Scrapy框架

Scrapy

Scrapy是一个为了爬取网站数据，提取结构性数据而编写的应用框架。 其可以应用在数据挖掘，信息处理或存储历史数据等一系列的程序中。
其最初是为了页面抓取 (更确切来说, 网络抓取 )所设计的， 也可以应用在获取API所返回的数据(例如 Amazon Associates Web Services ) 或者通用的网络爬虫。Scrapy用途广泛，可以用于数据挖掘、监测和自动化测试。

Scrapy 使用了 Twisted异步网络库来处理网络通讯。整体架构大致如下

Scrapy主要包括了以下组件：

  • 引擎(Scrapy)
    用来处理整个系统的数据流处理, 触发事务(框架核心)
  • 调度器(Scheduler)
    用来接受引擎发过来的请求, 压入队列中, 并在引擎再次请求的时候返回. 可以想像成一个URL（抓取网页的网址或者说是链接）的优先队列, 由它来决定下一个要抓取的网址是什么, 同时去除重复的网址
  • 下载器(Downloader)
    用于下载网页内容, 并将网页内容返回给蜘蛛(Scrapy下载器是建立在twisted这个高效的异步模型上的)
  • 爬虫(Spiders)
    爬虫是主要干活的, 用于从特定的网页中提取自己需要的信息, 即所谓的实体(Item)。用户也可以从中提取出链接,让Scrapy继续抓取下一个页面
  • 项目管道(Pipeline)
    负责处理爬虫从网页中抽取的实体，主要的功能是持久化实体、验证实体的有效性、清除不需要的信息。当页面被爬虫解析后，将被发送到项目管道，并经过几个特定的次序处理数据。
  • 下载器中间件(Downloader Middlewares)
    位于Scrapy引擎和下载器之间的框架，主要是处理Scrapy引擎与下载器之间的请求及响应。
  • 爬虫中间件(Spider Middlewares)
    介于Scrapy引擎和爬虫之间的框架，主要工作是处理蜘蛛的响应输入和请求输出。
  • 调度中间件(Scheduler Middewares)
    介于Scrapy引擎和调度之间的中间件，从Scrapy引擎发送到调度的请求和响应。

Scrapy运行流程大概如下：

  1. 引擎从调度器中取出一个链接(URL)用于接下来的抓取
  2. 引擎把URL封装成一个请求(Request)传给下载器
  3. 下载器把资源下载下来，并封装成应答包(Response)
  4. 爬虫解析Response
  5. 解析出实体（Item）,则交给实体管道进行进一步的处理
  6. 解析出的是链接（URL）,则把URL交给调度器等待抓取

一、安装

Linux:
    pip3 install scrapy 

Windows:
    pip3 install wheel
    D:twisted.wheel
    pip3 install D:twisted.wheel
    
    pip3 install scrapy 报错：twisted安装错误
    
    pywin32


PS: 
    - python3对twisted未完全支持
    - python2    对Scrapy支持更好些

import scrapy
View Code

二、基本使用

1. 基本命令

Django:
	django-admin startproject mysite
	cd mysite
	python manage.py startapp app01
	

Scrapy：
	# 创建项目，在当前目录中创建中创建一个项目文件（类似于Django）
	scrapy startproject sp1
		生成目录如下：
			sp1
				- sp1
					- spiders　　　　　　　　  目录，放置创建的爬虫应用
					- middlewares.py	中间件
					- items.py			格式化，与pipelines.py一同做持久化
					- pipelines.py		持久化
					- settings.py		配置文件
				- scrapy.cfg 			配置
		
	# 创建爬虫应用
	cd sp1
	scrapy genspider xiaohuar xiaohuar.com		# 创建了xiaohuar.py
	scrapy genspider baidu baidu.com		# 创建了baidu.py
	
	# 展示爬虫应用列表
	scrapy list

	# 执行爬虫，进入project
	scrapy crawl baidu
	scrapy crawl baidu --nolog

文件说明：

  • scrapy.cfg  项目的主配置信息。（真正爬虫相关的配置信息在settings.py文件中）
  • items.py    设置数据存储模板，用于结构化数据，如：Django的Model
  • pipelines    数据处理行为，如：一般结构化的数据持久化
  • settings.py 配置文件，如：递归的层数、并发数，延迟下载等
  • spiders      爬虫目录，如：创建文件，编写爬虫规则

注意：一般创建爬虫文件时，以网站域名命名

2. 基本操作

2.1  selector作筛选

hxs = Selector(response=response)
# print(hxs)
user_list = hxs.xpath('//div[@class="item masonry_brick"]')
for item in user_list:
    price = item.xpath('./span[@class="price"]/text()').extract_first()
    url = item.xpath('div[@class="item_t"]/div[@class="class"]//a/@href').extract_first()
    print(price,url)

result = hxs.xpath('/a[re:test(@href,"http://www.xiaohuar.com/list-1-\d+.html")]/@href')
print(result)
result = ['http://www.xiaohuar.com/list-1-1.html','http://www.xiaohuar.com/list-1-2.html']
View Code

