scrapy框架

spider：

import scrapy
from yswPro.items import YswproItem
from selenium import webdriver

class YswSpider(scrapy.Spider):
    name = 'ysw'
    # allowed_domains = ['www.xxx.com']
    start_urls = ['https://news.cctv.com/']
    models_urls = []
    def __init__(self):
        self.bro = webdriver.Chrome(executable_path=r'C:\Program Files (x86)\Google\Chrome\Application\chromedriver.exe')
    def parse(self, response):
        div_list = response.xpath('//*[@id="page_body"]/div[1]/div/div/div[2]/div[1]/div')
        alist = [1,2,3,4]
        for index in alist:
            model_url = div_list[index].xpath('./span/a/@href').extract_first()
            self.models_urls.append(model_url)
        for url in self.models_urls:
            yield scrapy.Request(url=url,callback=self.parse_model)
    def parse_model(self,response):
        li_list = response.xpath('//*[@id="newslist"]/li')
        for li in li_list:
            title = li.xpath('./div[2]/h3/a/text()').extract_first()
            item = YswproItem()
            item['title'] = title
            yield item
    def closed(self,spider):
        self.bro.quit()
setting：

# Scrapy settings for yswPro 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 = 'yswPro'

SPIDER_MODULES = ['yswPro.spiders']
NEWSPIDER_MODULE = 'yswPro.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/91.0.4472.114 Safari/537.36 Edg/91.0.864.54'

# 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 = {
#    'yswPro.middlewares.YswproSpiderMiddleware': 543,
#}

# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
   'yswPro.middlewares.YswproDownloaderMiddleware': 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 = {
   'yswPro.pipelines.YswproPipeline': 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'
middle：

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

from scrapy import signals

# useful for handling different item types with a single interface
from itemadapter import is_item, ItemAdapter
from time import sleep
from scrapy.http import HtmlResponse




class YswproDownloaderMiddleware:
    # Not all methods need to be defined. If a method is not defined,
    # scrapy acts as if the downloader middleware does not modify the
    # passed objects.



    def process_request(self, request, spider):
        # Called for each request that goes through the downloader
        # middleware.

        # Must either:
        # - return None: continue processing this request
        # - or return a Response object
        # - or return a Request object
        # - or raise IgnoreRequest: process_exception() methods of
        #   installed downloader middleware will be called
        return None

    def process_response(self, request, response, spider):
        # Called with the response returned from the downloader.
        bro = spider.bro
        if request.url in spider.models_urls:
            bro.get(request.url)
            sleep(2)
            page_text = bro.page_source
            new_response = HtmlResponse(url=request.url, body=page_text, encoding='utf-8', request=request)
            return new_response
        else:
            return response
        # Must either;
        # - return a Response object
        # - return a Request object
        # - or raise IgnoreRequest
        return response

    def process_exception(self, request, exception, spider):
        # Called when a download handler or a process_request()
        # (from other downloader middleware) raises an exception.

        # Must either:
        # - return None: continue processing this exception
        # - return a Response object: stops process_exception() chain
        # - return a Request object: stops process_exception() chain
        pass

    def spider_opened(self, spider):
        spider.logger.info('Spider opened: %s' % spider.name)

pip：

# 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
import pymysql

class QiubaiproPipeline:
    fp = None
    # 重写父类方法：该方法只在开始爬虫的时候被调用一次
    def open_spider(self,spider):
        print('开始爬虫：')
        self.fp = open('./qiubai.txt','w',encoding='utf-8')
    # 专门用来处理item类型对象
    # 该方法可以接收虫文件提交过来的item对象
    # 该方法每接收到一个item 就会被调用一次
    def process_item(self, item, spider):
        author = item['author']
        content = item['content']

        self.fp.write(author+':'+content+'\n')

        return item # 就会传递给 下一个即将被执行的管道类
    def close_spider(self,spider):
        print('结束爬虫')
        self.fp.close()


# 管道文件中一个管道类对应将一组数据存储到一个平台或者载体中
class mysqlPileLine(object):
    conn = None
    cursor = None
    def open_spider(self,spider):
        self.conn = pymysql.Connect(host = '127.0.0.1',port='3306',user='root',password='123456',db='qiubai',charset='utf8')
    def process_item(self,item,spider):
        self.cursor = self.conn.cursor()
        try:
            self.cursor.execute('insert into qiubai values("%s","%s")'%(item["author"],item["content"]))
            self.conn.commit()
        except Exception as e:
            print(e)
            self.conn.rollback()
    def close_spider(self,spider):
        self.cursor.close()
        self.conn.close()