stash

stash/config/scrapers/community/ATKGirlfriends/ATKGirlfriends.py

@@ -0,0 +1,70 @@
+import json
+import os
+import re
+import requests
+import sys
+
+import py_common.log as log
+
+try:
+    from lxml import html
+except ModuleNotFoundError:
+    log.error("You need to install the lxml module. (https://lxml.de/installation.html#installation)")
+    log.error("If you have pip (normally installed with python), run this command in a terminal (cmd): python -m pip install lxml")
+    sys.exit()
+
+kgs_per_lb = 0.45359237
+cms_per_in = 2.54
+filename_pattern = re.compile(r"(?P<model_id>[a-z]{3}\d{3})ATK_(?P<movie_id>\d{6})(?P<scene>\d{3})_(?P<resolution>\w+)(?:\.(?P<extension>\w+))?", re.IGNORECASE)
+
+def getSceneByFilename(filename):
+    # Parse filename
+    filename_match = filename_pattern.match(filename)
+    (model_id, movie_id, _, _, _) = filename_match.groups()
+
+    # Fetch model page
+    model_url = f"https://www.atkgirlfriends.com/tour/model/{model_id}"
+    log.debug(f"Fetching {model_url} ({movie_id})")
+    response = requests.get(model_url, cookies=dict(start_session_galleria = 'stash'))
+    if (response.url.startswith("https://www.atkgirlfriends.com?nats")):
+        # Refetch page on cookie failure
+        response = requests.get(model_url, cookies=dict(start_session_galleria = 'stash'))
+
+    # Build performer
+    tree = html.fromstring(response.text)
+    performer = dict(Gender = "female")
+    model_profile_wrap_xpath = '//div[contains(@class, "model-profile-wrap")]'
+    performer["name"] = tree.xpath('//h1[contains(@class, "page-title")]')[0].text
+    performer["url"] = f"{model_url}/1/atk-girlfriends-{performer['name'].replace(' ', '-')}"
+    performer["ethnicity"] = tree.xpath(f'{model_profile_wrap_xpath}/b[contains(text(), "Ethnicity")]/following-sibling::text()')[0].strip().capitalize()
+    performer["hair_color"] = tree.xpath(f'{model_profile_wrap_xpath}/b[contains(text(), "Hair Color")]/following-sibling::text()')[0].strip().capitalize()
+    height_ft_ins_str = tree.xpath(f'{model_profile_wrap_xpath}/b[contains(text(), "Height")]/following-sibling::text()')[0].strip()
+    (height_ft_str, height_ins_str) = re.compile(r"(\d+)[\"'](\d+)").findall(height_ft_ins_str)[0]
+    height_ins = float(height_ft_str) * 12 + float(height_ins_str)
+    performer["height"] = str(int(height_ins * cms_per_in))
+    weight_lbs_str = tree.xpath(f'{model_profile_wrap_xpath}/b[contains(text(), "Weight")]/following-sibling::text()')[0].strip()
+    weight_lbs = float(re.compile(r"\d+").findall(weight_lbs_str)[0])
+    performer["weight"] = str(int(weight_lbs * kgs_per_lb))
+    performer["measurements"] = tree.xpath(f'{model_profile_wrap_xpath}/b[contains(text(), "Bust Size")]/following-sibling::text()')[0].strip()
+    performer["image"] = tree.xpath(f'{model_profile_wrap_xpath}/img/@src')[0]
+
+    # Build scene
+    scene = dict(studio = dict(name = "ATK Girlfriends"), performers = [performer])
+    movie_wrap_xpath = f'//img[contains(@src, "/{model_id}/{movie_id}")]/../../../..'
+    scene["title"] = tree.xpath(f'{movie_wrap_xpath}//h1')[0].text.strip()
+    scene["details"] = tree.xpath(f'{movie_wrap_xpath}//b[contains(text(), "Description")]/following-sibling::text()')[0].strip()
+    movie_url_relative = tree.xpath(f'{movie_wrap_xpath}//a/@href')[0]
+    scene["url"] = f'https://www.atkgirlfriends.com{movie_url_relative}'
+    scene["image"] = tree.xpath(f'{movie_wrap_xpath}//img/@src')[0]
+
+    return scene
+
+input = sys.stdin.read()
+match = filename_pattern.search(input)
+if (match):
+    scene = getSceneByFilename(match.group())
+    output = json.dumps(scene)
+    print(output)
+else:
+    log.debug("Filename does not match ATKGirlfriends pattern")
+    print(r"{}")

