sports_scrapy/hg3535/settings.py

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

# Scrapy settings for hg3535 project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://doc.scrapy.org/en/latest/topics/settings.html
#     https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://doc.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'hg3535'

SPIDER_MODULES = ['hg3535.spiders']
NEWSPIDER_MODULE = 'hg3535.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = {
    'Mozilla/5.0 (Macintosh; Intel Mac OS X 10.8; rv:16.0) Gecko/20120813 Firefox/16.0'
}

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
CONCURRENT_REQUESTS = 64

# 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
DOWNLOAD_DELAY = 0
# The download delay setting will honor only one of:
CONCURRENT_REQUESTS_PER_DOMAIN = 32
CONCURRENT_REQUESTS_PER_IP = 0

# 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://doc.scrapy.org/en/latest/topics/spider-middleware.html
# from scrapy_deltafetch
# SPIDER_MIDDLEWARES = {
#    # 'scrapy_deltafetch.DeltaFetch': 100,
#    'hg3535.middlewares.Hg3535SpiderMiddleware': 543
# }
# #
# DELTAFETCH_ENABLED = True


# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
#    'hg3535.middlewares.Hg3535DownloaderMiddleware': 543,
# }

# 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 = {
   # 篮球
   'hg3535.pipelines.Lanqiupipeline': 300,
   # 冠军
   'hg3535.pipelines.Guanjunpipeline': 300,
   # 联赛
   'hg3535.pipelines.Liansaipipeline': 300,
   # 足球
   'hg3535.pipelines.Zuqiupipeline': 300,
   # 网球
   "hg3535.pipelines.Wangqiupipeline": 300,
   # 网球波胆
   'hg3535.pipelines.Wqbodanpipeline': 300,
   # 棒球让球&大小盘
   "hg3535.pipelines.Bangqiupipeline": 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 = 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://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'

POST_HOST = 'localhost'
POST_DATABASE = 'postgres'
POST_USER = 'postgres'
POST_PORT = '5433'
POST_PASSWORD = '123456'

R_HOST = 'localhost'
R_POST = '6379'
R_PASSWORD = '123456'

# POST_HOST = '192.168.2.200'
# POST_DATABASE = 'kaiyou'
# POST_USER = 'kaiyou'
# POST_PORT = '10432'
# POST_PASSWORD = '123456'