config.default.yaml

## Common Settings
# The directory where prepared uploads are stored
output_dir: /home/user/podcasts

# If this is set, files will always be stored here
# instead of the parent dir of the podcast. This is
# mainly useful when generating torrents or reports.
base_dir: null

# The temporary name for a new download
temp_dir_name: temp_download

# Whether to include metadata in the upload
include_metadata: true

# The directory where metadata is stored
metadata_directory: Metadata

# Keep a copy of the metadata json
archive_metadata: false

# The directory to store the archived metadata
archive_metadata_directory: /home/user/podcasts/archive

# Whether to keep the source RSS file, only applies to local files
keep_source_rss: false

# The size you want the resized cover art to be
cover_size: 800

# The announce URL for the tracker
announce_url: https://tracker.com/announce/thisismysecretkey

# Source tag to add to the torrent
tracker_source: null

# The API key to access the tracker
api_key: andthisismyapikey

# The URL to check for duplicates
dupecheck_url: https://tracker.com/api/torrents/filter

# How the RSS feed should be censored. Can be 'delete', 'edit'
rss_censor_mode: delete

## Cache settings
cache:
  directory: /home/user/podcasts/cache # The directory to store the cache
  hours: 24 # The number of hours to keep the cache

# The cutoff for using mixed labels
cutoff: .7

# If true, uploads of active podcasts will be split on current year
full_years_only: false

## API Settings
# The Podchaser API settings
podchaser: 
  active: false # Whether to use the Podchaser API
  token: null # The Podchaser API token
  fields: # The fields to retrieve from the API
    - id
    - title
    - description
    - author:
      - name
    - url
    - webUrl
    - rssUrl
    - language
    - status
    - numberOfEpisodes
    - avgEpisodeLength
    - daysBetweenEpisodes
    - startDate
    - latestEpisodeDate
    - ratingAverage
    - ratingCount
    - applePodcastsId
    - spotifyId
    - networks:
      - id
      - title
      - url
    - categories:
      - title
  url: https://api.podchaser.com/graphql # The Podchaser API URL
  formatters: # The formatters to apply to the data
    - property: description # The property to format
      method: limit_line_length # The method to apply
      settings: # The settings for the method
        max_length: 125 # The maximum length of the line

# The Podcast Index API settings
podcastindex:
  active: false # Whether to use the Podcast Index API
  key: null # The Podcast Index API key
  secret: null # The Podcast Index API secret
  url: https://api.podcastindex.org/api/1.0/search/byterm?q= # The Podcast Index API URL

## Scraper settings
# Podnews settings
podnews:
  active: false # Whether to use the Podnews scraper
  url: https://podnews.net/search?q= # The Podnews Search URL

## podcast-dl Settings
podcast_dl:
  episode_template: '{{podcast_title}} - {{release_year}}-{{release_month}}-{{release_day}} {{title}}' # The template for the episode name
  threads: 4 # Number of threads to use for downloading

## Various settings
# The script will ask if you want to delete files matching these strings
unwanted_files:
  - What to Listen to Next
  - More from
  - Introducing
  - New from
  - Presents
  - Preview
  - Replay
  - Rebroadcast
  - Re-run
  - Re-release
  - Presenting

# The premium networks to check for
premium_networks:
  - text: Wondery+
    tag: title
    name: Wondery+
  - text: W+
    tag: title
    name: Wondery+
  - text: patreon.com
    tag: link
    name: Patreon

# Indicators that an episode is a trailer (affects episode numbering)
trailer_patterns:
  - trailer
  - preview
  - introducing

# Decides if the premium tag should be included in the name
include_premium_tag: true

# The number of days to wait before a podcast is considered complete
completed_threshold_days: 365

# The replacements to make in the folder and file names
file_replacements:
  - pattern: 'Wondery\+ Edition'
    replacement: ''
    flags:
      - IGNORECASE
  - pattern: 'Wondery\+'
    replacement: ''
    flags:
      - IGNORECASE
  - pattern: 'W\+'
    replacement: ''
    flags:
      - IGNORECASE
  - pattern: 'Premium'
    replacement: ''
    flags:
      - IGNORECASE
  - pattern: '_'
    replacement: ' -'
  - pattern: '\s*-\s*\.'
    replacement: '.'
  - pattern: '\s{2,}'
    replacement: ' '
  - pattern: '\s+\.(\w+)$'
    replacement: '.\1'
  - pattern: '(?<!\d)(-)(?!\d)(\w)'
    replacement: '\1 \2'
  - pattern: '-\s+-'
    replacement: '-'
    repeat_until_no_change: true
  - pattern: '\s+(?=\.)'
    replacement: ''

