config.yml

defintions:
  seasons: [2012, 2013, 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022, 2023, 2024]
  console_handler: &console_handler
    class: logging.StreamHandler
    level: INFO
    stream: ext://sys.stdout
    formatter: console
  file_handler: &file_handler
    class: logging.FileHandler
    level: DEBUG
    filename: logs/run.log
    mode: w
    formatter: file
  console_formatter: &console_formatter
    format: '%(asctime)s [%(levelname)s]: %(message)s'
  file_formatter: &file_formatter
    format: '%(asctime)s [%(levelname)s] %(pathname)s: %(message)s'

acquire:
  scrapy_config:
    USER_AGENT: transfermarkt-datasets/1.0 (https://github.com/dcaribou/transfermarkt-datasets)
    FEED_URI_PARAMS: tfmkt.utils.uri_params
    FEEDS:
      "data/raw/transfermarkt-scraper/%(season)s/%(name)s.json.gz":
        format: jsonlines
        postprocessing: [scrapy.extensions.postprocessing.GzipPlugin]
    SPIDER_MODULES: ['tfmkt']
    REQUEST_FINGERPRINTER_IMPLEMENTATION: '2.7'
    HTTPCACHE_ENABLED: True
  logging:
    version: 1
    disable_existing_loggers: False
    loggers:
      "": # root logger
        handlers: [console, file]
        level: DEBUG
      # from https://docs.scrapy.org/en/latest/_modules/scrapy/utils/log.html#configure_logging
      hpack:
        level: ERROR
        handlers: [console, file]
      scrapy:
        level: DEBUG
        handlers: [file]
      twisted:
        level: ERROR
        handlers: [console, file]
    handlers:
      console: *console_handler
      file:
        <<: *file_handler
        filename: logs/acquire.log
    formatters:
      console: *console_formatter
      file: *file_formatter