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

# Scrapy settings for letecky_rejstrik project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     http://doc.scrapy.org/en/latest/topics/settings.html
#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html

#BOT_NAME = 'letecky_rejstrik'

# SPIDER_MODULES = ['letecky_rejstrik']
# NEWSPIDER_MODULE = 'letecky_rejstrik'

# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'letecky_rejstrik (+http://www.yourdomain.com)'

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

# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
DOWNLOAD_DELAY=0
# The download delay setting will honor only one of:
CONCURRENT_REQUESTS_PER_DOMAIN=1
CONCURRENT_REQUESTS_PER_IP=1

# 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',
#}


DOWNLOADER_MIDDLEWARES = {
        'scrapy.contrib.downloadermiddleware.httpcompression.HttpCompressionMiddleware':None, # to avoid the raise IOError, 'Not a gzipped file' exceptions.IOError: Not a gzipped file
        'scrapy.contrib.downloadermiddleware.useragent.UserAgentMiddleware' : None,
#        'reviews.rotate_useragent.RotateUserAgentMiddleware' :400,
        'scrapy.contrib.downloadermiddleware.httpproxy.HttpProxyMiddleware': 110, 
        #'reviews.middlewares.ProxyMiddleware': 100,
    }

PROXIES = [{'ip_port': '168.63.249.35:80', 'user_pass': ''},
           {'ip_port': '162.17.98.242:8888', 'user_pass': ''},
           {'ip_port': '70.168.108.216:80', 'user_pass': ''},
           {'ip_port': '45.64.136.154:8080', 'user_pass': ''},
           {'ip_port': '149.5.36.153:8080', 'user_pass': ''},
           {'ip_port': '185.12.7.74:8080', 'user_pass': ''},
           {'ip_port': '150.129.130.180:8080', 'user_pass': ''},
           {'ip_port': '185.22.9.145:8080', 'user_pass': ''},
           {'ip_port': '200.20.168.135:80', 'user_pass': ''},
           {'ip_port': '177.55.64.38:8080', 'user_pass': ''},]
#    'scrapy.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
#ITEM_PIPELINES = {
#    'letecky_rejstrik.pipelines.SomePipeline': 300,
#}

# Enable and configure the AutoThrottle extension (disabled by default)
# See http://doc.scrapy.org/en/latest/topics/autothrottle.html
# NOTE: AutoThrottle will honour the standard settings for concurrency and delay
AUTOTHROTTLE_ENABLED=False
# The initial download delay
AUTOTHROTTLE_START_DELAY=5
# The maximum download delay to be set in case of high latencies
AUTOTHROTTLE_MAX_DELAY=60
# Enable showing throttling stats for every response received:
AUTOTHROTTLE_DEBUG=False

# Enable and configure HTTP caching (disabled by default)
# See http://scrapy.readthedocs.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'

FEED_EXPORTERS = { "turtle": 'turtle_exporter.TurtleExporter' }