spider/elabSpider/settings.py

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

# Scrapy settings for elabSpider 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 = 'elabSpider'

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

# MONGO_HOST = '139.196.5.59'  #测试环境
# MONGO_HOST = '139.196.108.59'    #正式环境，已废弃
# MONGO_HOST = 'mongodb://logdb:logdb@dds-uf6da0fedc9881d41450-pub.mongodb.rds.aliyuncs.com:3717,dds-uf6da0fedc9881d42459-pub.mongodb.rds.aliyuncs.com:3717/logdb?replicaSet=mgset-12835903'
MONGO_HOST = 'mongodb://logdb:logdb@dds-uf6da0fedc9881d41154-pub.mongodb.rds.aliyuncs.com:3717,dds-uf6da0fedc9881d42456-pub.mongodb.rds.aliyuncs.com:3717/logdb?replicaSet=mgset-12835903'
MONGO_PORT = 27017
MONGO_DB = 'logdb'
MONGO_COLL = 'ershoufang'
MONGO_USER = 'dbuser'
MONGO_PSW = 'elab@123'

PROXY_HOST = 'http://http-dyn.abuyun.com'
PROXY_PORT = '9020'
# PROXY_IDENTIFY = 'HY39548V0FZ45UKD'
# PROXY_SECRETKEY = '07DBA6C5E470150B'

USER_AGENT_PATH = 'fake_useragent.json'

# LOG_FILE = 'spider.log'


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

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# 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 = 5

# Disable cookies (enabled by default)
COOKIES_ENABLED = False

# COOKIES_DEBUG = True

# 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
#SPIDER_MIDDLEWARES = {
#    'elabSpider.middlewares.ElabspiderSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html

DOWNLOADER_MIDDLEWARES = {
   'elabSpider.middlewares.UserAgent': 1,
   # 'elabSpider.middlewares.TooManyRequestsRetryMiddleware': 500,
   'elabSpider.middlewares.ElabspiderDownloaderMiddleware': 543,
   'scrapy.downloadermiddlewares.httpproxy.HttpProxyMiddleware': 550,
   'scrapy.downloadermiddlewares.useragent.UserAgentMiddleware': None,
   'scrapy.downloadermiddlewares.defaultheaders.DefaultHeadersMiddleware': None,
   'scrapy.spidermiddlewares.offsite.OffsiteMiddleware': None,
   # 'scrapy.downloadermiddlewares.retry.RetryMiddleware': None

}

# 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 = {
   'elabSpider.pipelines.ElabspiderPipeline': 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 = 0.25
# 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 = 5.0
# 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'
REDIRECT_ENABLED = False
RETRY_ENABLED = True
RETRY_TIMES = 10
RETRY_HTTP_CODES = [403, 429, 404, 301, 302, 503]
HTTPERROR_ALLOWED_CODES = [403, 429, 404, 301, 302, 503]

DOWNLOAD_TIMEOUT = 15

# RANDOMIZE_DOWNLOAD_DELAY = False
# CONCURRENT_REQUESTS_PER_IP = 40