name: Watch4Beauty
sceneByURL:
  - action: scrapeJson
    url: &storiesURL
      - https://www.watch4beauty.com/stories/
    queryURL: &queryURL https://www.watch4beauty.com/api/{url}
    scraper: sceneStoriesScraper
    queryURLReplace: &storiesQueryURL
      url:
        - regex: ".+/stories/"
          with: "magazines/"
  - action: scrapeJson
    url: &updatesURL
      - https://www.watch4beauty.com/updates/
    queryURL: *queryURL
    scraper: sceneUpdatesScraper
    queryURLReplace: &updatesQueryURL
      url:
        - regex: ".+/updates/"
          with: "issues/"
galleryByURL:
  - action: scrapeJson
    url: *storiesURL
    queryURL: *queryURL
    scraper: galleryStoriesScraper
    queryURLReplace: *storiesQueryURL
  - action: scrapeJson
    url: *updatesURL
    queryURL: *queryURL
    scraper: galleryUpdatesScraper
    queryURLReplace: *updatesQueryURL

jsonScrapers:
  sceneStoriesScraper:
    scene:
      Title: &storiesTitle 0.magazine_title
      Details: &storiesDetails 0.magazine_text
      Date: &storiesDate
        selector: 0.magazine_datetime
        postProcess:
          - replace:
              - regex: T.+
                with: ""
      Image: &storiesImage
        selector: 0.magazine_datetime
        postProcess:
          - replace:
              - regex: T.+
                with: ""
          - replace:
              - regex: '(\d+)-(\d+)-(\d+)'
                with: "https://s5q3w2t8.ssl.hwcdn.net/production/$1$2$3-magazine-cover-wide-2560.jpg" # wide cover
                #with: "https://s5q3w2t8.ssl.hwcdn.net/production/$1$2$3-magazine-cover-640.jpg" # normal cover
      Performers: &storiesPerformers
        Name:
          selector: 0.magazine_simple_title
          postProcess:
            - replace:
                - regex: ^
                  with: "https://www.watch4beauty.com/api/magazines/"
                - regex: $
                  with: "/models"
            - subScraper:
                selector: "0.Models.#.model_nickname"
                concat: ","

          split: ","
      Studio: &studioAttr
        Name:
          fixed: Watch4Beauty
      Tags: &storiesTags
        Name:
          selector: 0.magazine_tags
          split: ", "
  sceneUpdatesScraper:
    scene:
      Title: &updatesTitle 0.issue_title
      Details: &updatesDetails 0.issue_text
      Date: &updatesDate
        selector: 0.issue_datetime
        postProcess:
          - replace:
              - regex: T.+
                with: ""
      Image:
        selector: 0.issue_datetime
        postProcess:
          - replace:
              - regex: T.+
                with: ""
          - replace:
              - regex: '(\d+)-(\d+)-(\d+)'
                with: "https://s5q3w2t8.ssl.hwcdn.net/production/$1$2$3-issue-cover-wide-2560.jpg" # wide cover
                #with: "https://s5q3w2t8.ssl.hwcdn.net/production/$1$2$3-issue-cover-640.jpg" # normal cover
      Performers: &updatesPerformers
        Name:
          selector: 0.issue_simple_title
          postProcess:
            - replace:
                - regex: ^
                  with: "https://www.watch4beauty.com/api/issues/"
                - regex: $
                  with: "/models"
            - subScraper:
                selector: "0.Models.#.model_nickname"
                concat: ","
          split: ","
      Studio: *studioAttr
      Tags: &updatesTags
        Name:
          selector: 0.issue_tags
          split: ", "
  galleryStoriesScraper:
    gallery:
      Title: *storiesTitle
      Details: *storiesDetails
      Date: *storiesDate
      Performers: *storiesPerformers
      Studio: *studioAttr
      Tags: *storiesTags
  galleryUpdatesScraper:
    gallery:
      Title: *updatesTitle
      Details: *updatesDetails
      Performers: *updatesPerformers
      Date: *updatesDate
      Studio: *studioAttr
      Tags: *updatesTags
# Last Updated November 12, 2021