20-爬虫之scrapy框架CrawlSpider07

CrawlSpider

是Spider的一个子类，Spider是爬虫文件中的爬虫父类
- 之类的功能一定是对于父类

• 作用：被作用于专业实现全站数据爬取
  • 将一个页面下的所有页码对应的数据进行爬取
• 基本使用
  • 创建一个爬虫工程：scrapy startproject proName
  • 进入工程创建一个基于CrawlSpider的爬虫文件
    • scrapy genspider -t crawl spiderName www.xxx.com
  • 执行工程：scrapy crawl spiderName

注意

• 一个链接提取器对应一个规则解析器（多个链接提取器和多个规则解析器）
• 在实现深度爬取的过程中，需要和scrapy.Request（）结合使用
• link = LinkExtractor(allow=r’’)# allow是空follow是True那么我们就能取出全站所有链接

普通爬取

爬虫源码

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule


class TestSpider(CrawlSpider):
    name = 'test'
    #allowed_domains = ['www.xxx.com']
    start_urls = ['http://www.521609.com/daxuemeinv/']

    # 链接提取器：根据指定规则（allow参数）在页面中进行链接（url）提取
    # allow = "正则"：提取链接的规则
    link = LinkExtractor(allow=r'list8d+.html')# 实例化LinkExtractor对象
    # link = LinkExtractor(allow=r'')# allow是空follow是True那么我们就能取出全站所有链接
    rules = (
        # 是实例化一个Rule对象
        #规则解析器:接收链接提取器提取到的链接，对其发起请求，然后根据指定规则（callback）解析数据
        Rule(link, callback='parse_item', follow=True),
    )
    # follow = True
    # 将链接提取器，继续作用到链接 提取器提取到的页码所对应的页面中
    def parse_item(self, response):
        print(response)
        # 基于response实现数据解析

深度爬取

CrawlSpider实现深度爬取

• 通用方式：CrawlSpider + Spider实现深度爬取

• 创建一个爬虫工程：scrapy startproject proName

• 进入工程创建一个基于CrawlSpider的爬虫文件

  • scrapy genspider -t crawl spiderName www.xxx.com

• 执行工程：scrapy crawl spiderName

settings.py

# Scrapy settings for sunPro 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 = 'sunPro'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.138 Safari/537.36"

# 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 = {
#    'sunPro.middlewares.SunproSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'sunPro.middlewares.SunproDownloaderMiddleware': 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 = {
   'sunPro.pipelines.SunproPipeline': 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'

items.py

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

import scrapy


class SunproItem(scrapy.Item):
    title = scrapy.Field()
    status = scrapy.Field()

class SunProItemDetail(scrapy.Item):
    content = scrapy.Field()

pipelines.py

# 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


# useful for handling different item types with a single interface
from itemadapter import ItemAdapter


class SunproPipeline:
    def process_item(self, item, spider):
        if item.__class__.__name__=='SunproItem':
            title = item['title']
            status = item['status']
            print(title+":"+status)
        else:
            content = item['content']
            print(content)

        return item

sun.py 爬虫源文件

此方法进行数据爬取，，持久化存储目前无法将title和content进行一一匹配，我们需要手动发起请求

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from sunPro.items import SunproItem,SunProItemDetail



class TestSpider(CrawlSpider):
    name = 'sun'
    #allowed_domains = ['www.xxx.com']
    start_urls = ['http://wz.sun0769.com/political/index/politicsNewest?id=1&page=1']

    # 链接提取器：根据指定规则（allow参数）在页面中进行链接（url）提取
    # allow = "正则"：提取链接的规则
    link = LinkExtractor(allow=r'id=1&page=d+')# 实例化LinkExtractor对象
    link_detail = LinkExtractor(allow=r'dindex?id=d+') #详情页url
    # link = LinkExtractor(allow=r'')# allow是空follow是True那么我们就能取出全站所有链接
    rules = (
        # 是实例化一个Rule对象
        #规则解析器:接收链接提取器提取到的链接，对其发起请求，然后根据指定规则（callback）解析数据
        Rule(link, callback='parse_item', follow=True),
        Rule(link_detail, callback='parse_detail'),
    )
    # follow = True
    # 将链接提取器，继续作用到链接 提取器提取到的页码所对应的页面中
    #标题&状态
    def parse_item(self, response):
        li_list = response.xpath('/html/body/div[2]/div[3]/ul[2]/li')
        for li in li_list:
            title = li.xpath('./span[3]/a/text()').extract_first()
            status = li.xpath('./span[2]/text()').extract_first()
            item = SunproItem()
            item['title']=title
            item['status'] =status
            yield item
        # 实现深度爬取：爬取详情页中的数据
        # 1，对详情页的url进行捕获
        # 2，对详情页的url发起请求获取数据
    def parse_detail(self,response):
        content = response.xpath('/html/body/div[3]/div[2]/div[2]/div[2]/pre/text()').extract_first()
        item = SunProItemDetail()
        item['content']=content
        yield item
        # 爬虫文件会向管道提交两个不同形式的item，管道会接受到两个不同形式的item。
        #我们需要在管道中判断接收到item到底是哪一个
        #此方法进行数据爬取，，持久化存储目前无法将title和content进行一一匹配，我们需要手动发起请求

CrawlSpider+Spider全站深度爬取

items.py

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

import scrapy


class SunproItem(scrapy.Item):
    title = scrapy.Field()
    status = scrapy.Field()
    content = scrapy.Field()

pipelines.py

# 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


# useful for handling different item types with a single interface
from itemadapter import ItemAdapter


class SunproPipeline:
    def process_item(self, item, spider):
        print(item)
        return item

sun.py 爬虫源文件

import scrapy
from scrapy.linkextractors import LinkExtractor
from scrapy.spiders import CrawlSpider, Rule
from sunPro.items import SunproItem



class TestSpider(CrawlSpider):
    name = 'sun'
    #allowed_domains = ['www.xxx.com']
    start_urls = ['http://wz.sun0769.com/political/index/politicsNewest?id=1&page=1']

    # 链接提取器：根据指定规则（allow参数）在页面中进行链接（url）提取
    # allow = "正则"：提取链接的规则
    link = LinkExtractor(allow=r'id=1&page=d+')# 实例化LinkExtractor对象
    #link_detail = LinkExtractor(allow=r'dindex?id=d+') #详情页url

    rules = (
        # 是实例化一个Rule对象
        #规则解析器:接收链接提取器提取到的链接，对其发起请求，然后根据指定规则（callback）解析数据
        Rule(link, callback='parse_item', follow=True),
       # Rule(link_detail, callback='parse_detail'),
    )
    # #follow = True
    # 将链接提取器，继续作用到链接 提取器提取到的页码所对应的页面中
    #标题&状态
    def parse_item(self, response):
        li_list = response.xpath('/html/body/div[2]/div[3]/ul[2]/li')
        for li in li_list:
            title = li.xpath('./span[3]/a/text()').extract_first()
            status = li.xpath('./span[2]/text()').extract_first()
            detail_url ="http://wz.sun0769.com" + li.xpath('./span[3]/a/@href').extract_first()#详情页url
            item = SunproItem()
            item['title'] = title
            item['status'] = status
            yield scrapy.Request(url=detail_url,callback=self.parse_detail,meta={'item':item})
    def parse_detail(sele,response):
        content = response.xpath('/html/body/div[3]/div[2]/div[2]/div[2]/pre/text()').extract_first()
        item = response.meta['item']
        item['content'] = content
        yield item