settings.py

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

BOT_NAME = 'opentable'

SPIDER_MODULES = ['opentable.spiders']
NEWSPIDER_MODULE = 'opentable.spiders'

SPLASH_URL = 'http://localhost:8050/'

DOWNLOADER_MIDDLEWARES = {
    'scrapy_splash.SplashCookiesMiddleware'                                 : 723,
    'scrapy_splash.SplashMiddleware'                                        : 725,
    'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
    # 'scrapy.downloadermiddleware.useragent.UserAgentMiddleware'             : None,
    'random_useragent.RandomUserAgentMiddleware'                            : 400
}

SPIDER_MIDDLEWARES = {
    'opentable.middlewares.OpentableSpiderMiddleware': 543,
    'scrapy_splash.SplashDeduplicateArgsMiddleware'  : 100,
}

DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter'

HTTPCACHE_STORAGE = 'scrapy_splash.SplashAwareFSCacheStorage'

# Obey robots.txt rules
ROBOTSTXT_OBEY = True

# 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://doc.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',
# }

CONCURRENT_REQUESTS = 1
# Enable or disable extensions
# See https://doc.scrapy.org/en/latest/topics/extensions.html
# EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
# }

# Configure item pipelines
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
# ITEM_PIPELINES = {
#    'opentable.pipelines.OpentablePipeline': 300,
# }

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://doc.scrapy.org/en/latest/topics/autothrottle.html
# AUTOTHROTTLE_ENABLED = True
# The initial download delay
# AUTOTHROTTLE_START_DELAY = 1
# The maximum download delay to be set in case of high latencies
# AUTOTHROTTLE_MAX_DELAY = 10
# 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 = True

# Enable and configure HTTP caching (disabled by default)
# See https://doc.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'

# EXTENSIONS = {
#     'opentable.extensions.MonitorDownloadsExtension': 100,
#     'opentable.extensions.DumpStatsExtension'       : 101,
#     'scrapy.extensions.logstats.LogStats'           : 500,
# }

LOG_LEVEL = 'DEBUG'
LOG_FILE = 'spider.log'

USER_AGENT_LIST = "opentable/user_agents.txt"