2.2 yield Request(url=url,callback=self.parse) 　　# 迭代去执行

2.3 代码的实现

# -*- coding: utf-8 -*-
import scrapy

class BaiduSpider(scrapy.Spider):
    name = 'baidu'                          # 爬虫应用的名称，通过此名称启动爬虫命令
    allowed_domains = ['baidu.com']         # 允许的域名
    start_urls = ['http://baidu.com/']     # 起始URL

    def parse(self, response):
        print(response.text)
        print(response.body)
baidu.py
import scrapy
from scrapy.selector import HtmlXPathSelector,Selector
from scrapy.http import Request

class XiaohuarSpider(scrapy.Spider):
    name = 'xiaohuar'
    allowed_domains = ['xiaohuar.com']
    start_urls = ['http://www.xiaohuar.com/hua/']            # 起始url

    def parse(self, response):
        # 要废弃
        # hxs = HtmlXPathSelector(response)     # 拿到的内容response转换成对象
        # print(hxs)
        # result = hxs.select('//a[@class="item_list"]')        # select：表示查找；//a :是找页面所有的a标签
        ## result = hxs.select('//a[@class="item_list"]').extract()        # .extract()使返回的值result不是对象，而是列表[<a></a>,<a></a>...]
        ## result = hxs.select('//a[@class="item_list"]').extract_one()        # 拿第一个
        ## result = hxs.select('//a[@class="item_list"]/@href').extract_one()        # 表示拿href属性
        ## result = hxs.select('//a[@class="item_list"]/text()').extract_one()        # 表示拿文本内容

        ############################# 以上写法不推荐 #############################


        ############################### 推荐以下方式 ##############################

        hxs = Selector(response=response)
        # print(hxs)
        user_list = hxs.xpath('//div[@class="item masonry_brick"]')     # 拿到的是对象，但可以对这个对象进行循环。找到class="item masonry_brick"的所有div标签
        for item in user_list:                                              # 每个item也是对象
            price = item.xpath('.//span[@class="price"]/text()').extract_first()     # 相对于当前标签的找子子孙孙使用.//span...
            # price = item.xpath('//span[@class="price"]/text()').extract_first()是错误的,因为//span...是向整个html里找
            url = item.xpath('div[@class="item_t"]/div[@class="class"]//a/@href').extract_first()
            # / 表示去儿子里找，//表示到子子孙孙里找。但必须是在内部才有意义。最外层//和/ 都是有特殊意义
            print(price,url)
            
        # 上面找的只是第一页索引的内容，下面找的是分页的内容
        result = hxs.xpath('/a[re:test(@href,"http://www.xiaohuar.com/list-1-\d+.html")]/@href')    # re:test(） 正则查找
        print(result)
        result = ['http://www.xiaohuar.com/list-1-1.html','http://www.xiaohuar.com/list-1-2.html']

        # 规则
        for url in result:
            yield Request(url=url,callback=self.parse)      # yield Request(url=url) 只是把url封装起来放到调度器里了，callback=self.parse源源不断的发请求，迭代去执行
xiaohuar.py

补充：

选择器：
	//			# 子子孙孙
        /			# 儿子
        /@属性名	# 取属性
        /text()		# 取文本

	
特殊：
	item.xpath('./')	# 相对当前子孙中找
	item.xpath('a')		# 相对当前儿子中找

　　

三、深入了解

（一）以下内容 以登录抽屉并点赞来举例进行深入了解

1. 起始URL

不指明callback=self.parse1情况下，默认下载完后执行 parse函数

import scrapy
from scrapy.http import Request

class ChoutiSpider(scrapy.Spider):
	name = 'chouti'
	allowed_domains = ['chouti.com']
	start_urls = ['http://chouti.com/']

	def start_requests(self):       # 看源码，如果我们没有start_requests函数，默认会执行继承的类scrapy.Spider里的start_requests方法
		for url in self.start_urls:
			yield Request(url, dont_filter=True,callback=self.parse1)       # dont_filter=True对爬取的url不去重

	def parse1(self, response):
		pass

 

2. 如何发POST请求，携带请求头，cookie，数据

requests.get(params={},headers={},cookies={})
requests.post(params={},headers={},cookies={},data={},json={})

2.1 requests请求相关的参数

url, 
method='GET', 
headers=None, 
body=None,
cookies=None,
...
View Code

2.2 GET请求

url, 
method='GET', 
headers={}, 
cookies={}, cookiejar            # cookies可以是字典也可以是cookiejar对象
View Code

2.3 POST请求

url, 
method='GET', 
headers={}, 
cookies={}, cookiejar            # cookies可以是字典也可以是cookiejar对象
body=None,                        # 请求体
    请求头application/x-www-form-urlencoded; charset=UTF-8格式下，数据"phone=86155fa&password=asdf&oneMonth=1" 
    请求头json格式application/json; charset=UTF-8，数据时字典格式"{k1:'v1','k2':'v2'}"
    
    当请求头application/x-www-form-urlencoded; charset=UTF-8格式下，form_data = {'user':'xyp','pwd': 123}需要for循环拼接成"user=xyp$pwd=123"
    但scrapy框架提供了模块可以自动完成拼接
        import urllib.parse
        data = urllib.parse.urlencode({'k1':'v1','k2':'v2'})
        print(data)
        # ---> "k1=v1&k2=v2"  
         
        
    请求头json格式application/json; charset=UTF-8格式下
        json.dumsp({k1:'v1','k2':'v2'})
        
        "{k1:'v1','k2':'v2'}"
View Code

2.4 POST请求示例

 Request(
    url='http://dig.chouti.com/login',
    method='POST',
    headers={'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8'},
    body='phone=8615131255089&password=pppppppp&oneMonth=1',
    callback=self.check_login
)
View Code

2.5 cookie

Request(
    url='http://dig.chouti.com/login',
    method='POST',
    headers={'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8'},
    body='phone=8615131255089&password=pppppppp&oneMonth=1',
    cookies=self.cookie_dict,
    callback=self.check_login
)
View Code

