scrapy-redis 实操应用----以4k风景为例

首先，在终端打开redis数据库！

第一种（单机爬虫）创建命令：scrapy genspider -t crawl bizhi netbian.com

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule


class BizhiSpider(CrawlSpider):
    name = 'bizhi'
    allowed_domains = ['netbian.com']
    start_urls = ['http://pic.netbian.com/4kfengjing/']

    page_link = LinkExtractor(allow='http://pic.netbian.com/4kfengjing/index_2.html')

    rules = (
        Rule(page_link, callback='get_detail', follow=True),
    )

    def get_detail(self,response):
        print('--------------------')
        li_list = response.xpath('//div[@class="slist"]/ul/li')
        # print(li_list)
        for li in li_list:

            img = li.xpath('.//a/img/@src').extract_first('')
            print(img)

            title =li.xpath('.//a/b/text()').extract_first('')
            print(title)

settings里面设置如下：

ITEM_PIPELINES = {
   'bizhispider.pipelines.BizhispiderPipeline': 300,
    'scrapy_redis.pipelines.RedisPipeline': 400,
}

#添加这两句代码
DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
# 使用scrapy_redis的调度器，不使用scrapy默认的调度器
SCHEDULER = "scrapy_redis.scheduler.Scheduler"

终端运行命令：scrapy crawl bizhi  即可

第二种（分布式）命令：scrapy genspider fengjing  netbian.com

import scrapy
#引入
from scrapy_redis.spiders import RedisCrawlSpider
#两者选其一
#from scrapy_redis.spiders import RedisSpider，Rule

#继承RedisCrawlSpider
class FengjingSpider(RedisCrawlSpider):
    name = 'fengjing'
    allowed_domains = ['netbian.com']

    # start_urls = ['http://pic.netbian.com/4kfengjing/index_3.html']

    redis_key = 'fengjingspider:start_urls'

    #规则
   #rules = (
     #   Rule(page_link, callback='parse', follow=True),
   # )

    def parse(self, response):
        print('--------------------')
        li_list = response.xpath('//div[@class="slist"]/ul/li')
        # print(li_list)
        for li in li_list:
            img = li.xpath('.//a/img/@src').extract_first('')
            print(img)

            title = li.xpath('.//a/b/text()').extract_first('')
            print(title)

settings里面设置同上

终端运行命令：scrapy crawl fengjiang   等运行暂停后，打开一个新的cmd终端，输入命令：redis-cli 

然后输入命令：lpush + redis-key值 + 需要请求的url，程序即可继续运行。