scrapy 增量式

前言

首先通常我们的爬虫都是一次性。应用场景并不多

概念

用于检测网站的数据跟新并实时抓取数据

核心机制 (去除重复数据)

去重 利用reids的set实现去重

一、创建项目

# scrapy startproject zlsPro

# cd zlsPro

# scrapy genspider -t crawl zls www.xxx.com
 
# scrapy crawl zls

二、配置文件settings文件

ROBOTSTXT_OBEY = False
LOG_LERVER='ERROR'
USER_AGENT = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36"

三、爬虫文件代码实现

爬虫文件

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

class ZlsSpider(CrawlSpider):
    conn = Redis(host='127.0.0.1',port=6379)
    name = 'zls'
    # allowed_domains = ['www.xxx.com']
    start_urls = ['https://www.4567kan.com/index.php/vod/show/id/6.html']

    rules = (
        Rule(LinkExtractor(allow=r'page/\d+\.html'), callback='parse_item', follow=False),
    )
    def parse_item(self, response):
        li_list = response.xpath("/html/body/div[1]/div/div/div/div[2]/ul/li")
        for li in li_list:
            name = li.xpath('./div/a/@title').extract_first()
            detail_url = li.xpath('./div/a/@href').extract_first()
            itme = ZlsproItem()
            itme["name"] = name
            # 利用redis set 去除重复链接 
            if self.conn.sadd("set_detail_url",detail_url) == 1:

                yield Request("https://www.4567kan.com"+detail_url,callback=self.parse_detail,meta={"itme":itme})
            else:
                pass

    def parse_detail(self,response):
        itme = response.meta["itme"]
        desc = response.xpath('/html/body/div[1]/div/div/div/div[2]/p[5]/span[2]/text()').extract_first()
        itme["desc"] = desc
        yield itme

管道文件pipelines.py

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

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: https://docs.scrapy.org/en/latest/topics/item-pipeline.html


class ZlsproPipeline(object):
    def process_item(self, item, spider):
        print(item)
        conn = spider.conn
        conn.lpush("data",item)
        return item

Items.py

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

# Define here the models for your scraped items
#
# See documentation in:
# https://docs.scrapy.org/en/latest/topics/items.html

import scrapy


class ZlsproItem(scrapy.Item):
    # define the fields for your item here like:
    name = scrapy.Field()
    desc = scrapy.Field()
    print(desc)

settings.py

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

# Scrapy settings for zlsPro project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     https://docs.scrapy.org/en/latest/topics/settings.html
#     https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#     https://docs.scrapy.org/en/latest/topics/spider-middleware.html

BOT_NAME = 'zlsPro'

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

USER_AGENT = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_14_6) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36"

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

# Obey robots.txt rules
ROBOTSTXT_OBEY = False
LOG_LEVEL = "ERROR"

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

# Configure a delay for requests for the same website (default: 0)
# See https://docs.scrapy.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
#DOWNLOAD_DELAY = 3
# The download delay setting will honor only one of:
#CONCURRENT_REQUESTS_PER_DOMAIN = 16
#CONCURRENT_REQUESTS_PER_IP = 16

# Disable cookies (enabled by default)
#COOKIES_ENABLED = False

# Disable Telnet Console (enabled by default)
#TELNETCONSOLE_ENABLED = False

# Override the default request headers:
#DEFAULT_REQUEST_HEADERS = {
#   'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
#   'Accept-Language': 'en',
#}

# Enable or disable spider middlewares
# See https://docs.scrapy.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
#    'zlsPro.middlewares.ZlsproSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'zlsPro.middlewares.ZlsproDownloaderMiddleware': 543,
#}

# Enable or disable extensions
# See https://docs.scrapy.org/en/latest/topics/extensions.html
#EXTENSIONS = {
#    'scrapy.extensions.telnet.TelnetConsole': None,
#}

# Configure item pipelines
# See https://docs.scrapy.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
   'zlsPro.pipelines.ZlsproPipeline': 300,
}

# Enable and configure the AutoThrottle extension (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/autothrottle.html
#AUTOTHROTTLE_ENABLED = True
# The initial download delay
#AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
#AUTOTHROTTLE_MAX_DELAY = 60
# The average number of requests Scrapy should be sending in parallel to
# each remote server
#AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0
# Enable showing throttling stats for every response received:
#AUTOTHROTTLE_DEBUG = False

# Enable and configure HTTP caching (disabled by default)
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings
#HTTPCACHE_ENABLED = True
#HTTPCACHE_EXPIRATION_SECS = 0
#HTTPCACHE_DIR = 'httpcache'
#HTTPCACHE_IGNORE_HTTP_CODES = []
#HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'

来源：https://www.cnblogs.com/jiangchunsheng/p/12554143.html

标签

scrapy