具体代码实现：

#以下代码是循环不停的，加上去重操作
# -*- coding: utf-8 -*-
import scrapy
from scrapy.http import Request
from scrapy.selector import Selector

class ChoutiSpider(scrapy.Spider):
    name = 'chouti'
    allowed_domains = ['chouti.com']
    start_urls = ['http://chouti.com/']
    cookie_dict = {}
    """
    1. 发送一个GET请求,抽屉
       获取cookie
       
    2. 用户密码POST登录：携带上一次cookie
       返回值：9999表示登录成功
       
    3. 为所欲为，携带cookie，点赞
    """
    def start_requests(self):       # 看源码，如果我们没有start_requests函数，默认会执行继承的类scrapy.Spider里的start_requests方法
        for url in self.start_urls:
            yield Request(url, dont_filter=True,callback=self.parse1)       # dont_filter=True对爬取的url不去重

    def parse1(self,response):
        # response.text 首页所有内容
        from scrapy.http.cookies import CookieJar
        cookie_jar = CookieJar() # 对象，对象中封装了 cookies
        cookie_jar.extract_cookies(response, response.request) # 去响应中获取cookies

        for k, v in cookie_jar._cookies.items():
            for i, j in v.items():
                for m, n in j.items():
                    self.cookie_dict[m] = n.value
        post_dict = {
            'phone': '8615131255089',
            'password': 'woshiniba',
            'oneMonth': 1,
        }
        import urllib.parse

        # 目的：发送POST进行登录
        yield Request(
            url="http://dig.chouti.com/login",
            method='POST',
            cookies=self.cookie_dict,       # 或者cookies=self.cookie_jar 也行
            body=urllib.parse.urlencode(post_dict),     # 要发送的body数据
            headers={'Content-Type':'application/x-www-form-urlencoded; charset=UTF-8'},
            callback=self.parse2                        # 回调函数
        )

    def parse2(self,response):
        print(response.text)        # 这里需根据response判断是否登录成功，此处省略判断
        # 获取新闻列表
        yield Request(url='http://dig.chouti.com/',cookies=self.cookie_dict,callback=self.parse3)

    def parse3(self,response):

        # 找div，class=part2, 获取share-linkid属性，得到文章id
        hxs = Selector(response)
        link_id_list = hxs.xpath('//div[@class="part2"]/@share-linkid').extract()       # 取到当前页面所有的文章id
        print(link_id_list)
        for link_id in link_id_list:
            # 获取每一个ID去点赞
            base_url = "http://dig.chouti.com/link/vote?linksId=%s" %(link_id,)
            yield Request(url=base_url,method="POST",cookies=self.cookie_dict,callback=self.parse4)


        #################### 以上只是把首页文章全部点赞 ####################
        
        
        ####################### 分页每个文章都点赞 ####################### 
        
        page_list = hxs.xpath('//div[@id="dig_lcpage"]//a/@href').extract()     # 拿到所有的页码
        for page in page_list:
            #page ： /all/hot/recent/2
            page_url = "http://dig.chouti.com%s" %(page,)
            yield Request(url=page_url,method='GET',callback=self.parse3)       # 循环不同页码点赞

    def parse4(self, response):
        print(response.text)
自动登录抽屉并点赞

 

 

（二）以下内容 以获取煎蛋文章标题和url来举例进行持久化的了解

3. 持久化

3.1 获取煎蛋文章标题和url：具体代码及持久化详细注释

# -*- coding: utf-8 -*-
import scrapy
from scrapy.http import Request
from scrapy.selector import Selector

class JianDanSpider(scrapy.Spider):
    name = 'jiandan'
    allowed_domains = ['jandan.net']
    start_urls = ['http://jandan.net/']

    def start_requests(self):
        for url in self.start_urls:
            yield Request(url, dont_filter=True,callback=self.parse1)
    def parse1(self,response):
        # response.text 首页所有内容
        hxs = Selector(response)
        a_list = hxs.xpath('//div[@class="indexs"]/h2')
        for tag in a_list:
            url = tag.xpath('./a/@href').extract_first()
            text = tag.xpath('./a/text()').extract_first()
            from ..items import Sp2Item
            yield Sp2Item(url=url,text=text)        # 创建特殊的对象直接交给pipeline，没有做持久化操作，只是把工作转交给了pipeline
        #以上获取的是首页文章的文本和url
        # 获取页码 [url,url]
        """
        for url in url_list:
            yield Request(url=url,callback=self.parse1)
        """
jiandan.py
import scrapy

class Sp2Item(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    url = scrapy.Field()
    text = scrapy.Field()
items.py
# -*- coding: utf-8 -*-

# Define your item pipelines here
#
# Don't forget to add your pipeline to the ITEM_PIPELINES setting
# See: http://doc.scrapy.org/en/latest/topics/item-pipeline.html


class Sp2Pipeline(object):
    def __init__(self):
        self.f = None

    def process_item(self, item, spider):
        """

        :param item:  爬虫中yield回来的对象
        :param spider: 爬虫对象 obj = JianDanSpider()
        :return:
        """
        if spider.name == 'jiadnan':
            pass
        print(item)
        self.f.write('....')
        # 将item传递给下一个pipeline的process_item方法
        # return item
        # from scrapy.exceptions import DropItem
        # raise DropItem()  下一个pipeline的process_item方法不在执行

