爬虫之scrapy（爬取抽屉网的所有信息，如果网的IP被封就需要用代理软件，如花生代理软件，一般手机热点是不会被封IP的）
Scrapy
一、安装
1. pip3 install wheel 2. pip3 install lxml 3. pip3 install pyopenssl 4. pip3 install -i https://mirrors.aliyun.com/pypi/simple/ pypiwin32 5. 下载文件(twisted): https://www.lfd.uci.edu/~gohlke/pythonlibs/#twisted pip3 install 文件路径\Twisted-19.2.0-cp36-cp36m-win_amd64.whl 6.pip3 install scrapy 7.scrapy 测试安装是否成功 Scrapy 1.6.0 - no active project
二、scrapy命令
全局(所有路径下都可以使用): bench Run quick benchmark test fetch Fetch a URL using the Scrapy downloader # 会把爬虫程序创建在当前目录下 genspider Generate new spider using pre-defined templates # 可以在当前目录下启动爬虫程序 runspider Run a self-contained spider (without creating a project) runspider 爬虫程序的绝对路径 settings Get settings values shell Interactive scraping console # 创建scrapy项目 startproject Create new project version Print Scrapy version view 局部(在scrapy项目中可以使用): bench Run quick benchmark test # 监测语法 check Check spider contracts # 根据爬虫程序的name 启动爬虫程序 crawl Run a spider # ！！！！！！！重点使用它！！！！！！！ scrapy crawl name edit Edit spider fetch Fetch a URL using the Scrapy downloader genspider Generate new spider using pre-defined templates # 查看所有的爬虫程序 list List available spiders parse Parse URL (using its spider) and print the results runspider Run a self-contained spider (without creating a project) settings Get settings values shell Interactive scraping console startproject Create new project version Print Scrapy version view Open URL in browser, as seen by Scrapy
三、创建scrapy项目
Django: # 创建项目 django-admin startproject P1 cd P1 # 创建实例 python3 manage.py app01 python3 manage.py bbs Scrapy: # 创建项目 scrapy startproject spider_project cd spider_project # 创建爬虫程序 scrapy genspider baidu baidu.com settings： # 不遵循反爬协议 ROBOTSTXT_OBEY = False
列表
spider_project.spiders下的chouti.py
# -*- coding: utf-8 -*- import scrapy from scrapy import Request from spider_project.items import SpiderNewListItem, SpiderUserListItem # from scrapy.http.response.html import HtmlResponse # 去重规则源码 # from scrapy.dupefilters import RFPDupeFilter class ChoutiSpider(scrapy.Spider): name = 'chouti' allowed_domains = ['chouti.com'] start_urls = ['http://chouti.com/'] # 爬虫的第一次访问结果会返回给parse def parse(self, response): # print(response, type(response)) # print(response.text) ''' 解析新闻主页 :param response: :return: ''' # .extract()查找所有 # .extract_first() 查找一个 # 查找标签[] content_list = response.xpath('//div[@class="content-list"]/div[@class="item"]') # print(content_list) for content in content_list: # 查找属性@ # 新闻链接 new_url = content.xpath('.//a/@href').extract_first() # 新闻文本 new_text = content.xpath('.//a/text()').extract_first().strip() if new_text.startswith('/'): new_text = 'https://dig.chouti.com' + new_text # 点赞数 nice_num = content.xpath('.//a[@class="digg-a"]/b/text()').extract_first() # 新闻ID new_id = content.xpath('.//a[@class="digg-a"]/i/text()').extract_first() print(new_id) # 评论数 commit_num = content.xpath('.//a[@class="discus-a"]/b/text()').extract_first() # 新闻详情 new_content = content.xpath('.//span[@class="summary"]/text()').extract_first() # print(new_content) # 发表新闻用户的主页 user_link = 'https://dig.chouti.com' + content.xpath('.//a[@class="user-a"]/@href').extract_first() # 主页新闻items类 items =SpiderNewListItem( new_url=new_url, new_text=new_text, nice_num=nice_num, new_id=new_id, commit_num=commit_num, new_content=new_content, user_link=user_link ) yield items # print(user_link) yield Request(url=user_link, callback=self.parse_user_index) # with open('chouti.txt', 'a', encoding='utf-8') as f: # f.write('%s-%s-%s-%s-%s-%s' % (new_url, new_text, nice_num, new_id, commit_num, user_link) + '\n') # print(new_url) a_s = response.xpath('//div[@id="dig_lcpage"]//a/@href').extract() print(a_s) for a in a_s: new_index_url = 'https://dig.chouti.com' + a print(new_index_url) # Request这个类帮我们提交请求 yield Request(url=new_index_url, callback=self.parse) # pass def parse_user_index(self, response): ''' 解析用户主页 :param response: :return: ''' # .extract()查找所有 # .extract_first() 查找一个 # 查找标签[] content_list = response.xpath('//div[@class="content-list"]/div[@class="item"]') # print(content_list) for content in content_list: # 查找属性@ # 新闻链接 new_url = content.xpath('.