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 = 16

# 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 = 16
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': 200,
    'hg3535.middlewares.Hg3535timeoutDownloaderMiddleware': 200,
    'scrapy.downloadermiddlewares.downloadtimeout.DownloadTimeoutMiddleware': 500,
    # 'scrapy.contrib.downloadermiddleware.retry.RetryMiddleware': 502,

}

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

# Configure item pipeline
# See https://doc.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {}

# 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'
# DOWNLOAD_TIMEOUT = 180

REACTOR_THREADPOOL_MAXSIZE = 40
# LOG_LEVEL = 'INFO'
COOKIES_ENABLED = False
RETRY_ENABLED = False
DOWNLOAD_TIMEOUT = 10
REDIRECT_ENABLED = False
CONCURRENT_ITEMS = 1000
# SCHEDULER_PERSIST = False  # 是否在关闭时候保留原来的调度器和去重记录，True=保留，False=清空
# SCHEDULER_FLUSH_ON_START = False
# TELNETCONSOLE_PORT = None
# TELNETCONSOLE_ENABLED=False
# AttributeError: 'TelnetConsole' object has no attribute 'port'

# RETRY_ENABLED = True
# RETRY_TIMES = 2
# RETRY_HTTP_CODES = [500, 502, 503, 504, 400, 408]

# LOG_LEVEL = 'DEBUG'
# SCHEDULER_PERSIST = False
# LOG_FILE = './log/'

# upMatch
# POST_HOST = 'localhost'
# POST_DATABASE = 'kaiyou'
# POST_USER = 'kaiyou'
# POST_PORT = '10432'
# POST_PASSWORD = '123456'
# SCHEDULER = "scrapy_redis.scheduler.Scheduler"
# DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
# SCHEDULER_SERIALIZER = "scrapy_redis.picklecompat"
# ＃不要清理redis队列，允许暂停/恢复抓取。
# SCHEDULER_PERSIST = False
# ＃使用优先级队列安排请求。（默认）
# SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.PriorityQueue'
# REDIS_HOST = '192.168.2.200'
# REDIS_PORT = 6379
# REDIS_PARAMS = {'password': 123456, 'db': 1}
# 随机等待
# RANDOMIZE_DOWNLOAD_DELAY = True
# # AutoThrottle扩展
# AUTOTHROTTLE_ENABLED = True
# AUTOTHROTTLE_DEBUG = True
# AUTOTHROTTLE_TARGET_CONCURRENCY = 0.25
# AUTOTHROTTLE_MAX_DELAY = 5
# SCHEDULER = "scrapy_redis.scheduler.Scheduler"
# DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
# REDIS_URL = 'redis://:123456@192.168.2.200:6379'
# SCHEDULER_PERSIST = False

# mongo
M_HOST = '192.168.2.200'
M_POST = 27017
M_USER = 'kaiyou'
M_DB = 'kaiyou'
M_PASSWORD = 'kaiyou'

# redis
R_HOST = '192.168.2.200'
R_POST = 6379
R_DB = 1
R_PASSWORD = 123456

# token
T_USER = 'python'
T_PASSWORD = 'python888'
T_URL = 'http://stadmin.bocai108.com/getToken'


# 域名
POST_URL = 'http://stadmin.bocai108.com:19093'