name: AniDB

# ~~~~~~ GETTING STARTED ~~~~~~
# Store this file in the ~/stash/scrapers/AniDB.yml
#  - If the scrapers directory is not there, you must create it first
#
# ~~~~~~ SETTING COOKIES ~~~~~~      
#  Note: I recommend creating a new account just for this scraper                                    
#  1. Access the anidb.net website > login > right button > inspect > find cookies storage
#  2. Copy the "Value" of "adbsess" and "adbuin" and replace in the cookies category of this document
#  3. If your account is new, you need to access any NSFW anime and confirm that you want to see 18+ content
#  4. Do not change the order of the columns, as it can make it stop working
#
# ~~~~~~ SETTING USER AGENT ~~~~~~
#  - Go to your Stash > Settings > Metadata Providers > Scraping > Scraper User Agent
#  - Use the User Agent of your choice
#     - For example: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:79.0) Gecko/20100101 Firefox/79.0
#
# ~~~~~ RECOMMENDED WORKFLOW ~~~~~
#  1. Scrape scene by fragment (for performers, tags, artwork, etc)
#     - If this fails, scrape by anime URL
#  2. Scrape by episode URL (for title, date)
#  3. Manually set movie scene number on scene page
#  3. Navigate to each performer's page & scrape by URL
#  4. Navigate to movie page & scrape by URL
#
# ~~~~~~ HOW TO USE (detailed) ~~~~~~    
# tl;dr when in doubt, use the URL scrapers 
#  - For scenes: anidb.net/episode/XXX, anidb.net/anime/XXX
#  - For performers: anidb.net/character/XXX
#  - For movies: anidb.net/anime/XXX
#                                         
# SCENES (by anime):                                                    
#  - The Scraper by Fragment will usually work, assuming a filename like "[XX] My Lewd Anime - 01 (720p) (x264).mkv"
#      - This regex expression strips underscores, dashes, content containing brackets and parentheses, and two digit numbers
#      - For example, the above filename is stripped to "My Lewd Anime"
#  - If this does not work, I recommend scraping with the episode URL, the anime URL, or the name scraper
#  - By default, the scene scraper does not set the title, as the episode scraper serves this purpose better
#     - However, if you'd like to enable this functionality, uncomment the "Title" line in sceneScraperAnime > scene
#  - The scene (by anime) scraper automatically creates a new movie (i.e., series) entry, 
#    but unfortunately you will have to set the movie scene (i.e., episode) number manually
#
# SCENES (by episode):
#  - This scraper is only accessible by scraping the episode URL (anidb.net/episode/XXX)
#  - The scene episode scraper sets the episode title, the anime URL (if missing), and the original airing date
#    - By default, the regex expression strips the episode number when setting the title
#    - If you want to keep the episode number, delete the second regex replacement in 
#      sceneScraperEpisode > scene > Title > postProcess > replace
#
# MOVIES:
#  - The scene (by anime) scraper automatically creates a new movie entry using the anime title and anime URL
#  - On the movie page, you can scrape by URL
# 
# PERFORMERS:                                                  
#  - Performers need to be individually scraped by name or URL                           
#  - I recommend creating them by scraping the anime URL, then navigating to the performer page.
#    The performer URL should already be set, so you just need to press the scrape by URL button.
#
# ~~~~~ TROUBLESHOOTING ~~~~~
# - If you find that the scraper has suddenly stopped working, RESET YOUR COOKIES!
#
# ~~~~~ ANYTHING ELSE? ~~~~~
# THAT'S IT, ENJOY! 
# Made by @escargotbuffed, further improvements by @symptom6186

performerByURL:
  - action: scrapeXPath
    url:
      - https://anidb.net
    scraper: performerScraper
performerByName:
  action: scrapeXPath
  queryURL: https://anidb.net/search/anime/?adb.search={}&entity.chartb=1
  scraper: performerSearch

sceneByFragment:
  action: scrapeXPath
  queryURL: https://anidb.net/anime/?adb.search={filename}
  queryURLReplace:
    filename:
      - regex: '\[.*?\]|\(.*?\)|\d\d|\..*'
        with: 
      - regex: '\-|\_'
        with: " "
      - regex: \s+
        with: "%20"
  scraper: sceneScraperAnime
sceneByURL:
  - action: scrapeXPath
    url:
      - https://anidb.net/episode/
    scraper: sceneScraperEpisode
  - action: scrapeXPath
    url:
      - https://anidb.net/anime/
    scraper: sceneScraperAnime
sceneByName:
  action: scrapeXPath
  queryURL: https://anidb.net/search/anime/?adb.search={}&entity.animetb=1
  scraper: sceneSearch
sceneByQueryFragment:
  action: scrapeXPath
  queryURL: "{url}"
  scraper: sceneScraperAnime

movieByURL:
  - action: scrapeXPath
    url:
      - https://anidb.net/
    scraper: sceneScraperAnime

