ImmoScrap/ImmoScrap/settings.py

107 lines
4.0 KiB
Python

# Scrapy settings for ImmoScrap 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
BOT_NAME = 'ImmoScrap'
SPIDER_MODULES = ['ImmoScrap.spiders']
NEWSPIDER_MODULE = 'ImmoScrap.spiders'
LOG_LEVEL = 'WARNING'
FEEDS = {
'export.jsonl': {
'format': 'jsonlines'
}
}
# Crawl responsibly by identifying yourself (and your website) on the user-agent
# USER_AGENT = 'ImmoScrap (+http://www.yourdomain.com)'
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
# Configure maximum concurrent requests performed by Scrapy (default: 16)
# CONCURRENT_REQUESTS = 32
# 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 = 5 # Beetween 2.5 and 7.5 seconds : RANDOMIZE_DOWNLOAD_DELAY enabled by default
# The download delay setting will honor only one of:
# CONCURRENT_REQUESTS_PER_DOMAIN = 16
# CONCURRENT_REQUESTS_PER_IP = 16
# Disable cookies (enabled by default)
COOKIES_ENABLED = False # Some sites may use cookies to spot bot behaviour
# 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 = {
# 'ImmoScrap.middlewares.ImmoscrapSpiderMiddleware': 543,
# }
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
# Custom middleware to rotate User-Agents:
DOWNLOADER_MIDDLEWARES = {
'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware': None,
'scrapy.downloadermiddlewares.retry.RetryMiddleware': None,
'scrapy_fake_useragent.middleware.RandomUserAgentMiddleware': 400,
'scrapy_fake_useragent.middleware.RetryUserAgentMiddleware': 401,
}
FAKEUSERAGENT_PROVIDERS = [
# 'scrapy_fake_useragent.providers.FakeUserAgentProvider', # Depends on http://useragentstring.com which is currently down
'scrapy_fake_useragent.providers.FakerProvider', # if FakeUserAgentProvider fails, we'll use faker to generate a user-agent string for us
'scrapy_fake_useragent.providers.FixedUserAgentProvider', # fall back to USER_AGENT value
]
USER_AGENT = 'Mozilla/5.0 (X11; Linux x86_64; rv:79.0) Gecko/20100101 Firefox/79.0' # Fallback value
# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
EXTENSIONS = {
'scrapy.extensions.telnet.TelnetConsole': None
}
# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
'ImmoScrap.pipelines.PricePerSqmPipeline': 300,
}
# 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'