scrapy增量式爬虫

命令:

1.创建scrapy工程：scrapy startproject projectName
2.创建爬虫文件：scrapy genspider -t crawl spiderName www.xxx.com
　　指令多了 "-t crawl"，表示创建的爬虫文件是基于CrawlSpider这个类的，而不再是Spider这个基类。
3.运行 scrapy crawl spider2

spider.py

用hashlib来制作哈希值来放在Redis中, 可以减少放在Redis中的为了校验是否存在的内容

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from redis import Redis
from scrapy2.items import Scrapy2Item
import hashlib


class Spider2Spider(CrawlSpider):
    name = 'spider2'
    # allowed_domains = ['www.xxx.com']
    start_urls = ['https://www.qiushibaike.com/text/']

    rules = (
        Rule(LinkExtractor(allow=r'/text/page/\d+/'), callback='parse_item', follow=True),
    )

    def parse_item(self, response):
        div_list = response.xpath('//div[@class="article block untagged mb15 typs_hot"]')
        conn = Redis(host='127.0.0.1',port=6379)
        for div in div_list:
            item = Scrapy2Item()
            item['content'] = div.xpath('.//div[@class="content"]/span//text()').extract()
            item['content'] = ''.join(item['content'])
            item['author'] = div.xpath('./div/a[2]/h2/text() | ./div[1]/span[2]/h2/text()').extract_first()
            source = item['author']+item['content']
            hashValue = hashlib.sha256(source.encode()).hexdigest()

            ex = conn.sadd('qiubai_hash', hashValue)
            if ex == 1:
                yield item
            else:
                print('已爬取')

spider.py

# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from redis import Redis
from scrapy2.items import Scrapy2Item


class Spider2Spider(CrawlSpider):
    name = 'spider2'
    # allowed_domains = ['www.xxx.com']
    start_urls = ['https://www.4567tv.tv/index.php/vod/show/id/7.html']

    rules = (
        Rule(LinkExtractor(allow=r'/index.php/vod/show/id/7/page/\d+\.html'), callback='parse_item', follow=True),
    )

    def parse_item(self, response):
        conn = Redis(host='127.0.0.1', port=6379)
        detail_url_list = ['https://www.4567tv.tv' + el for el in  response.xpath(
            '//li[@class="col-md-6 col-sm-4 col-xs-3"]/div/a/@href').extract()]
        for url in detail_url_list:
            # ex == 1:set中没有存储url
            ex = conn.sadd('movies_url',url)
            if ex == 1:
                yield scrapy.Request(url=url, callback=self.parse_detail)
            else:
                print('已爬取过')

    def parse_detail(self,response):
        item = Scrapy2Item()
        item['name'] = response.xpath('/html/body/div[1]/div/div/div/div[2]/h1/text()').extract_first()
        item['actor'] = response.xpath('/html/body/div[1]/div/div/div/div[2]/p[3]/a/text()').extract_first()

        yield item

settings.py

BOT_NAME = 'scrapy2'

SPIDER_MODULES = ['scrapy2.spiders']
NEWSPIDER_MODULE = 'scrapy2.spiders'

USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/72.0.3626.119 Safari/537.36'

# Crawl responsibly by identifying yourself (and your website) on the user-agent
#USER_AGENT = 'scrapy2 (+http://www.yourdomain.com)'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
CONCURRENT_REQUESTS = 32

ITEM_PIPELINES = {
    'scrapy2.pipelines.Scrapy2Pipeline': 300
}

pipelines.py

from redis import Redis
class Scrapy2Pipeline(object):
    def __init__(self):
        self.conn = None
    def open_spider(self, spider):
        self.conn = Redis(host='127.0.0.1', port=6379)

    def process_item(self, item, spider):
        dic = {
            'name':item['name'],
            'actor':item['actor']
        }
        self.conn.lpush('qiubaiData',dic)
        print('爬取到一条数据,正在入库......')
        return item