Scrapy-Redis之RedisSpider与RedisCrawlSpider详解

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

BOT_NAME = 'dang_dang'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/71.0.3578.98 Safari/537.36'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False


######################################################
##############下面是Scrapy-Redis相关配置################
######################################################

# 指定Redis的主机名和端口
REDIS_HOST = 'localhost'
REDIS_PORT = 6379

# 调度器启用Redis存储Requests队列
SCHEDULER = "scrapy_redis.scheduler.Scheduler"

# 确保所有的爬虫实例使用Redis进行重复过滤
DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"

# 将Requests队列持久化到Redis，可支持暂停或重启爬虫
SCHEDULER_PERSIST = True

# Requests的调度策略，默认优先级队列
SCHEDULER_QUEUE_CLASS = 'scrapy_redis.queue.PriorityQueue'

# 将爬取到的items保存到Redis 以便进行后续处理
ITEM_PIPELINES = {
  'scrapy_redis.pipelines.RedisPipeline': 300
}

# -*- coding: utf-8 -*-
import scrapy
import re
import urllib
from copy import deepcopy
from scrapy_redis.spiders import RedisSpider


class DangdangSpider(RedisSpider):
  name = 'dangdang'
  allowed_domains = ['dangdang.com']
  redis_key = 'dangdang:book'
  pattern = re.compile(r"(http|https)://category.dangdang.com/cp(.*?).html", re.I)

  # def __init__(self, *args, **kwargs):
  #   # 动态定义可爬取的域范围
  #   domain = kwargs.pop('domain', '')
  #   self.allowed_domains = filter(None, domain.split(','))
  #   super(DangdangSpider, self).__init__(*args, **kwargs)

  def parse(self, response): # 从首页提取图书分类信息
    # 提取一级分类元素
    div_list = response.xpath("//div[@class='con flq_body']/div")
    for div in div_list:
      item = {}
      item["b_cate"] = div.xpath("./dl/dt//text()").extract()
      item["b_cate"] = [i.strip() for i in item["b_cate"] if len(i.strip()) > 0]
      # 提取二级分类元素
      dl_list = div.xpath("./div//dl[@class='inner_dl']")
      for dl in dl_list:
        item["m_cate"] = dl.xpath(".//dt/a/@title").extract_first()
        # 提取三级分类元素
        a_list = dl.xpath("./dd/a")
        for a in a_list:
          item["s_cate"] = a.xpath("./text()").extract_first()
          item["s_href"] = a.xpath("./@href").extract_first()
          if item["s_href"] is not None and self.pattern.match(item["s_href"]) is not None:
            yield scrapy.Request(item["s_href"], callback=self.parse_book_list,
                       meta={"item": deepcopy(item)})

  def parse_book_list(self, response): # 从图书列表页提取数据
    item = response.meta['item']
    li_list = response.xpath("//ul[@class='bigimg']/li")
    for li in li_list:
      item["book_img"] = li.xpath("./a[@class='pic']/img/@src").extract_first()
      if item["book_img"] == "images/model/guan/url_none.png":
        item["book_img"] = li.xpath("./a[@class='pic']/img/@data-original").extract_first()
      item["book_name"] = li.xpath("./p[@class='name']/a/@title").extract_first()
      item["book_desc"] = li.xpath("./p[@class='detail']/text()").extract_first()
      item["book_price"] = li.xpath(".//span[@class='search_now_price']/text()").extract_first()
      item["book_author"] = li.xpath("./p[@class='search_book_author']/span[1]/a/text()").extract_first()
      item["book_publish_date"] = li.xpath("./p[@class='search_book_author']/span[2]/text()").extract_first()
      if item["book_publish_date"] is not None:
        item["book_publish_date"] = item["book_publish_date"].replace('/', '')
      item["book_press"] = li.xpath("./p[@class='search_book_author']/span[3]/a/text()").extract_first()
      yield deepcopy(item)

    # 提取下一页地址
    next_url = response.xpath("//li[@class='next']/a/@href").extract_first()
    if next_url is not None:
      next_url = urllib.parse.urljoin(response.url, next_url)
      yield scrapy.Request(next_url, callback=self.parse_book_list, meta={"item": item})

lpush dangdang:book http://book.dangdang.com/

# -*- coding: utf-8 -*-
import scrapy
import re
import urllib
from copy import deepcopy
from scrapy.spiders import CrawlSpider, Rule
from scrapy.linkextractors import LinkExtractor
from scrapy_redis.spiders import RedisCrawlSpider


class DangdangCrawler(RedisCrawlSpider):
  name = 'dangdang2'
  allowed_domains = ['dangdang.com']
  redis_key = 'dangdang:book'
  pattern = re.compile(r"(http|https)://category.dangdang.com/cp(.*?).html", re.I)

  rules = (
    Rule(LinkExtractor(allow=r'(http|https)://category.dangdang.com/cp(.*?).html'), callback='parse_book_list',
       follow=False),
  )

  def parse_book_list(self, response): # 从图书列表页提取数据
    item = {}
    item['book_list_page'] = response._url
    li_list = response.xpath("//ul[@class='bigimg']/li")
    for li in li_list:
      item["book_img"] = li.xpath("./a[@class='pic']/img/@src").extract_first()
      if item["book_img"] == "images/model/guan/url_none.png":
        item["book_img"] = li.xpath("./a[@class='pic']/img/@data-original").extract_first()
      item["book_name"] = li.xpath("./p[@class='name']/a/@title").extract_first()
      item["book_desc"] = li.xpath("./p[@class='detail']/text()").extract_first()
      item["book_price"] = li.xpath(".//span[@class='search_now_price']/text()").extract_first()
      item["book_author"] = li.xpath("./p[@class='search_book_author']/span[1]/a/text()").extract_first()
      item["book_publish_date"] = li.xpath("./p[@class='search_book_author']/span[2]/text()").extract_first()
      if item["book_publish_date"] is not None:
        item["book_publish_date"] = item["book_publish_date"].replace('/', '')
      item["book_press"] = li.xpath("./p[@class='search_book_author']/span[3]/a/text()").extract_first()
      yield deepcopy(item)

    # 提取下一页地址
    next_url = response.xpath("//li[@class='next']/a/@href").extract_first()
    if next_url is not None:
      next_url = urllib.parse.urljoin(response.url, next_url)
      yield scrapy.Request(next_url, callback=self.parse_book_list)