python-scrapy-增量式

标签：crawl   false   pytho   允许   管道   pid   The   art   lse   

movie.py

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from zlsPro.items import ZlsproItem
from redis import Redis

class MovieSpider(CrawlSpider):
    name = ‘movie‘
    start_urls = [‘https://www.4567kan.com/index.php/vod/show/id/1.html‘]
    rules = (
        Rule(LinkExtractor(allow=r‘/index\.php/vod/show/id/1/page/\d+\.html‘), callback=‘parse_item‘, follow=True),
    )
    coon = Redis(host=‘127.0.0.1‘,port=6379)
    def parse_item(self, response):
        li_list = response.xpath(‘//div[1]/div/div/div/div[2]/ul/li‘)
        for li in li_list:
            title = li.xpath(‘./div/div/h4/a/text()‘)[0].extract()
            href = ‘https://www.4567kan.com‘ + li.xpath(‘./div/div/h4/a/@href‘)[0].extract()
            item = ZlsproItem()
            item[‘title‘] = title
            item[‘href‘] = href
            ex = self.coon.sadd(‘movie_url‘,href)
            if ex == 1:
                print(‘有新增‘)
                yield scrapy.Request(url=href,callback=self.parse_href,meta={‘item‘: item})
            else:
                print(‘暂无新增‘)

    def parse_href(self,response):
        detail = response.xpath(‘/html/body/div[1]/div/div/div/div[2]/p[5]/span[2]/text()‘).extract_first()
        item = response.meta[‘item‘]
        item[‘detail‘] = detail
        yield item

settings.py

USER_AGENT = ‘Mozilla/5.0 (Macintosh; Intel Mac OS X 10_12_0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/68.0.3440.106 Safari/537.36‘
ROBOTSTXT_OBEY = False
LOG_LEVEL = ‘ERROR‘

# 使用scrapy-redis组件的去重队列
DUPEFILTER_CLASS = "scrapy_redis.dupefilter.RFPDupeFilter"
# 使用scrapy-redis组件自己的调度器
SCHEDULER = "scrapy_redis.scheduler.Scheduler"
# 是否允许暂停
SCHEDULER_PERSIST = True
# 指定管道
ITEM_PIPELINES = {
    ‘scrapy_redis.pipelines.RedisPipeline‘: 400
}
# 指定数据库
REDIS_HOST = ‘127.0.0.1‘
REDIS_PORT = 6379

items.py

import scrapy
class ZlsproItem(scrapy.Item):
    # define the fields for your item here like:
    title = scrapy.Field()
    href = scrapy.Field()
    detail = scrapy.Field()
运行项目 scrapy crawl movie

python-scrapy-增量式

标签：crawl   false   pytho   允许   管道   pid   The   art   lse   

原文地址：https://www.cnblogs.com/shiyi525/p/14286167.html