//a/@href').extract_first() # 新闻文本 new_text = content.xpath('.//a/text()').extract_first().strip() if new_text.startswith('/'): new_text = 'https://dig.chouti.com' + new_text # 点赞数 nice_num = content.xpath('.//a[@class="digg-a"]/b/text()').extract_first() # 新闻ID new_id = content.xpath('.//a[@class="digg-a"]/i/text()').extract_first() # 评论数 commit_num = content.xpath('.//a[@class="discus-a"]/b/text()').extract_first() # 新闻详情 new_content = content.xpath('.//span/[@class="summary"]/text()').extract_first() # 用户名 user_name = content.xpath('//div[@class="tu"]/a/text()').extract_first() print(user_name) # with open('chouti.txt', 'a', encoding='utf-8') as f: # f.write('%s-%s-%s-%s-%s-%s' % (new_url, new_text, nice_num, new_id, commit_num, user_link) + '\n') # print(new_url) items = SpiderUserListItem( new_url=new_url, new_text=new_text, nice_num=nice_num, new_id=new_id, commit_num=commit_num, new_content=new_content, user_name=user_name ) yield items a_s = response.xpath('//div[@id="dig_lcpage"]//a/@href').extract() # print(a_s) for a in a_s: new_index_url = 'https://dig.chouti.com' + a # print(new_index_url) # Request这个类帮我们提交请求 yield Request(url=new_index_url, callback=self.parse_user_index)
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 SpiderProjectItem(scrapy.Item): # # define the fields for your item here like: # name = scrapy.Field() # 新闻items类 class SpiderNewListItem(scrapy.Item): # define the fields for your item here like: # 新闻链接 new_url = scrapy.Field() # 新闻文本 new_text = scrapy.Field() # 点赞数 nice_num = scrapy.Field() # 新闻ID new_id = scrapy.Field() # 评论数 commit_num = scrapy.Field() # 新闻详情 new_content = scrapy.Field() # 发表新闻用户的主页 user_link = scrapy.Field() # 新闻items类 class SpiderUserListItem(scrapy.Item): # define the fields for your item here like: # 新闻链接 new_url = scrapy.Field() # 新闻文本 new_text = scrapy.Field() # 点赞数 nice_num = scrapy.Field() # 新闻ID new_id = scrapy.Field() # 评论数 commit_num = scrapy.Field() # 新闻详情 new_content = scrapy.Field() # 用户名 user_name = scrapy.Field()
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 SpiderProjectSpiderMiddleware(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 SpiderProjectDownloaderMiddleware(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)
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 # class SpiderProjectPipeline(object): # def process_item(self, item, spider): # return item import scrapy from pymongo import MongoClient # 新闻详情 class SpiderNewListPipeline(object): def __init__(self, ip, port, mongo_db): self.ip = ip self.port = port self.mongo_db = mongo_db # 一 启动scrapy项目会先执行此方法加载settings里面的配置文件 @classmethod def from_crawler(cls, crawler): ip = crawler.settings.get('IP') port = crawler.settings.get('PORT') mongo_db = crawler.settings.get('DB') return cls(ip, port, mongo_db) # 二 执行爬虫程序会先执行此方法 def open_spider(self, spider): self.client = MongoClient(self.ip, self.port) def process_item(self, item, spider): new_url = item.get('new_url') new_text = item.get('new_text') nice_num = item.get('nice_num') new_id = item.get('new_id') commit_num = item.get('commit_num') new_content = item.get('new_content') user_link = item.get('user_link') new_data = { 'new_url': new_url, 'new_text': new_text, 'nice_num': nice_num, 'new_id': new_id, 'commit_num': commit_num, 'new_content': new_content, 'user_link': user_link } self.client[self.mongo_db]['new_list'].insert_one(new_data) return item def close_spider(self, spider): self.client.close() # 用户主页新闻详情 class SpiderUserListPipeline(object): def __init__(self, ip, port, mongo_db): self.ip = ip self.port = port self.mongo_db = mongo_db # 一 启动scrapy项目会先执行此方法加载settings里面的配置文件 @classmethod def from_crawler(cls, crawler): ip = crawler.settings.get('IP') port = crawler.settings.get('PORT') mongo_db = crawler.settings.get('DB') return cls(ip, port, mongo_db) # 二 执行爬虫程序会先执行此方法 def open_spider(self, spider): self.client = MongoClient(self.ip, self.port) def process_item(self, item, spider): new_url = item.get('new_url') new_text = item.get('new_text') nice_num = item.get('nice_num') new_id = item.get('new_id') commit_num = item.get('commit_num') new_content = item.get('new_content') user_name = item.get('user_name') new_data = { 'new_url': new_url, 'new_text': new_text, 'nice_num': nice_num, 'new_id': new_id, 'commit_num': commit_num, 'new_content': new_content, } self.client[self.mongo_db][user_name].insert_one(new_data) return item def close_spider(self, spider): self.client.close() # class MysqlSpiderNewListPipeline(object): # # def __init__(self, ip, port, mongo_db): # self.ip = ip # self.port = port # self.mongo_db = mongo_db # # # 一 启动scrapy项目会先执行此方法加载settings里面的配置文件 # @classmethod # def from_crawler(cls, crawler): # ip = crawler.settings.get('IP') # port = crawler.settings.get('PORT') # mongo_db = crawler.settings.get('DB') # # return cls(ip, port, mongo_db) # # # 二 执行爬虫程序会先执行此方法 # def open_spider(self, spider): # self.client = MongoClient(self.ip, self.port) # # def process_item(self, item, spider): # new_url = item.get('new_url') # new_text = item.get('new_text') # nice_num = item.get('nice_num') # new_id = item.get('new_id') # commit_num = item.get('commit_num') # new_content = item.get('new_content') # user_link = item.get('user_link') # # new_data = { # 'new_url': new_url, # 'new_text': new_text, # 'nice_num': nice_num, # 'new_id': new_id, # 'commit_num': commit_num, # 'new_content': new_content, # 'user_link': user_link # } # # self.client[self.mongo_db]['new_list'].insert_one(new_data) # # return item # # # # def close_spider(self, spider): # self.client.close()
settings.py
# -*- coding: utf-8 -*- ''' settings里面的参数必须全大写，小写无效 ''' # Scrapy settings for spider_project 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 # from spider_project import spiders BOT_NAME = 'spider_project' SPIDER_MODULES = ['spider_project.spiders'] NEWSPIDER_MODULE = 'spider_project.spiders' # Crawl responsibly by identifying yourself (and your website) on the user-agent #USER_AGENT = 'spider_project (+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 = { # 'spider_project.middlewares.SpiderProjectSpiderMiddleware': 543, #} # Enable or disable downloader middlewares # See https://doc.scrapy.org/en/latest/topics/downloader-middleware.html #DOWNLOADER_MIDDLEWARES = { # 'spider_project.middlewares.SpiderProjectDownloaderMiddleware': 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 # 必须配置才可以启动ITEM_PIPELINES ITEM_PIPELINES = { 'spider_project.pipelines.SpiderNewListPipeline': 300, 'spider_project.pipelines.SpiderUserListPipeline': 301, } # MongoDB配置信息 IP = 'localhost' PORT = 27017 DB = 'chouti' # 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'
main.py
from scrapy.cmdline import execute # execute(['scrapy', 'crawl', 'baidu']) execute("scrapy crawl --nolog chouti".split(' '))
浙公网安备 33010602011771号