config.yaml

# Tell me what's going on.. can also pass command line argument -v
verbose: False

# The directory where exitwp looks for wordpress export xml files.
wp_exports: wordpress-xml

# The target directory where all output is saved.
build_dir: build

# Output format: primary choices are html or markdown.
# Some functions, like the inclusion of comments, only output in markdown,
# and may look not as expected in html.
target_format: markdown

# The date format of the wikipedia export file.
# I'm not sure if this ever differs depending on WordPress localization.
# Wordpress is often so full of strange quirks so I wouldn't rule it out.
date_format: '%Y-%m-%d %H:%M:%S'

# Try to download and relocate all images locally to the blog.
download_images: True

# Image URL filtering
image_settings:
  # URL parts to exclude when processing images
  excluded_url_parts:
    - 'tracking.pixel.com'
    - 'http://www.assoc-amazon.com/'
  # Domains to always include when processing images
  included_domains:
    - 'images.mysite.com'
    - 'cdn.mysite.com'
    - 'myoldblog.com'
  # Default behavior for image validity when no other conditions are met
  # Set to true to include images by default, false to exclude by default
  #
  # If set to true:
  #   - All images will be considered valid unless explicitly excluded
  #   - The 'included_domains' setting will have no effect
  #
  # If set to false:
  #   - Only images from 'included_domains' will be considered valid
  #   - All other images will be excluded unless explicitly included
  #   - This can be handy if you want to process only images from your old
  #     blog for example, but not download images from the public internet
  #     to your own (new) server.
  #
  # Examples:
  # 1. To process all images except those from specific domains:
  #    default_image_validity: true
  #    excluded_url_parts:
  #      - 'ads.example.com'
  #      - 'tracking.example.com'
  #
  # 2. To process only images from specific domains:
  #    default_image_validity: false
  #    included_domains:
  #      - 'images.mysite.com'
  #      - 'cdn.mysite.com'
  #
  default_image_validity: false
  # Icon to use when an image is not found. Make sure to put this file in
  # the right place on your destination server manually.
  # (This file is not supplied with exitwp, you have to pick one yourself.)
  not_found_icon: '/icons/question-warning.svg'
  # Default timeout (in seconds) for image downloads
  download_timeout: 3

# Include old/existing comments with the post
include_comments: true

# Item types we don't want to import.
item_type_filter: {attachment, nav_menu_item}

# filter by any field type on the post.
# By default, we're filtering based on field "status" set to "draft"
item_field_filter: {status: draft}

# Output label for categories or tags.
# NOTE: This overrides the name_mapping in the taxonomies below!
# Default will be tags_label: 'categories', as specified in the exitwp.py
# script, if not defined here.
tags_label: 'tags'

taxonomies:
  # Filter taxonomies.
  filter: {}
  # Filter taxonomies entries.
  entry_filter: {category: Uncategorized}
  # Rename taxonomies when writing jekyll output format.
  # NOTE: categories label is overwritten by the tags_label above!!
  name_mapping: {category: categories, post_tag: tags}

# Replace certain patterns in body
# Simply replace the key with its value
body_replace: {
  # '\(/media/': '(/images/posts/',
  # '<pre.*?lang="(.*?)".*?>': '\n{% codeblock \1 lang:\1 %}\n',
  # '<pre.*?>': '\n{% codeblock %}\n',
  # '</pre>': '\n{% endcodeblock %}\n',

  #    '[python]': '{% codeblock lang:python %}',
  #    '[/python]': '{% endcodeblock %}',
  }