分布式爬虫参数设置

一、自身的spider.py设置

from scrapy_redis.spiders import RedisSpider


class MySpider(RedisSpider):
    redis_key = 'myspider:start_urls'

    def __init__(self, *args, **kwargs):
        domain = kwargs.pop('domain', '')            #当我们初始化爬虫时，如果定义了初始域名，
                                                     #则采用
        self.allowed_domains = filter(None, domain.split(','))  #对域名进行筛选
        super(MySpider, self).__init__(*args, **kwargs)

二、配置文件settings.py的设置

# Scrapy settings for example project
#
# For simplicity, this file contains only the most important settings by
# default. All the other settings are documented here:
#
#     http://doc.scrapy.org/topics/settings.html
#
SPIDER_MODULES = ['example.spiders']
NEWSPIDER_MODULE = 'example.spiders'

USER_AGENT = 'scrapy-redis (+https://github.com/rolando/scrapy-redis)'

DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"    #是否筛选
SCHEDULER = "scrapy_redis.scheduler.Scheduler"    #调度器
SCHEDULER_PERSIST = True                #断点续传
# SCHEDULER_QUEUE_CLASS = "scrapy_redis.queue.SpiderPriorityQueue"
# SCHEDULER_QUEUE_CLASS = "scrapy_redis.queue.SpiderQueue"
# SCHEDULER_QUEUE_CLASS = "scrapy_redis.queue.SpiderStack"

ITEM_PIPELINES = {
    'example.pipelines.ExamplePipeline': 300,
    'scrapy_redis.pipelines.RedisPipeline': 400,            /自动放到redis数据库
}

LOG_LEVEL = 'DEBUG'

# Introduce an artifical delay to make use of parallelism. to speed up the
# crawl.
DOWNLOAD_DELAY = 1

REDIS_URL = 'redis://127.0.0.1:6379'        #设置redis服务