在上一篇爬虫文章（14爬虫：scrapy实现翻页爬取-CSDN博客）中，我们对翻页爬取17k网站中涂书的名称，但是17k网站改版加入了无限debug模式导致分页爬取失败。在本次内容中，我们在下载器中间件和selenium实现了分页爬取。
整个程序的逻辑如上图所示：
（1）初始url的响应在spider中解析完毕后，得到的数据通过engine传递给pipeline，实现数据的持久化保存。得到的下一页url封装为SeleniumRequest请求对象，通过engine加入schedule，在由engine提交给downloder。
（2）SeleniumRequest请求对象在传递给downloader的过程中，遇到了下载器中间件（中间件我们可以简单的理解为一堵墙，只有符合条件的才能放行）。在下载器中间件中，我们设置如果是普通的Request对象则直接放行，由downloader完成数据请求在通过下载器提交至engine；但是页面2的url我们封装的是seleniumRequest，因此在下载器中间的process_request方法中实现selenium数据获取并返回Response对象，按照scrapy规则，process_request方法返回Response对象直接给engine，相当于把流程在下载器中间件处截断。
（3）后续的流程就是解析数据，数据持久化保存，selenium请求第三页url。
接下来，我们就给出相应的代码：
python
from scrapy.cmdline import execute
if __name__ == '__main__':
execute("scrapy crawl novelName".split())
python
from scrapy import Request
class SeleniumRequest(Request):
passspider
python
import scrapy
from novelSpider.items import NovelspiderItem
from novelSpider.request import SeleniumRequest
'''
settings.py中进行的设置
USER_AGENT = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
ROBOTSTXT_OBEY = False
LOG_LEVEL = "WARNING"
DOWNLOAD_DELAY = 3
ITEM_PIPELINES = {
"novelSpider.pipelines.NovelspiderPipeline": 300,
}
'''
class NovelnameSpider(scrapy.Spider):
name = "novelName"
allowed_domains = ["17k.com"]
start_urls = ["https://www.17k.com/all"] # 修改起始url为我们需要的地址
def parse(self, response, **kwargs):
# print(response.text)
# 当前页内容解析
items = response.xpath('//tbody//td[@class="td3"]/span/a')
for item in items:
name = item.xpath('.//text()').extract_first()
# print(name)
# 小说名称发送至pipeline
item = NovelspiderItem() # 构建item对象
item['name'] = name
yield item
# 翻页
page_urls = response.xpath('//div[@class="page"]/a')
for page_url in page_urls:
p_url = page_url.xpath('.//@href').extract_first()
if p_url.startswith("javascript"):
continue
# print(p_url)
# 拼接url，构建Request对象
p_url = response.urljoin(p_url)
print(p_url)
yield SeleniumRequest(url=p_url, method='GET', callback=self.parse) # 后续的网页请求零用selenium完成middleware
python
from scrapy import signals
from novelSpider.request import SeleniumRequest
from scrapy.http import HtmlResponse
from selenium.webdriver import Chrome
import time
class NovelspiderDownloaderMiddlewareBySelenium:
# 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.
@classmethod
def from_crawler(cls, crawler):
# This method is used by Scrapy to create your spiders.
s = cls()
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
crawler.signals.connect(s.spider_closed, signal=signals.spider_closed)
return s
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
# 首先判断是否需要selenium爬取数据
if isinstance(request, SeleniumRequest): # 需要selenium发送请求，返回响应给engine
self.web = Chrome()
time.sleep(5)
self.web.get(request.url)
return HtmlResponse(
url = request.url,
status = 200,
request = request,
body = self.web.page_source,
encoding = 'utf-8'
)
# 如果不需要selenium发送请求，则直接放行
return None
def process_response(self, request, response, spider):
# Called with the response returned from the downloader.
# 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):
# scrapy开始的时候创建selenium的Chrome对象
self.web = Chrome()
def spider_closed(self, spider):
# scrapy结束的时候关闭selenium
self.web.close()pipeline
python
class NovelspiderPipeline:
def process_item(self, item, spider):
print(item['name'])
return itemitem
python
import scrapy
class NovelspiderItem(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
name = scrapy.Field()settings
python
# Scrapy settings for novelSpider 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 = "novelSpider"
SPIDER_MODULES = ["novelSpider.spiders"]
NEWSPIDER_MODULE = "novelSpider.spiders"
# Crawl responsibly by identifying yourself (and your website) on the user-agent
USER_AGENT = "Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36"
# Obey robots.txt rules
ROBOTSTXT_OBEY = False
LOG_LEVEL = "WARNING"
# 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 = {
# "novelSpider.middlewares.NovelspiderSpiderMiddleware": 543,
#}
# Enable or disable downloader middlewares
# See https://docs.scrapy.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
# "novelSpider.middlewares.NovelspiderDownloaderMiddleware": 543,
"novelSpider.middlewares.NovelspiderDownloaderMiddlewareBySelenium":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 = {
"novelSpider.pipelines.NovelspiderPipeline": 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"
# Set settings whose default value is deprecated to a future-proof value
REQUEST_FINGERPRINTER_IMPLEMENTATION = "2.7"
TWISTED_REACTOR = "twisted.internet.asyncioreactor.AsyncioSelectorReactor"
FEED_EXPORT_ENCODING = "utf-8"运行结果