    @classmethod
    def from_crawler(cls, crawler):
        """
        初始化时候，用于创建pipeline对象
        :param crawler:
        :return:
        """
        # val = crawler.settings.get('MMMM')
        print('执行pipeline的from_crawler，进行实例化对象')
        return cls()

    def open_spider(self,spider):
        """
        爬虫开始执行时，调用
        :param spider:
        :return:
        """
        print('打开爬虫')
        self.f = open('a.log','a+')

    def close_spider(self,spider):
        """
        爬虫关闭时，被调用
        :param spider:
        :return:
        """
        self.f.close()
pipelines.py
ITEM_PIPELINES = {
           'sp2.pipelines.Sp2Pipeline': 300,        # 300是优先级
        }
settings.py

3.2 总结

① pipeline执行的前提

- spider中yield Item对象
- settings中注册
	ITEM_PIPELINES = {
	   'sp2.pipelines.Sp2Pipeline': 300,		# 300为优先级，越小越先执行
	   'sp2.pipelines.Sp3Pipeline': 100,
	}

② 编写pipeline

class Sp2Pipeline(object):
    def __init__(self):
        self.f = None

    def process_item(self, item, spider):
        """

        :param item:  爬虫中yield回来的对象
        :param spider: 爬虫对象 obj = JianDanSpider()
        :return:
        """
        print(item)
        self.f.write('....')
        return item
        # from scrapy.exceptions import DropItem
        # raise DropItem()  下一个pipeline的process_item方法不在执行

    @classmethod
    def from_crawler(cls, crawler):
        """
        初始化时候，用于创建pipeline对象
        :param crawler:
        :return:
        """
        # val = crawler.settings.get('MMMM')
        print('执行pipeline的from_crawler，进行实例化对象')
        return cls()

    def open_spider(self,spider):
        """
        爬虫开始执行时，调用
        :param spider:
        :return:
        """
        print('打开爬虫')
        self.f = open('a.log','a+')

    def close_spider(self,spider):
        """
        爬虫关闭时，被调用
        :param spider:
        :return:
        """
        self.f.close()
View Code
当注册Sp2Pipeline和Sp3Pipeline时，先执行优先级高的__init__函数初始化方法，from_crawler方法，open_spider方法。但是不继续执行优先级高的爬虫方法。
而是等优先级低的执行完__init__函数初始化方法，from_crawler方法，open_spider方法后才会执行爬虫方法。

PipeLine是全局生效，所有爬虫都会执行，个别做特殊操作： 通过spider.name判断

③ pipelines.py可以自定义的方法，及程序运行顺序　

# class CustomPipeline(object):
#     def __init__(self,val):
#         self.val = val
#
#     def process_item(self, item, spider):
#         # 操作并进行持久化
#
#         # return表示会被后续的pipeline继续处理
#         return item
#
#         # 表示将item丢弃，不会被后续pipeline处理
#         # raise DropItem()
#
#     @classmethod
#     def from_crawler(cls, crawler):
#         """
#         初始化时候，用于创建pipeline对象
#         :param crawler:
#         :return:
#         """
#         val = crawler.settings.get('MMMM')
#         return cls(val)
#
#     def open_spider(self,spider):
#         """
#         爬虫开始执行时，调用
#         :param spider:
#         :return:
#         """
#         print('000000')
#
#     def close_spider(self,spider):
#         """
#         爬虫关闭时，被调用
#         :param spider:
#         :return:
#         """
#         print('111111')

"""
检测 CustomPipeline类中是否有 from_crawler方法
如果有：
       obj = 类.from_crawler()
如果没有：
       obj = 类()
obj.open_spider()

while True:
    爬虫运行，并且执行parse各种各样的爬虫方法，yield item
    obj.process_item()

obj.close_spider()    

"""
View Code

以上以例子为了解的内容结束。

 

 

4. 自定义去重规则

4.1 配置文件中指定

scrapy默认使用 scrapy.dupefilter.RFPDupeFilter 进行去重，默认在settings相关配置有：
	DUPEFILTER_CLASS = 'scrapy.dupefilter.RFPDupeFilter'
	DUPEFILTER_DEBUG = False
	JOBDIR = "保存范文记录的日志路径，如：/root/"  # 最终路径为 /root/requests.seen

4.2 自定义URL去重操作

class RepeatUrl:
    def __init__(self):
        self.visited_url = set() # 放在当前服务的内存

    @classmethod
    def from_settings(cls, settings):
        """
        初始化时，调用
        :param settings:
        :return:
        """
        return cls()

    def request_seen(self, request):
        """
        检测当前请求是否已经被访问过
        :param request:
        :return: True表示已经访问过；False表示未访问过
        """
        if request.url in self.visited_url:
            return True
        self.visited_url.add(request.url)
        return False

    def open(self):
        """
        开始爬去请求时，调用
        :return:
        """
        print('open replication')

    def close(self, reason):
        """
        结束爬虫爬取时，调用
        :param reason:
        :return:
        """
        print('close replication')

    def log(self, request, spider):
        """
        记录日志
        :param request:
        :param spider:
        :return:
        """
        print('repeat', request.url)
rep.py
DUPEFILTER_CLASS = 'sp2.rep.RepeatUrl'
settings.py

 

 

5. 自定义扩展【基于信号】

from scrapy import signals

class MyExtension(object):
    def __init__(self, value):
        self.value = value

    @classmethod
    def from_crawler(cls, crawler):
        val = crawler.settings.getint('MMMM')
        ext = cls(val)

