2020-07-02 08:40:13 +02:00
|
|
|
# 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'
|
2020-08-16 01:26:33 +02:00
|
|
|
LOG_LEVEL = 'WARNING'
|
2020-07-02 08:40:13 +02:00
|
|
|
|
2020-08-16 17:33:24 +02:00
|
|
|
FEEDS = {
|
2021-12-12 21:58:25 +01:00
|
|
|
'export.jsonl': {
|
|
|
|
'format': 'jsonlines'
|
2020-08-16 17:33:24 +02:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2020-07-02 08:40:13 +02:00
|
|
|
|
|
|
|
# Crawl responsibly by identifying yourself (and your website) on the user-agent
|
2020-08-16 01:13:20 +02:00
|
|
|
# USER_AGENT = 'ImmoScrap (+http://www.yourdomain.com)'
|
2020-07-02 08:40:13 +02:00
|
|
|
|
|
|
|
# Obey robots.txt rules
|
|
|
|
ROBOTSTXT_OBEY = False
|
|
|
|
|
|
|
|
# Configure maximum concurrent requests performed by Scrapy (default: 16)
|
2020-08-16 01:13:20 +02:00
|
|
|
# CONCURRENT_REQUESTS = 32
|
2020-07-02 08:40:13 +02:00
|
|
|
|
|
|
|
# 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
|
2021-12-12 21:58:25 +01:00
|
|
|
DOWNLOAD_DELAY = 5 # Beetween 2.5 and 7.5 seconds : RANDOMIZE_DOWNLOAD_DELAY enabled by default
|
2020-07-02 08:40:13 +02:00
|
|
|
# The download delay setting will honor only one of:
|
2020-08-16 01:13:20 +02:00
|
|
|
# CONCURRENT_REQUESTS_PER_DOMAIN = 16
|
|
|
|
# CONCURRENT_REQUESTS_PER_IP = 16
|
2020-07-02 08:40:13 +02:00
|
|
|
|
|
|
|
# Disable cookies (enabled by default)
|
2020-08-16 01:23:04 +02:00
|
|
|
COOKIES_ENABLED = False # Some sites may use cookies to spot bot behaviour
|
2020-07-02 08:40:13 +02:00
|
|
|
|
|
|
|
# Disable Telnet Console (enabled by default)
|
2020-08-16 01:13:20 +02:00
|
|
|
# TELNETCONSOLE_ENABLED = False
|
2020-07-02 08:40:13 +02:00
|
|
|
|
|
|
|
# Override the default request headers:
|
2020-08-16 01:13:20 +02:00
|
|
|
# DEFAULT_REQUEST_HEADERS = {
|
2020-07-02 08:40:13 +02:00
|
|
|
# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
|
|
|
|
# 'Accept-Language': 'en',
|
2020-08-16 01:13:20 +02:00
|
|
|
# }
|
2020-07-02 08:40:13 +02:00
|
|
|
|
|
|
|
# Enable or disable spider middlewares
|
|
|
|
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
|
2020-08-16 01:13:20 +02:00
|
|
|
# SPIDER_MIDDLEWARES = {
|
2020-07-02 08:40:13 +02:00
|
|
|
# 'ImmoScrap.middlewares.ImmoscrapSpiderMiddleware': 543,
|
2020-08-16 01:13:20 +02:00
|
|
|
# }
|
2020-07-02 08:40:13 +02:00
|
|
|
|
|
|
|
# Enable or disable downloader middlewares
|
|
|
|
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
|
2020-08-16 01:13:20 +02:00
|
|
|
|
|
|
|
# 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
|
2020-07-02 08:40:13 +02:00
|
|
|
|
|
|
|
# Enable or disable extensions
|
|
|
|
# See https://docs.scrapy.org/en/latest/topics/extensions.html
|
2020-08-12 22:52:17 +02:00
|
|
|
EXTENSIONS = {
|
|
|
|
'scrapy.extensions.telnet.TelnetConsole': None
|
|
|
|
}
|
2020-07-02 08:40:13 +02:00
|
|
|
|
|
|
|
# Configure item pipelines
|
|
|
|
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
|
2020-08-16 18:10:59 +02:00
|
|
|
ITEM_PIPELINES = {
|
|
|
|
'ImmoScrap.pipelines.PricePerSqmPipeline': 300,
|
|
|
|
}
|
2020-07-02 08:40:13 +02:00
|
|
|
|
|
|
|
# Enable and configure the AutoThrottle extension (disabled by default)
|
|
|
|
# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
|
2020-08-16 01:13:20 +02:00
|
|
|
# AUTOTHROTTLE_ENABLED = True
|
2020-07-02 08:40:13 +02:00
|
|
|
# The initial download delay
|
2020-08-16 01:13:20 +02:00
|
|
|
# AUTOTHROTTLE_START_DELAY = 5
|
2020-07-02 08:40:13 +02:00
|
|
|
# The maximum download delay to be set in case of high latencies
|
2020-08-16 01:13:20 +02:00
|
|
|
# AUTOTHROTTLE_MAX_DELAY = 60
|
2020-07-02 08:40:13 +02:00
|
|
|
# The average number of requests Scrapy should be sending in parallel to
|
|
|
|
# each remote server
|
2020-08-16 01:13:20 +02:00
|
|
|
# AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
|
2020-07-02 08:40:13 +02:00
|
|
|
# Enable showing throttling stats for every response received:
|
2020-08-16 01:13:20 +02:00
|
|
|
# AUTOTHROTTLE_DEBUG = False
|
2020-07-02 08:40:13 +02:00
|
|
|
|
|
|
|
# Enable and configure HTTP caching (disabled by default)
|
|
|
|
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
|
2020-08-16 01:13:20 +02:00
|
|
|
# HTTPCACHE_ENABLED = True
|
|
|
|
# HTTPCACHE_EXPIRATION_SECS = 0
|
|
|
|
# HTTPCACHE_DIR = 'httpcache'
|
|
|
|
# HTTPCACHE_IGNORE_HTTP_CODES = []
|
|
|
|
# HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'
|