scraper.QueryURLReplacements != nil {
|
|
queryURL.applyReplacements(s.scraper.QueryURLReplacements)
|
|
}
|
|
url := queryURL.constructURL(s.scraper.QueryURL)
|
|
|
|
scraper := s.getJsonScraper()
|
|
|
|
if scraper == nil {
|
|
return nil, errors.New("json scraper with name " + s.scraper.Scraper + " not found in config")
|
|
}
|
|
|
|
doc, err := s.loadURL(ctx, url)
|
|
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
q := s.getJsonQuery(doc)
|
|
return scraper.scrapeGallery(ctx, q)
|
|
}
|
|
|
|
func (s *jsonScraper) getJsonQuery(doc string) *jsonQuery {
|
|
return &jsonQuery{
|
|
doc: doc,
|
|
scraper: s,
|
|
}
|
|
}
|
|
|
|
type jsonQuery struct {
|
|
doc string
|
|
scraper *jsonScraper
|
|
}
|
|
|
|
func (q *jsonQuery) runQuery(selector string) ([]string, error) {
|
|
value := gjson.Get(q.doc, selector)
|
|
|
|
if !value.Exists() {
|
|
return nil, fmt.Errorf("could not find json path '%s' in json object", selector)
|
|
}
|
|
|
|
var ret []string
|
|
if value.IsArray() {
|
|
value.ForEach(func(k, v gjson.Result) bool {
|
|
ret = append(ret, v.String())
|
|
return true
|
|
})
|
|
} else {
|
|
ret = append(ret, value.String())
|
|
}
|
|
|
|
return ret, nil
|
|
}
|
|
|
|
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())
|
|
return nil
|
|
}
|
|
|
|
return q.scraper.getJsonQuery(doc)
|
|
}
|