虫子spider、items.py、pipelines.py管道、settings.py配置文件

原创

wx63a427ac86e31 2022-12-23 00:44:33 博主文章分类：爬虫 ©著作权

文章标签 ide html 字符串 文章分类 运维

©著作权归作者所有：来自51CTO博客作者wx63a427ac86e31的原创作品，请联系作者获取转载授权，否则将追究法律责任

import scrapy
from firstBlood.items import FirstbloodItem

class FirstSpider(scrapy.Spider):
    爬虫文件的名称：爬虫源文件的唯一标识
    name = 'first'
    允许的域名：
    allowed_domains = ['www.baidu.com']
    起始的url列表：列表中的列表元素会被scrapy自动的进行请求发送
    start_urls = ['https://dig.chouti.com/']
    解析数据
    基于终端指令的持久化存储
    def parse(self, response):
        data_list = []
        div_list = response.xpath('/html/body/main/div/div/div[1]/div/div[2]/div[1]')
        for div in div_list:
            #注意：xpath返回的列表中的列表元素是Selector对象，我们要解析获取的字符串的数据是存储在该对象中
            #必须经过一个extract()的操作才可以将改对象中存储的字符串的数据获取
            # content = div.xpath('./div/div/div[1]/a/text()')[0].extract()
            content = div.xpath('./div/div/div[1]/a/text()').extract_first()
            #xpath返回的列表中的列表元素有多个（Selector对象），想要将每一个列表元素对应的Selector中的字符串取出改如何操作？response.xpath('/div//text()').extract()
            print(content) #<Selector xxx='dsdsd' data="短发hi的说法绝对是">
            data_list.append(content)
        return data_list

    #管道的持久化存储
    def parse(self, response):
        div_list = response.xpath('/html/body/main/div/div/div[1]/div/div[2]/div[1]')
        for div in div_list:
            #注意：xpath返回的列表中的列表元素是Selector对象，我们要解析获取的字符串的数据是存储在该对象中
            #必须经过一个extract()的操作才可以将改对象中存储的字符串的数据获取
            # content = div.xpath('./div/div/div[1]/a/text()')[0].extract()
            content = div.xpath('./div/div/div[1]/a/text()').extract_first()
            item = FirstbloodItem()
            item['content'] = content
            #xpath返回的列表中的列表元素有多个（Selector对象），想要将每一个列表元素对应的Selector中的字符串取出改如何操作？response.xpath('/div//text()').extract()
            print(content) #<Selector xxx='dsdsd' data="短发hi的说法绝对是">

            yield item #将item对象提交给管道

items.py：

import scrapy


class FirstbloodItem(scrapy.Item):
    # define the fields for your item here like:
    content = scrapy.Field()#Field是一个万能的数据类型

pipelines.py：

#专门用作于持久化存储
class FirstbloodPipeline(object):
    fp = None
    def open_spider(self,spider):
        """重写父类方法"""
        print('我只会在爬虫开始的时候执行一次！！！')
        self.fp = open('./data.txt','w',encoding='utf-8')
    def process_item(self, item, spider):
        """处理item"""
        content = item['content']
        self.fp.write(content)
        return item
    def close_spider(self,spider):
        print('我只会在爬虫结束的时候调用一次1!!')
        self.fp.close()

settings.py：

BOT_NAME = 'firstBlood'

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


# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

# 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 = {
#    'firstBlood.middlewares.FirstbloodSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
#DOWNLOADER_MIDDLEWARES = {
#    'firstBlood.middlewares.FirstbloodDownloaderMiddleware': 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 = {
   'firstBlood.pipelines.FirstbloodPipeline': 300,#300表示的优先级，越小优先级越高
}

# 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'