        # 在scrapy中注册信号： spider_opened
        crawler.signals.connect(ext.opened, signal=signals.spider_opened)        # ext.opened触发信号时执行的函数 
                
        # 在scrapy中注册信号： spider_closed
        crawler.signals.connect(ext.closed, signal=signals.spider_closed)
        
        return ext

    def opened(self, spider):
        print('open')

    def closed(self, spider):
        print('close')
extends.py
EXTENSIONS = {
   # 'scrapy.extensions.telnet.TelnetConsole': None,
}
settings.py注册

 

6. 中间件

6.1 爬虫中间件

SPIDER_MIDDLEWARES = {
   'sp3.middlewares.Sp3SpiderMiddleware': 543,
}
settings.py注册
class Sp3SpiderMiddleware(object):

    def process_spider_input(self,response, spider):
        """
        下载完成，执行，然后交给parse处理
        :param response: 
        :param spider: 
        :return: 
        """
        pass

    def process_spider_output(self,response, result, spider):
        """
        spider处理完成，返回时调用
        :param response:
        :param result:
        :param spider:
        :return: 必须返回包含 Request 或 Item 对象的可迭代对象(iterable)
        """
        return result

    def process_spider_exception(self,response, exception, spider):
        """
        异常调用
        :param response:
        :param exception:
        :param spider:
        :return: None,继续交给后续中间件处理异常；含 Response 或 Item 的可迭代对象(iterable)，交给调度器或pipeline
        """
        return None


    def process_start_requests(self,start_requests, spider):
        """
        爬虫启动时调用
        :param start_requests:
        :param spider:
        :return: 包含 Request 对象的可迭代对象
        """
        return start_requests
middlewares.py

6.2 下载中间件

DOWNLOADER_MIDDLEWARES = {
   'sp3.middlewares.DownMiddleware1': 543,
}
settings.py注册
class DownMiddleware1(object):
    def process_request(self, request, spider):
        """
        请求需要被下载时，经过所有下载器中间件的process_request调用
        :param request: 
        :param spider: 
        :return:  
            None,继续后续中间件去下载；
            Response对象，停止process_request的执行，开始执行process_response
            Request对象，停止中间件的执行，将Request重新调度器
            raise IgnoreRequest异常，停止process_request的执行，开始执行process_exception
        """
        
        
        """
        from scrapy.http import Request
        # print(request)
        # request.method = "POST"
        request.headers['proxy'] = "{'ip_port': '111.11.228.75:80', 'user_pass': ''},"
        return None
        """
        
        
        """
        from scrapy.http import Response
        import requests
        v = request.get('http://www.baidu.com')
        data = Response(url='xxxxxxxx',body=v.content,request=request)
        return data
         """
        
        
        pass



    def process_response(self, request, response, spider):
        """
        spider处理完成，返回时调用
        :param response:
        :param result:
        :param spider:
        :return: 
            Response 对象：转交给其他中间件process_response
            Request 对象：停止中间件，request会被重新调度下载
            raise IgnoreRequest 异常：调用Request.errback
        """
        print('response1')
        return response

    def process_exception(self, request, exception, spider):
        """
        当下载处理器(download handler)或 process_request() (下载中间件)抛出异常
        :param response:
        :param exception:
        :param spider:
        :return: 
            None：继续交给后续中间件处理异常；
            Response对象：停止后续process_exception方法
            Request对象：停止中间件，request将会被重新调用下载
        """
        return None
middlewares.py

 

 

7. 自定义命令【scrapy crawl baidu看源码的入口】

在spiders同级创建任意目录，如：commands
在其中创建 crawlall.py 文件 （此处文件名就是自定义的命令）

class Command(ScrapyCommand):

    requires_project = True

    def syntax(self):
        return '[options]'

    def short_desc(self):
        return 'Runs all of the spiders'

    def run(self, args, opts):
        # 爬虫列表
        spider_list = self.crawler_process.spiders.list()
        for name in spider_list:
            print(name)                                                # #
            # 初始化爬虫
            self.crawler_process.crawl(name, **opts.__dict__)
        # 开始执行所有的爬虫
        self.crawler_process.start()
crawlall.py
在settings.py 中添加配置 COMMANDS_MODULE = '项目名称.目录名称'
在项目目录执行命令：scrapy crawlall 
		
就多了命令：scrapy crawlall		
scrapy crawlall	--nolog	 	#---> xxx
scrapy genspider ooo ooo.com
scrapy crawlall	--nolog	 	
'''
	---> xxx
		 ooo
'''

 

 

 

8. 其他（scrapy配置文件）

# -*- coding: utf-8 -*-

# Scrapy settings for step8_king project
#
# For simplicity, this file contains only settings considered important or
# commonly used. You can find more settings consulting the documentation:
#
#     http://doc.scrapy.org/en/latest/topics/settings.html
#     http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
#     http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html

# 1. 爬虫名称
BOT_NAME = 'step8_king'    


# 2. 爬虫应用路径
SPIDER_MODULES = ['step8_king.spiders']
NEWSPIDER_MODULE = 'step8_king.spiders'


# Crawl responsibly by identifying yourself (and your website) on the user-agent
# 3. 客户端 user-agent请求头                
# USER_AGENT = 'step8_king (+http://www.yourdomain.com)'                # user-agent客户端设备