stash/config/scrapers/community/ATKGirlfriends/ATKGirlfriends.yml

@@ -0,0 +1,90 @@
+name: ATK Girlfriends
+# requires: py_common
+sceneByFragment:
+  action: script
+  script:
+    - python
+    - ATKGirlfriends.py
+performerByURL:
+  - action: scrapeXPath
+    url:
+      # Trying to scrape without the www. prefix will result in a redirect loop
+      - www.atkgirlfriends.com/tour/model/
+    scraper: performerScraper
+sceneByURL:
+  - action: scrapeXPath
+    url:
+      # Trying to scrape without the www. prefix will result in a redirect loop
+      - www.atkgirlfriends.com/tour/movie/
+    scraper: sceneScraper
+xPathScrapers:
+  performerScraper:
+    common:
+      $modelWrap: &modelWrap //div[contains(@class, "model-profile-wrap")]
+    performer:
+      Name: //h1[contains(@class, "page-title")]
+      Gender:
+        fixed: female
+      Ethnicity:
+        selector: $modelWrap/b[contains(text(), "Ethnicity")]/following-sibling::text()
+      HairColor:
+        selector: $modelWrap/b[contains(text(), "Hair Color")]/following-sibling::text()
+        postProcess:
+          - map:
+              black: Black
+              blond: Blonde
+              brown: Brown
+              red: Red
+              white: White
+      Height:
+        selector: $modelWrap/b[contains(text(), "Height")]/following-sibling::text()
+        postProcess:
+          - feetToCm: true
+      Weight:
+        selector: $modelWrap/b[contains(text(), "Weight")]/following-sibling::text()
+        postProcess:
+          - replace:
+              - regex: (\d+).*
+                with: $1
+          - lbToKg: true
+      Measurements:
+        selector: $modelWrap/b[contains(text(), "Bust Size")]/following-sibling::text()
+      Image:
+        selector: $modelWrap/img/@src
+  sceneScraper:
+    common:
+      $movieWrap: //div[contains(@class, "movie-wrap")]
+      $modelWrap: *modelWrap
+    scene:
+      Title: //title
+      Details: $movieWrap/b[contains(text(), "Description")]/following-sibling::text()
+      Image:
+        selector: //video/@poster | //div[@class="flowplayer minimalist is-splash"]/@style
+        postProcess:
+          - replace:
+              - regex: background-image:url\('(.*)'\);
+                with: $1
+      Studio:
+        Name:
+          fixed: ATK Girlfriends
+        URL:
+          fixed: https://www.atkgirlfriends.com/
+      Tags:
+        Name:
+          selector: $movieWrap/b[contains(text(), "Tags")]/following-sibling::text()
+          postProcess:
+            - replace:
+                - regex: \s*,\s*
+                  with: ","
+          split: ","
+      Performers:
+        Name: $modelWrap/text()[1]
+driver:
+  cookies:
+    - CookieURL: https://www.atkgirlfriends.com
+      Cookies:
+        - Name: start_session_galleria
+          Domain: www.atkgirlfriends.com
+          Value: stash # Rotate this value if the scraper is blocked. The first request with the new value should fail.
+          Path: /
+# Last Updated March 14, 2024

stash/config/scrapers/community/ATKGirlfriends/manifest

@@ -0,0 +1,10 @@
+id: ATKGirlfriends
+name: ATK Girlfriends
+metadata: {}
+version: 71e0b03
+date: "2024-03-15 01:14:32"
+requires: []
+source_repository: https://stashapp.github.io/CommunityScrapers/stable/index.yml
+files:
+- ATKGirlfriends.yml
+- ATKGirlfriends.py