|
|
# -*- coding: utf-8 -*-
|
|
|
|
|
|
# Scrapy settings for tencent project
|
|
|
#
|
|
|
# For simplicity, this file contains only settings considered important or
|
|
|
# commonly used. You can find more settings consulting the documentation:
|
|
|
#
|
|
|
# https://docs.scrapy.org/en/latest/topics/settings.html
|
|
|
# https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
|
|
|
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
|
|
|
|
|
|
BOT_NAME = 'tencent'
|
|
|
|
|
|
SPIDER_MODULES = ['tencent.spiders']
|
|
|
NEWSPIDER_MODULE = 'tencent.spiders'
|
|
|
|
|
|
# LOG_LEVEL = 'WARNING'
|
|
|
# Crawl responsibly by identifying yourself (and your website) on the user-agent
|
|
|
#USER_AGENT = 'tencent (+http://www.yourdomain.com)'
|
|
|
USER_AGENT = 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'
|
|
|
|
|
|
|
|
|
SCHEDULER = "scrapy_redis.scheduler.Scheduler"
|
|
|
|
|
|
DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
|
|
|
|
|
|
SCHEDULER_PERSIST = True
|
|
|
# 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://docs.scrapy.org/en/latest/topics/settings.html#download-delay
|
|
|
# See also autothrottle settings and docs
|
|
|
DOWNLOAD_DELAY = 0.5
|
|
|
# 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',
|
|
|
#}
|
|
|
|
|
|
# Enable or disable spider middlewares
|
|
|
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
|
|
|
#SPIDER_MIDDLEWARES = {
|
|
|
# 'tencent.middlewares.TencentSpiderMiddleware': 543,
|
|
|
#}
|
|
|
|
|
|
# Enable or disable downloader middlewares
|
|
|
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
|
|
|
DOWNLOADER_MIDDLEWARES = {
|
|
|
'tencent.middlewares.TencentDownloaderMiddleware': 543,
|
|
|
'tencent.middlewares.RandomUserAgentMiddlware': 333,
|
|
|
}
|
|
|
|
|
|
# Enable or disable extensions
|
|
|
# See https://docs.scrapy.org/en/latest/topics/extensions.html
|
|
|
#EXTENSIONS = {
|
|
|
# 'scrapy.extensions.telnet.TelnetConsole': None,
|
|
|
#}
|
|
|
|
|
|
# Configure item pipelines
|
|
|
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
|
|
|
ITEM_PIPELINES = {
|
|
|
'tencent.pipelines.TencentPipeline': 300,
|
|
|
'scrapy_redis.pipelines.RedisPipeline':400,
|
|
|
}
|
|
|
|
|
|
# Enable and configure the AutoThrottle extension (disabled by default)
|
|
|
# See https://docs.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://docs.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'
|
|
|
|
|
|
REDIS_HOST = '127.0.0.1' # 主机名
|
|
|
REDIS_PORT = 6379
|
|
|
# 启用 Scrapy-Redis 调度存储请求队列
|
|
|
#SCHEDULER = "scrapy_redis.scheduler.Scheduler"
|
|
|
|
|
|
# 去重规则对应处理的类
|
|
|
#DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
|
|
|
|
|
|
# 对保存到 redis 中的数据进行序列化，默认使用pickle
|
|
|
# SCHEDULER_SERIALIZER = "scrapy_redis.picklecompat"
|
|
|
|
|
|
# 不清除 Redis 队列，即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。这样可以暂停/恢复 爬取
|
|
|
#SCHEDULER_PERSIST = True
|
|
|
|
|
|
# 是否在开始之前清空 调度器和去重记录，True=清空，False=不清空
|
|
|
# SCHEDULER_FLUSH_ON_START = True
|
|
|
|
|
|
#DEPTH_PRIORITY = 1 # 广度优先
|
|
|
# DEPTH_PRIORITY = -1 # 深度优先
|
|
|
# 使用优先级调度请求队列 （默认使用）
|
|
|
#SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.PriorityQueue'
|
|
|
HTTPERROR_ALLOWED_CODES = [500]
|
|
|
|
|
|
|
