118 lines
4.4 KiB
Python
118 lines
4.4 KiB
Python
# Scrapy settings for raena_crawler 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 = "raena_crawler"
|
|
|
|
SPIDER_MODULES = ["raena_crawler.spiders"]
|
|
NEWSPIDER_MODULE = "raena_crawler.spiders"
|
|
|
|
|
|
# Crawl responsibly by identifying yourself (and your website) on the user-agent
|
|
#USER_AGENT = "raena_crawler (+http://www.yourdomain.com)"
|
|
|
|
# Obey robots.txt rules
|
|
ROBOTSTXT_OBEY = True
|
|
|
|
# Configure maximum concurrent requests performed by Scrapy (default: 16)
|
|
CONCURRENT_REQUESTS = 10
|
|
|
|
# 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 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
|
|
|
|
# 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 = {
|
|
# "raena_crawler.middlewares.RaenaCrawlerSpiderMiddleware": 543,
|
|
#}
|
|
|
|
# Enable or disable downloader middlewares
|
|
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
|
|
#DOWNLOADER_MIDDLEWARES = {
|
|
# "raena_crawler.middlewares.RaenaCrawlerDownloaderMiddleware": 543,
|
|
#}
|
|
|
|
# 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 = {
|
|
'raena_crawler.pipelines.OliveYoungPipeline': 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"
|
|
|
|
# Set settings whose default value is deprecated to a future-proof value
|
|
REQUEST_FINGERPRINTER_IMPLEMENTATION = "2.7"
|
|
TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"
|
|
FEED_EXPORT_ENCODING = "utf-8"
|
|
|
|
SPLASH_URL = 'http://localhost:8050'
|
|
DOWNLOADER_MIDDLEWARES = {
|
|
'scrapy_splash.SplashCookiesMiddleware': 723,
|
|
'scrapy_splash.SplashMiddleware': 725,
|
|
'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware': None,
|
|
'scrapy.downloadermiddlewares.retry.RetryMiddleware': None,
|
|
'scrapy_fake_useragent.middleware.RandomUserAgentMiddleware': 400,
|
|
'scrapy_fake_useragent.middleware.RetryUserAgentMiddleware': 401,
|
|
'rotating_proxies.middlewares.RotatingProxyMiddleware': 610,
|
|
'rotating_proxies.middlewares.BanDetectionMiddleware': 620,
|
|
}
|
|
SPIDER_MIDDLEWARES = {
|
|
'scrapy_splash.SplashDeduplicateArgsMiddleware': 100,
|
|
}
|
|
DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter'
|
|
|
|
FAKEUSERAGENT_PROVIDERS = [
|
|
'scrapy_fake_useragent.providers.FakeUserAgentProvider', # This is the first provider we'll try
|
|
'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 (iPad; CPU OS 12_2 like Mac OS X) AppleWebKit/605.1.15 (KHTML, like Gecko) Mobile/15E148'
|