# Obey robots.txt rules
# 4. 禁止爬虫配置
# ROBOTSTXT_OBEY = False            # 是否遵循爬虫协议                    


# Configure maximum concurrent requests performed by Scrapy (default: 16)
# 5. 并发请求数
# CONCURRENT_REQUESTS = 4


# Configure a delay for requests for the same website (default: 0)
# See http://scrapy.readthedocs.org/en/latest/topics/settings.html#download-delay
# See also autothrottle settings and docs
# 6. 延迟下载秒数
# DOWNLOAD_DELAY = 2


# The download delay setting will honor only one of:        # 如果设置单域名访问并发数和单IP访问并发数会把第五条并发请求数覆盖
# 7. 单域名访问并发数，并且延迟下次秒数也应用在每个域名
# CONCURRENT_REQUESTS_PER_DOMAIN = 2
# 单IP访问并发数，如果有值则忽略：CONCURRENT_REQUESTS_PER_DOMAIN，并且延迟下次秒数也应用在每个IP
# CONCURRENT_REQUESTS_PER_IP = 3


# Disable cookies (enabled by default)
# 8. 是否支持cookie，cookiejar进行操作cookie
# COOKIES_ENABLED = True
# COOKIES_DEBUG = True


# Disable Telnet Console (enabled by default)
# 9. Telnet用于查看当前爬虫的信息，操作爬虫等...            # 对于你的爬虫进行监控
#    使用telnet ip port ，然后通过命令操作
# TELNETCONSOLE_ENABLED = True
# TELNETCONSOLE_HOST = '127.0.0.1'
# TELNETCONSOLE_PORT = [6023,]


# 10. 默认请求头，设置所有的请求头，但是优先级比较低，在爬虫名.py文件中设置请求头优先级高一些
# 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',
# }


# Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
# 11. 定义pipeline处理请求
# ITEM_PIPELINES = {
#    'step8_king.pipelines.JsonPipeline': 700,
#    'step8_king.pipelines.FilePipeline': 500,
# }



# 12. 自定义扩展，基于信号进行调用
# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
# EXTENSIONS = {
#     # 'step8_king.extensions.MyExtension': 500,
# }


# 13. 爬虫允许的最大深度，可以通过meta查看当前深度；0表示无深度
# DEPTH_LIMIT = 3


# 14. 爬取时，0表示深度优先Lifo(默认)；1表示广度优先FiFo

# 后进先出，深度优先
# DEPTH_PRIORITY = 0
# SCHEDULER_DISK_QUEUE = 'scrapy.squeue.PickleLifoDiskQueue'
# SCHEDULER_MEMORY_QUEUE = 'scrapy.squeue.LifoMemoryQueue'
# 先进先出，广度优先

# DEPTH_PRIORITY = 1
# SCHEDULER_DISK_QUEUE = 'scrapy.squeue.PickleFifoDiskQueue'
# SCHEDULER_MEMORY_QUEUE = 'scrapy.squeue.FifoMemoryQueue'


# 15. 调度器队列
# SCHEDULER = 'scrapy.core.scheduler.Scheduler'        # scrapy框架默认的调度器，与14条队列结合
# from scrapy.core.scheduler import Scheduler


# 16. 访问URL去重
# DUPEFILTER_CLASS = 'step8_king.duplication.RepeatUrl'


# Enable and configure the AutoThrottle extension (disabled by default)
# See http://doc.scrapy.org/en/latest/topics/autothrottle.html

"""
17. 自动限速算法
    from scrapy.contrib.throttle import AutoThrottle
    自动限速设置
    1. 获取最小延迟 DOWNLOAD_DELAY
    2. 获取最大延迟 AUTOTHROTTLE_MAX_DELAY
    3. 设置初始下载延迟 AUTOTHROTTLE_START_DELAY
    4. 当请求下载完成后，获取其"连接"时间 latency，即：请求连接到接受到响应头之间的时间
    5. 用于计算的... AUTOTHROTTLE_TARGET_CONCURRENCY
    target_delay = latency / self.target_concurrency
    new_delay = (slot.delay + target_delay) / 2.0 # 表示上一次的延迟时间
    new_delay = max(target_delay, new_delay)
    new_delay = min(max(self.mindelay, new_delay), self.maxdelay)
    slot.delay = new_delay
"""

# 开始自动限速
# AUTOTHROTTLE_ENABLED = True
# The initial download delay
# 初始下载延迟
# AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
# 最大下载延迟
# AUTOTHROTTLE_MAX_DELAY = 10
# The average number of requests Scrapy should be sending in parallel to each remote server
# 平均每秒并发数
# AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0

# Enable showing throttling stats for every response received:
# 是否显示
# AUTOTHROTTLE_DEBUG = True

# Enable and configure HTTP caching (disabled by default)
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html#httpcache-middleware-settings


"""
18. 启用缓存
    目的用于将已经发送的请求或相应缓存下来，以便以后使用
    
    from scrapy.downloadermiddlewares.httpcache import HttpCacheMiddleware
    from scrapy.extensions.httpcache import DummyPolicy
    from scrapy.extensions.httpcache import FilesystemCacheStorage
"""
# 是否启用缓存策略
# HTTPCACHE_ENABLED = True

# 缓存策略：所有请求均缓存，下次在请求直接访问原来的缓存即可
# HTTPCACHE_POLICY = "scrapy.extensions.httpcache.DummyPolicy"
# 缓存策略：根据Http响应头：Cache-Control、Last-Modified 等进行缓存的策略
# HTTPCACHE_POLICY = "scrapy.extensions.httpcache.RFC2616Policy"

