open-contracting / kingfisher-collect / 46eccbf8bb6568c66b612265c597292d05f03f8a-PR-386

# -*- coding: utf-8 -*-

# Scrapy settings for kingfisher_scrapy project

#

# For simplicity, this file contains only settings considered important or

# commonly used. You can find more settings consulting the documentation:

#

#     https://docs.scrapy.org/en/latest/topics/settings.html

#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html

#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html

# Crawl responsibly by identifying yourself (and your website) on the user-agent

# Obey robots.txt rules

# Configure maximum concurrent requests performed by Scrapy (default: 16)

# Configure a delay for requests for the same website (default: 0)

# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay

# See also autothrottle settings and docs

#DOWNLOAD_DELAY = 3

# The maximum response size (in bytes) that downloader will download (default: 1073741824):

# The download delay setting will honor only one of:

#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)

#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)

#TELNETCONSOLE_ENABLED = False

# Override the default request headers:

#DEFAULT_REQUEST_HEADERS = {

#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',

#   'Accept-Language': 'en',

#}

# Enable or disable spider middlewares

# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html

#SPIDER_MIDDLEWARES = {

#    'kingfisher_scrapy.middlewares.MyCustomSpiderMiddleware': 543,

#}

# Enable or disable downloader middlewares

# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html

#DOWNLOADER_MIDDLEWARES = {

#    'kingfisher_scrapy.middlewares.MyCustomDownloaderMiddleware': 543,

#}

# Enable or disable extensions

# See https://docs.scrapy.org/en/latest/topics/extensions.html

#EXTENSIONS = {

#    'scrapy.extensions.telnet.TelnetConsole': None,

#}

    # `KingfisherFilesStore` must run before `KingfisherProcessAPI`, because the file needs to be written before the

    # request is sent to Kingfisher Process.

    'kingfisher_scrapy.extensions.KingfisherFilesStore': 100,

    'kingfisher_scrapy.extensions.KingfisherProcessAPI': 500,

    # before any other extension

    'kingfisher_scrapy.extensions.SentryLogging': -1,

}

# Configure item pipelines

# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html

#ITEM_PIPELINES = {

#    'kingfisher_scrapy.pipelines.KingfisherScrapyPipeline': 300,

#}

# To send the logs to sentry

# To send items to Kingfishet Process, set this to, for example, "http://kingfisher.example.com" (no trailing slash).

# Set this to the same value as Kingfisher Process' `API_KEYS` setting.

# See https://kingfisher-process.readthedocs.io/en/latest/config.html#web-api

# If Kingfisher Process can read Kingfisher Collect's `FILES_STORE`, then Kingfisher Collect can send file paths

# instead of files to Kingfisher Process' API. To enable that, set this to the absolute path to the `FILES_STORE`.

# To get an API account, visit https://contrataciones.gov.py/datos/signup

# To get an API account, contact contact@openopps.com.

# Enable and configure the AutoThrottle extension (disabled by default)

# See https://docs.scrapy.org/en/latest/topics/autothrottle.html

#AUTOTHROTTLE_ENABLED = True

# The initial download delay

#AUTOTHROTTLE_START_DELAY = 5

# The maximum download delay to be set in case of high latencies

#AUTOTHROTTLE_MAX_DELAY = 60

# The average number of requests Scrapy should be sending in parallel to

# each remote server

#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0

# Enable showing throttling stats for every response received:

#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)

# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings

#HTTPCACHE_ENABLED = True

#HTTPCACHE_EXPIRATION_SECS = 0

#HTTPCACHE_DIR = 'httpcache'

#HTTPCACHE_IGNORE_HTTP_CODES = []

#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

# https://docs.scrapy.org/en/latest/topics/media-pipeline.html#std:setting-FILES_STORE

# https://docs.scrapy.org/en/latest/topics/spider-middleware.html#httperror-allow-all

# https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpproxy-enabled

# Scrapyd won't have (and doesn't need) access to this module.

    # https://docs.scrapy.org/en/latest/topics/commands.html#commands-module