爬虫 scrapy 分布式

scrapy_redis

1. scrapy startproject chouti
2. cd chouti
3. scrapy genspider -t crawl chouti www.baidu.com

setting.py

LOG_LEVEL = 'ERROR'
# 日志文件等级

ROBOTSTXT_OBEY = False
# 不遵循robots协议

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'
# UA伪装

# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule


class ChoutiSpider(CrawlSpider):
    # name = 'chouti'
    # # allowed_domains = ['www.xxx.com']
    # start_urls = ['https://dig.chouti.com/r/scoff/hot/1']
    #
    # #连接提取器:
    # #allow:表示的就是链接提取器提取连接的规则(正则)
    # link = LinkExtractor(allow=r'/r/scoff/hot/d+')
    #
    # rules = (
    #     #规则解析器:将链接提取器提取到的连接所对应的页面数据进行指定形式的解析
    #     Rule(link, callback='parse_item', follow=True),
    #     # 让连接提取器继续作用到链接提取器提取到的连接所对应的页面中
    # )
    #
    # def parse_item(self, response):
    #     print(response)

    name = 'qiubai'
    # allowed_domains = ['www.xxx.com']
    start_urls = ['https://www.qiushibaike.com/pic/']

    # 连接提取器:
    # allow:表示的就是链接提取器提取连接的规则(正则)/pic/page/3?s=5172496
    link = LinkExtractor(allow=r'/pic/page/d+?s=d+')
    link1 = LinkExtractor(allow=r'/pic/$')
    # link1 = LinkExtractor(allow=r'')
    rules = (
        # 规则解析器:将链接提取器提取到的连接所对应的页面数据进行指定形式的解析
        Rule(link, callback='parse_item', follow=True),
        # 让连接提取器继续作用到链接提取器提取到的连接所对应的页面中

        Rule(link1, callback='parse_item', follow=True),
    )

    def parse_item(self, response):
        print(response)

        
        
        
 # -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from redis import Redis
from increment1_Pro.items import Increment1ProItem
class MovieSpider(CrawlSpider):
    name = 'movie'
    # 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'+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('网站没有更新数据,暂无新数据可爬!')

    def parse_detail(self,response):
        item = Increment1ProItem()
        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
        
        
        
        
# -*- coding: utf-8 -*-
import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule

from increment2_Pro.items import Increment2ProItem
from redis import Redis
import hashlib
class QiubaiSpider(CrawlSpider):
    name = 'qiubai'
    # 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 = Increment2ProItem()
            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']
            #自己制定了一种形式的数据指纹
            hashValue = hashlib.sha256(source.encode()).hexdigest()

            ex = conn.sadd('qiubai_hash',hashValue)
            if ex == 1:
                yield item
            else:
                print('没有更新数据可爬!!!')

1.请求传参(item):
    - 应用场景:解析的数据不在同一张页面中
    - Request(callback,meta={})
2.LOG_LEVEL  LOG_FILE
3.下载中间件:
    - 批量拦截请求(代理ip和UA)和响应(处理页面数据)
4.如何在scrapy使用selenium
    1.在spider的init方法中实例化一个浏览器对象
    2.在spider的closed方法中关闭浏览器对象
    3.在下载中间件类的process_response方法中接收spider中的浏览器对象
    4.处理执行相关自动化操作(发起请求,获取页面数据)
    5.实例化一个新的响应对象(from scrapy.http import HtmlResponse),且将页面数据存储到该对象中
    6.返回新的响应对象
    7.在配置文件中开启中间件
5.如何提升scrapy爬取数据的效率:

增加并发：
    默认scrapy开启的并发线程为32个，可以适当进行增加。在settings配置文件中修改CONCURRENT_REQUESTS = 100值为100,并发设置成了为100。

降低日志级别：
    在运行scrapy时，会有大量日志信息的输出，为了减少CPU的使用率。可以设置log输出信息为INFO或者ERROR即可。在配置文件中编写：LOG_LEVEL = ‘INFO’

禁止cookie：
    如果不是真的需要cookie，则在scrapy爬取数据时可以禁止cookie从而减少CPU的使用率，提升爬取效率。在配置文件中编写：COOKIES_ENABLED = False

禁止重试：
    对失败的HTTP进行重新请求（重试）会减慢爬取速度，因此可以禁止重试。在配置文件中编写：RETRY_ENABLED = False

减少下载超时：
    如果对一个非常慢的链接进行爬取，减少下载超时可以能让卡住的链接快速被放弃，从而提升效率。在配置文件中进行编写：DOWNLOAD_TIMEOUT = 10 超时时间为10s