scrapy爬取奇书网

spiders.py

# -*- coding: utf-8 -*- import scrapy # 引入item from ..items import BooksItem class BooksSpider(scrapy.Spider): name = 'books' allowed_domains = ['qishu.cc'] start_urls = ['http://www.qishu.cc/xuanhuan/list1_1.html'] def parse(self, response): # 根据xpath找到小说的详情页面链接 detail_links = response.xpath('//span[@class="mainSoftName"]/a/@href').extract() # for循环遍历所有小说链接 for link in detail_links: # 拼接完整的url地址 detail_url = 'http://www.qishu.cc' + link # yield 一个请求对象 yield scrapy.Request( url = detail_url, callback=self.parse_detail # 指定回调的函数 ) # 找到下一页 next_href = response.xpath('//dfn/a/@href').extract_first('') if next_href: # 拼接下一页的完整url地址 next_url = 'http://www.qishu.cc' + next_href yield scrapy.Request(next_url) # 解析详情页面 def parse_detail(self, response): # 获取小说标题 title = response.xpath('//dt[@id="downInfoTitle"]/text()').extract_first('') # 获取小说详细信息 info = response.xpath('//dd[@class="downInfoRowL"]/text()').extract() results = [] # for循环遍历所有信息 for msg in info: # 判断\r有没有在信息中 if '\r' not in msg: results.append(msg) # 如果拿到的数据是6个，取数据，否则全部设置为未知 if len(results) == 6: yxhj = results[0] # 运行环境 xsyy = results[1] # 小说语言 xslx = results[2] # 小说类型 xszz = results[3] # 小说作者 xsdx = results[4] # 小说大小 gxsj = results[5] # 更新时间 else: yxhj = xsyy = xslx = xszz = xsdx = gxsj = '未知' # 获取小说下载地址 download_url = response.xpath('//div[@id="downAddress"]/a[2]/@href').extract_first('') # 创建BooksItem对象 book = BooksItem() book['title'] = title book['yxhj'] = yxhj book['xsyy'] = xsyy book['xslx'] = xslx book['xszz'] = xszz book['xsdx'] = xsdx book['gxsj'] = gxsj # 下载文件需要将url放在列表中 book['download_url'] = [download_url] yield book

items.py

# -*- coding: utf-8 -*- # Define here the models for your scraped items # # See documentation in: # https://doc.scrapy.org/en/latest/topics/items.html import scrapy class BooksSpiderItem(scrapy.Item): # define the fields for your item here like: # name = scrapy.Field() pass class BooksItem(scrapy.Item): title = scrapy.Field() # 标题 yxhj = scrapy.Field() # 环境 xsyy = scrapy.Field() # 语言 xslx = scrapy.Field() # 类型 xszz = scrapy.Field() # 作者 xsdx = scrapy.Field() # 大小 gxsj = scrapy.Field() # 更新时间 download_url = scrapy.Field() # 下载地址

pipelines.py

# -*- coding: utf-8 -*- # Define your item pipelines here # # Don't forget to add your pipeline to the ITEM_PIPELINES setting # See: https://doc.scrapy.org/en/latest/topics/item-pipeline.html import xlwt class BooksSpiderPipeline(object): # 初始化的时候，新建workbook def __init__(self): self.workbook = xlwt.Workbook(encoding='utf-8') self.sheet = self.workbook.add_sheet(u'小说信息表') self.sheet.write(0, 0, '小说标题') self.sheet.write(0, 1, '运行环境') self.sheet.write(0, 2, '小说语言') self.sheet.write(0, 3, '小说类型') self.sheet.write(0, 4, '小说作者') self.sheet.write(0, 5, '小说大小') self.sheet.write(0, 6, '更新时间') self.sheet.write(0, 7, '下载地址') self.count = 1 def close_spider(self,spider): self.workbook.save(u'奇书小说信息.xls') def process_item(self, item, spider): self.sheet.write(self.count, 0, item['title']) self.sheet.write(self.count, 1, item['yxhj']) self.sheet.write(self.count, 2, item['xsyy']) self.sheet.write(self.count, 3, item['xslx']) self.sheet.write(self.count, 4, item['xszz']) self.sheet.write(self.count, 5, item['xsdx']) self.sheet.write(self.count, 6, item['gxsj']) self.sheet.write(self.count, 7, item['download_url'][0]) self.count += 1 return item from scrapy.pipelines.files import FilesPipeline import scrapy # 自定义小说下载pipeline 指定小说存放的名称 class MyFilesPipeline(FilesPipeline): def get_media_requests(self, item, info): url = item['download_url'][0] request = scrapy.Request( url=url, meta={'item':item} ) return [request] def file_path(self, request, response=None, info=None): item = request.meta['item'] title = item['title'] return '%s.txt'%title