# The replacements to make in the file level metadata fields
file_metadata_replacements:
  - fields: ['album', 'title']
    pattern: '\s*\(.*?John Doe.*?\)'
    replacement: ''
    flags:
      - IGNORECASE

# The replacements to make in the description
description_replacements:
  - pattern: '<br>'
    replace_with: '\n'
  - pattern: '<p>'
    replace_with: '\n'
  - pattern: '</p>'
    replace_with: '\n'
  - pattern: '&nbsp;'
    replace_with: ' '
  - pattern: '<em>'
    replace_with: '[i]'
  - pattern: '</em>'
    replace_with: '[/i]'

# The replacements to make in the title
title_replacements:
  - pattern: 'Wondery\+ Edition'
    replacement: ''
    flags:
      - IGNORECASE
  - pattern: 'Wondery\+'
    replacement: ''
    flags:
      - IGNORECASE
  - pattern: 'W\+'
    replacement: ''
    flags:
      - IGNORECASE
  - pattern: 'Premium'
    replacement: ''
    flags:
      - IGNORECASE
  - pattern: '[^\w\s-]'
    replacement: ''
  - pattern: '\s*-\s*$'
    replacement: ''

# Used when splitting the title to add episode numbers
title_split_pattern:  '- (?=[^-]*$)'

# Used when checking previous word for titlecase
pattern_previous_word: '\b(\d+\.)|\b\d+\b|-|\b\w+_?'

## Date formats
# Short date format
date_format_short: '%Y-%m-%d'

# Long date format
date_format_long: '%B %d %Y'

## Patterns
# The pattern to match the episode file
ep_nr_at_end_file_pattern: '^(.* - )(\d{4}-\d{2}-\d{2}) (.*?)( - )((Ep\.?|Episode|E)?\s*(\d+))(\.\w+)$'

# The pattern to match the episode file with a number
numbered_episode_pattern: '^(.* - )(\d{4}-\d{2}-\d{2}) (\d+)\. (.*)(\.\w+)'

# The pattern to match the episode file without a number
unnumbered_episode_pattern: '^(.*) - )(\d{4}-\d{2}-\d{2}) (.*)(\.\w+)'

# When renaming files, anything matching these patterns will be uppercase
force_uppercase:
  - '^S\d+E\d+$'
  - '^E\d+$'

# When renaming files, anything matching these patterns will be title case
force_titlecase:
  - '^A$'
  - '^An$'
  - '^As$'
  - '^At$'
  - '^In$'
  - '^The$'
  - '^To$'

# When renaming files, anything matching these patterns will be left untouched
skip_capitalization:
  - '\.meta'
  - '\.image'

# These patterns will be removed from the RSS feed
censor_rss_patterns:
  - pattern: 'token-[^&"\s]+'
    replacement: ''
    flags:
      - IGNORECASE
  - pattern: '\d+/patreon-media/p/post/\d+/\w+/\w+%3D%3D/'
    replacement: ''
    flags:
      - IGNORECASE
  - pattern: '\/([^\/?]+\.mp3)'
    replacement: '/obfuscated.mp3'
    flags:
      - IGNORECASE

# The pattern to match the episode number
episode_pattern: '(Ep\.?|Episode|E|Part)(\s*)(\d+)'

# the pattern to match date strings
date_pattern: '\b(\d{4}-\d{2}-\d{2})\b'

# How to prefix the episode number if dates are conflicting
conflicing_dates_replacement: '{prefix} - {date} Ep. {episode} - {suffix}'

# Gets a clean name from the folder name
clean_name: '^(.*?)(?=\()'

## Templates
# The template for the name to use in the report
name_template_file: name

# The template for the links themselves
link_template: "[url={{ link }}]{{ text }}[/url]"

# The template for the links section
links_section_template: |
  [b]Links[/b]
  {{ links }}

# The template for the report
template_file: default

## Database settings
# The database file to use
database:
  active: true # Whether to use the database
  file: ./podcasts.db # The database file

## Logging settings
# The log level for the application
log_level: WARNING

# The maximum size of the log file in MB
logfile_size_mb: 1

# The number of log files to keep
logfile_count: 5