# 缓存超时时间
# HTTPCACHE_EXPIRATION_SECS = 0

# 缓存保存路径
# HTTPCACHE_DIR = 'httpcache'

# 缓存忽略的Http状态码
# HTTPCACHE_IGNORE_HTTP_CODES = []

# 缓存存储的插件
# HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'


"""
19. 代理，需要在环境变量中设置
    from scrapy.contrib.downloadermiddleware.httpproxy import HttpProxyMiddleware
    
    方式一：使用默认
        os.environ
        {
            http_proxy:http://root:woshiniba@192.168.11.11:9999/
            https_proxy:http://192.168.11.11:9999/
        }
    方式二：使用自定义下载中间件
    
    def to_bytes(text, encoding=None, errors='strict'):
        if isinstance(text, bytes):
            return text
        if not isinstance(text, six.string_types):
            raise TypeError('to_bytes must receive a unicode, str or bytes '
                            'object, got %s' % type(text).__name__)
        if encoding is None:
            encoding = 'utf-8'
        return text.encode(encoding, errors)
        
    class ProxyMiddleware(object):
        def process_request(self, request, spider):
            PROXIES = [
                {'ip_port': '111.11.228.75:80', 'user_pass': ''},
                {'ip_port': '120.198.243.22:80', 'user_pass': ''},
                {'ip_port': '111.8.60.9:8123', 'user_pass': ''},
                {'ip_port': '101.71.27.120:80', 'user_pass': ''},
                {'ip_port': '122.96.59.104:80', 'user_pass': ''},
                {'ip_port': '122.224.249.122:8088', 'user_pass': ''},
            ]
            proxy = random.choice(PROXIES)
            if proxy['user_pass'] is not None:
                request.meta['proxy'] = to_bytes（"http://%s" % proxy['ip_port']）
                encoded_user_pass = base64.encodestring(to_bytes(proxy['user_pass']))
                request.headers['Proxy-Authorization'] = to_bytes('Basic ' + encoded_user_pass)
                print "**************ProxyMiddleware have pass************" + proxy['ip_port']
            else:
                print "**************ProxyMiddleware no pass************" + proxy['ip_port']
                request.meta['proxy'] = to_bytes("http://%s" % proxy['ip_port'])
    
    DOWNLOADER_MIDDLEWARES = {
       'step8_king.middlewares.ProxyMiddleware': 500,
    }
    
"""



"""
20. Https访问
    Https访问时有两种情况：
    1. 要爬取网站使用的可信任证书(默认支持)
        DOWNLOADER_HTTPCLIENTFACTORY = "scrapy.core.downloader.webclient.ScrapyHTTPClientFactory"
        DOWNLOADER_CLIENTCONTEXTFACTORY = "scrapy.core.downloader.contextfactory.ScrapyClientContextFactory"
        
    2. 要爬取网站使用的自定义证书
        DOWNLOADER_HTTPCLIENTFACTORY = "scrapy.core.downloader.webclient.ScrapyHTTPClientFactory"
        DOWNLOADER_CLIENTCONTEXTFACTORY = "step8_king.https.MySSLFactory"
        
        # https.py
        from scrapy.core.downloader.contextfactory import ScrapyClientContextFactory
        from twisted.internet.ssl import (optionsForClientTLS, CertificateOptions, PrivateCertificate)
        
        class MySSLFactory(ScrapyClientContextFactory):
            def getCertificateOptions(self):
                from OpenSSL import crypto
                v1 = crypto.load_privatekey(crypto.FILETYPE_PEM, open('/Users/xyp/client.key.unsecure', mode='r').read())
                v2 = crypto.load_certificate(crypto.FILETYPE_PEM, open('/Users/xyp/client.pem', mode='r').read())
                return CertificateOptions(
                    privateKey=v1,  # pKey对象
                    certificate=v2,  # X509对象
                    verify=False,
                    method=getattr(self, 'method', getattr(self, '_ssl_method', None))
                )
    其他：
        相关类
            scrapy.core.downloader.handlers.http.HttpDownloadHandler
            scrapy.core.downloader.webclient.ScrapyHTTPClientFactory
            scrapy.core.downloader.contextfactory.ScrapyClientContextFactory
        相关配置
            DOWNLOADER_HTTPCLIENTFACTORY
            DOWNLOADER_CLIENTCONTEXTFACTORY

"""



"""
21. 爬虫中间件
    class SpiderMiddleware(object):

        def process_spider_input(self,response, spider):
            '''
            下载完成，执行，然后交给parse处理
            :param response: 
            :param spider: 
            :return: 
            '''
            pass
    
        def process_spider_output(self,response, result, spider):
            '''
            spider处理完成，返回时调用
            :param response:
            :param result:
            :param spider:
            :return: 必须返回包含 Request 或 Item 对象的可迭代对象(iterable)
            '''
            return result
    
        def process_spider_exception(self,response, exception, spider):
            '''
            异常调用
            :param response:
            :param exception:
            :param spider:
            :return: None,继续交给后续中间件处理异常；含 Response 或 Item 的可迭代对象(iterable)，交给调度器或pipeline
            '''
            return None
    
    
        def process_start_requests(self,start_requests, spider):
            '''
            爬虫启动时调用
            :param start_requests:
            :param spider:
            :return: 包含 Request 对象的可迭代对象
            '''
            return start_requests
    
    内置爬虫中间件：
        'scrapy.contrib.spidermiddleware.httperror.HttpErrorMiddleware': 50,
        'scrapy.contrib.spidermiddleware.offsite.OffsiteMiddleware': 500,
        'scrapy.contrib.spidermiddleware.referer.RefererMiddleware': 700,
        'scrapy.contrib.spidermiddleware.urllength.UrlLengthMiddleware': 800,
        'scrapy.contrib.spidermiddleware.depth.DepthMiddleware': 900,