debug.py

# -*- coding: utf-8 -*- from scrapy.cmdline import execute execute(['scrapy', 'crawl', 'books'])

settings.py

# -*- coding: utf-8 -*- # Scrapy settings for Books_Spider project # # For simplicity, this file contains only settings considered important or # commonly used. You can find more settings consulting the documentation: # # https://doc.scrapy.org/en/latest/topics/settings.html # https://doc.scrapy.org/en/latest/topics/downloader-middleware.html # https://doc.scrapy.org/en/latest/topics/spider-middleware.html BOT_NAME = 'Books_Spider' SPIDER_MODULES = ['Books_Spider.spiders'] NEWSPIDER_MODULE = 'Books_Spider.spiders' # Crawl responsibly by identifying yourself (and your website) on the user-agent #USER_AGENT = 'Books_Spider (+http://www.yourdomain.com)' # 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://doc.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://doc.scrapy.org/en/latest/topics/spider-middleware.html #SPIDER_MIDDLEWARES = { # 'Books_Spider.middlewares.BooksSpiderSpiderMiddleware': 543, #} # Enable or disable downloader middlewares # See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html #DOWNLOADER_MIDDLEWARES = { # 'Books_Spider.middlewares.BooksSpiderDownloaderMiddleware': 543, #} # Enable or disable extensions # See https://doc.scrapy.org/en/latest/topics/extensions.html #EXTENSIONS = { # 'scrapy.extensions.telnet.TelnetConsole': None, #} # Configure item pipelines # See https://doc.scrapy.org/en/latest/topics/item-pipeline.html ITEM_PIPELINES = { 'Books_Spider.pipelines.BooksSpiderPipeline': 300, # 'Books_Spider.pipelines.MyFilesPipeline': 301 } # 根据item的哪个属性下载小说 FILES_URLS_FIELD = 'download_url' # 小说存放的路径 FILES_STORE = 'novels' # Enable and configure the AutoThrottle extension (disabled by default) # See https://doc.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://doc.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'

middlewares.py

# -*- coding: utf-8 -*- # Define here the models for your spider middleware # # See documentation in: # https://doc.scrapy.org/en/latest/topics/spider-middleware.html from scrapy import signals class BooksSpiderSpiderMiddleware(object): # Not all methods need to be defined. If a method is not defined, # scrapy acts as if the spider 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) return s def process_spider_input(self, response, spider): # Called for each response that goes through the spider # middleware and into the spider. # Should return None or raise an exception. return None def process_spider_output(self, response, result, spider): # Called with the results returned from the Spider, after # it has processed the response. # Must return an iterable of Request, dict or Item objects. for i in result: yield i def process_spider_exception(self, response, exception, spider): # Called when a spider or process_spider_input() method # (from other spider middleware) raises an exception. # Should return either None or an iterable of Response, dict # or Item objects. pass def process_start_requests(self, start_requests, spider): # Called with the start requests of the spider, and works # similarly to the process_spider_output() method, except # that it doesn’t have a response associated. # Must return only requests (not items). for r in start_requests: yield r def spider_opened(self, spider): spider.logger.info('Spider opened: %s' % spider.name) class BooksSpiderDownloaderMiddleware(object): # 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) 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 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): spider.logger.info('Spider opened: %s' % spider.name)