Fixed Gamma scene scraper extracting the wrong scene ID from non-standard URLs.

This commit is contained in:
2020-03-07 23:40:38 +01:00
parent d6fb9da176
commit 628c5a2013
3 changed files with 8 additions and 15 deletions

View File

@@ -187,7 +187,7 @@ function scrapeAll(html, site, networkUrl, hasTeaser = true) {
});
}
async function scrapeScene(html, url, site, scrapedRelease, mobileHtml) {
async function scrapeScene(html, url, site, baseRelease, mobileHtml) {
const $ = cheerio.load(html, { normalizeWhitespace: true });
const m$ = mobileHtml && cheerio.load(mobileHtml, { normalizeWhitespace: true });
const release = { $, url };
@@ -198,7 +198,7 @@ async function scrapeScene(html, url, site, scrapedRelease, mobileHtml) {
const [data, data2] = json ? JSON.parse(json) : [];
const videoData = videoJson && JSON.parse(videoJson.slice(videoJson.indexOf('{'), videoJson.indexOf('};') + 1));
[release.entryId] = (scrapedRelease?.path || new URL(url).pathname).split('/').slice(-1);
release.entryId = (baseRelease?.path || new URL(url).pathname).match(/\/(\d{2,})\//)[1];
release.title = videoData?.playerOptions?.sceneInfos.sceneTitle || data?.name;
// date in data object is not the release date of the scene, but the date the entry was added; only use as fallback