xPathScrapers:
  performerSearch:
    performer:
      Name: //td[@class="relid"]/a
      URL:
        selector: //td[@class="relid"]/a/@href
        postProcess:
          - replace:
              - regex: ^
                with: https://anidb.net
  performerScraper:
    common:
      $info: //div[@class="g_section info"]
      $tab_1_pane: //div[@class="g_section info"]//div[@id="tab_1_pane"]
      $looks: //div[@class="g_section info"]//div[@id="tab_1_pane"]//tr[contains(@class, 'looks')]
    performer:
      Name: $tab_1_pane//tr[contains(@class, 'mainname')]//span[@itemprop="name"]
      Aliases: $tab_1_pane//tr[contains(@class, 'official')]//label[@itemprop="alternateName"]
      Disambiguation: $tab_1_pane//tr[contains(@class, 'mainname')]//a[@class='shortlink']
      Gender: $tab_1_pane//tr[contains(@class, 'gender')]//span[@itemprop="gender"]
      Ethnicity: $tab_1_pane//tr[contains(@class, 'entity')]//span[@class="tagname"]
      HairColor: $looks//span[contains(@class, 'tagname') and contains(text(), 'hair')]
      EyeColor: $looks//span[contains(@class, 'tagname') and contains(text(), 'eyes')]
      Height: $tab_1_pane//tr[contains(@class, 'height')]//span[@itemprop="height"]
      Weight: $tab_1_pane//tr[contains(@class, 'weight')]//span[@itemprop="weight"]
      #Measurements: Todo
      URL: //link[@rel="canonical"]/@href
      Details: 
        selector: //div[@itemprop="description"]//text()
        concat: "\n"
      Tags:
        Name: $tab_1_pane//span[@class="g_tag"]//span[@class="tagname"]
      Image: $info//div[@class="image"]//img/@src

  sceneSearch:
    scene:
      Title: //td[@class="relid"]/a
      URL:
        selector: //td[@class="relid"]/a/@href
        postProcess:
          - replace:
              - regex: ^
                with: https://anidb.net
      Image: //td[@class="thumb anime"]//img/@src
  sceneScraperEpisode:
    scene:
      Title: 
        selector: //div[@id="layout-main"]//h1[@class="ep"]
        postProcess:
          - replace:
             - regex: ^.{0,9}
               with: ""
             - regex: \- \d+ \-
               with: "/"
      URL: 
        selector: //ul[@class="main-tabs"]//li[@class="g_odd anime"]//span/a/@href
        postProcess: 
          - replace:
              - regex: ^
                with: https://anidb.net
      Date: //div[@id="layout-main"]//span[@itemprop="datePublished"]/@content
  sceneScraperAnime:
    common:
      $info: //div[@class="g_section info"]
      $title: //div[@class="g_section info"]//div[@id="tab_1_pane"]//span[@itemprop="name"]
      $en_title: //div[@class="g_section info"]//div[@id="tab_1_pane"]//tr[contains(@class, "official verified") and contains(.//span, 'en')]//label[@itemprop="alternateName"]
      $character: //div[@id="characterlist"]//div[contains(@class, 'main character') or contains(@class, 'secondary cast')]//div[@itemprop="character"]
    scene:
      #Title: $en_title or $title
      #Date: 
      #  selector: $info//div[@id="tab_1_pane"]//span[contains(@itemprop, "datePublished") or contains(@itemprop, "startDate")]
      #  parseDate: 02.01.2006
      Details: 
        selector: //div[@itemprop="description"]//text()
        concat: " "
      Tags:
        Name: $info//div[@id="tab_1_pane"]//span[@class="tagname"]
      Performers:
        Name: $character/a/span
        URL: 
          selector: $character/a/@href
          postProcess:
            - replace:
                - regex: ^
                  with: https://anidb.net
      Movies:
        Name: $title
        URL: //link[@rel="canonical"]/@href
      Studio:
        Name: $info//table[@id="staffoverview"]//tr[last()]/td[@class="name creator"]/a
      Image: $info//div[@class="image"]//img/@src
      URL: //link[@rel="canonical"]/@href
    movie:
      Name: $title
      Aliases: $en_title
      Date: 
        selector: $info//div[@id="tab_1_pane"]//span[contains(@itemprop, "datePublished") or contains(@itemprop, "startDate")]
        postProcess:
          - parseDate: 02.01.2006
      Synopsis: 
        selector: //div[@itemprop="description"]//text()
        concat: " "
      Studio:
        Name: $info//table[@id="staffoverview"]//tr[last()]/td[@class="name creator"]/a
      FrontImage: $info//div[@class="image"]//img/@src
      URL: //link[@rel="canonical"]/@href
      
driver:
  cookies:
    - CookieURL: "https://anidb.net/"
      Cookies:
        # Access adult content requires a anidb account
        # Replace value field
        - Name: "adbsess"
          Domain: "anidb.net"
          Value: "" # Enter the value of the 'adbsess' here
          Path: "/"
        - Name: "adbuin"
          Domain: "anidb.net"
          Value: "" # Enter the value of the 'adbuin' here
          Path: "/"
# Last Updated Dec 20, 2023