Merge pull request #2070 from NormanPriv/master

Add scene and performer scrapers for ModelMediaAsia

scrapers/ModelMediaAsia.yml

@@ -0,0 +1,90 @@
+name: "ModelMediaAsia"
+sceneByURL:
+  - action: scrapeXPath
+    url:
+      - modelmediaasia.com/en-US/videos/
+      - modelmediaasia.com/zh-CN/videos/
+    scraper: sceneScraper
+
+sceneByFragment:
+  action: scrapeXPath
+  queryURL: https://modelmediaasia.com/videos/{filename}
+  queryURLReplace:
+    # Assume beginning part contains the code
+    filename:
+      # Get file that matches code
+      - regex: ^([\w\d-]+)
+        with: $1
+      - regex: .*\.[^\.]+$ # if no id is found in the filename
+        with: # clear the filename so that it doesn't leak
+  scraper: sceneScraper
+
+performerByURL:
+  - action: scrapeXPath
+    url:
+      - modelmediaasia.com/en-US/models/
+      - modelmediaasia.com/zh-CN/models/
+    scraper: performerScraper
+
+xPathScrapers:
+  sceneScraper:
+    common:
+      $detailspart: //div[@class="details-part"]
+    scene:
+      Title: $detailspart//h2
+      Date:
+        # Some text may be in front of the date
+        selector: $detailspart//span[contains(@class, "trending-year")]
+        postProcess:
+          - replace:
+            - regex: '.*(\d{4}/\d{1,2}/\d{1,2})'
+              with: $1
+          - parseDate: 2006/01/02
+      Details:
+        selector: //div[@id="description-01"]/div/p/text()
+      Performers:
+        Name: $detailspart//div[@class="content-details trending-info"][2]//h6/text()
+        # workaround for including URL
+        # URL arrays don't work https://github.com/stashapp/stash/issues/5294
+        # Details:
+        #   selector: //*[@id="__nuxt"]/main/div/div[2]/div/div/div/div[3]/div/ul/li/a/@href
+        #   postProcess:
+        #     - replace:
+        #       - regex: ^
+        #         with: https://modelmediaasia.com
+      Studio:
+        Name:
+          fixed: "Model Media"
+      Tags:
+        Name: //ul[contains(@class, "iq-blogtag")]/li/a/text()
+      Image: //div[@class="iq-main-slider site-video"]//div[contains(@class,"object-cover")]/img/@src
+      Code: //div[@class="details-part"]//a[contains(@class,"text-capitalize")]/text()
+  performerScraper:
+    common:
+      $infobox: //div[@id="__nuxt"]/main//div[@class="flex flex-col gap-3 my-5"]
+    performer:
+      Name: //div[@id="__nuxt"]/main//div[contains(@class,"text-white")]/div/h4[1]/text()
+      Gender:
+        fixed: Female
+      Ethnicity:
+        fixed: Asian
+      Height:
+        selector: $infobox/p[1]/text()
+        postProcess:
+          - replace:
+            - regex: '(\d+)\D+cm'
+              with: $1
+      Weight:
+        selector: $infobox/p[2]/text()
+        postProcess:
+          - replace:
+            - regex: '(\d+)\D+kg'
+              with: $1
+      Measurements:
+        selector: $infobox/p[3]/text()
+        postProcess:
+          - replace:
+            - regex: '\s*(\d+\w*)\D+(\d+)\D+(\d+)'
+              with: $1-$2-$3
+      Image: //img[@class="w-full aspect-[3/4]"]/@src
+# Last Updated October 26, 2024