"""
# from scrapy.contrib.spidermiddleware.referer import RefererMiddleware
# Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
SPIDER_MIDDLEWARES = {
   # 'step8_king.middlewares.SpiderMiddleware': 543,
}


"""
22. 下载中间件
    class DownMiddleware1(object):
        def process_request(self, request, spider):
            '''
            请求需要被下载时，经过所有下载器中间件的process_request调用
            :param request:
            :param spider:
            :return:
                None,继续后续中间件去下载；
                Response对象，停止process_request的执行，开始执行process_response
                Request对象，停止中间件的执行，将Request重新调度器
                raise IgnoreRequest异常，停止process_request的执行，开始执行process_exception
            '''
            pass
    
    
    
        def process_response(self, request, response, spider):
            '''
            spider处理完成，返回时调用
            :param response:
            :param result:
            :param spider:
            :return:
                Response 对象：转交给其他中间件process_response
                Request 对象：停止中间件，request会被重新调度下载
                raise IgnoreRequest 异常：调用Request.errback
            '''
            print('response1')
            return response
    
        def process_exception(self, request, exception, spider):
            '''
            当下载处理器(download handler)或 process_request() (下载中间件)抛出异常
            :param response:
            :param exception:
            :param spider:
            :return:
                None：继续交给后续中间件处理异常；
                Response对象：停止后续process_exception方法
                Request对象：停止中间件，request将会被重新调用下载
            '''
            return None

    
    默认下载中间件
    {
        'scrapy.contrib.downloadermiddleware.robotstxt.RobotsTxtMiddleware': 100,
        'scrapy.contrib.downloadermiddleware.httpauth.HttpAuthMiddleware': 300,
        'scrapy.contrib.downloadermiddleware.downloadtimeout.DownloadTimeoutMiddleware': 350,
        'scrapy.contrib.downloadermiddleware.useragent.UserAgentMiddleware': 400,
        'scrapy.contrib.downloadermiddleware.retry.RetryMiddleware': 500,
        'scrapy.contrib.downloadermiddleware.defaultheaders.DefaultHeadersMiddleware': 550,
        'scrapy.contrib.downloadermiddleware.redirect.MetaRefreshMiddleware': 580,
        'scrapy.contrib.downloadermiddleware.httpcompression.HttpCompressionMiddleware': 590,
        'scrapy.contrib.downloadermiddleware.redirect.RedirectMiddleware': 600,
        'scrapy.contrib.downloadermiddleware.cookies.CookiesMiddleware': 700,
        'scrapy.contrib.downloadermiddleware.httpproxy.HttpProxyMiddleware': 750,
        'scrapy.contrib.downloadermiddleware.chunked.ChunkedTransferMiddleware': 830,
        'scrapy.contrib.downloadermiddleware.stats.DownloaderStats': 850,
        'scrapy.contrib.downloadermiddleware.httpcache.HttpCacheMiddleware': 900,
    }

"""
# from scrapy.contrib.downloadermiddleware.httpauth import HttpAuthMiddleware
# Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
# DOWNLOADER_MIDDLEWARES = {
#    'step8_king.middlewares.DownMiddleware1': 100,
#    'step8_king.middlewares.DownMiddleware2': 500,
# }
settings.py

 

以上内容目录结构如下：

 

 

 

四、自己写自己写TinyScrapy框架

1. Twisted使用

# 一个线程并发操作

from twisted.web.client import getPage, defer
from twisted.internet import reactor


def all_done(arg):                            # 所有爬虫执行完后，循环终止
    reactor.stop()

def callback(contents):                        # 每一个爬虫获取结果后自动执行
    print(contents)


deferred_list = []

url_list = ['http://www.bing.com', 'http://www.baidu.com', ]
for url in url_list:
    deferred = getPage(bytes(url, encoding='utf8'))
    deferred.addCallback(callback)
    deferred_list.append(deferred)

dlist = defer.DeferredList(deferred_list)
dlist.addBoth(all_done)

reactor.run()                                # 事件循环
s1.py：基本使用
from twisted.web.client import getPage, defer
from twisted.internet import reactor

def all_done(arg):
    reactor.stop()

def onedone(response):
    print(response)


@defer.inlineCallbacks
def task(url):
    deferred = getPage(bytes(url, encoding='utf8'))
    deferred.addCallback(onedone)
    yield deferred


deferred_list = []

url_list = ['http://www.bing.com', 'http://www.baidu.com', ]
for url in url_list:
    deferred = task(url)        # 把下面注释掉的二行代码写入到函数take中
    # deferred = getPage(url)
    # deferred.addCallback(onedone)
    deferred_list.append(deferred)

dlist = defer.DeferredList(deferred_list)
dlist.addBoth(all_done)

reactor.run()
s2.py：基于装饰器（一）
from twisted.web.client import getPage, defer
from twisted.internet import reactor

def all_done(arg):
    reactor.stop()


def onedone(response):
    print(response)


@defer.inlineCallbacks
def task():                                                                    # task函数中执行第一个yield，第二个yield也会执行
    deferred2 = getPage(bytes("http://www.baidu.com", encoding='utf8'))
    deferred2.addCallback(onedone)
    yield deferred2                                                            


    deferred1 = getPage(bytes("http://www.google.com", encoding='utf8'))
    deferred1.addCallback(onedone)
    yield deferred1


ret = task()
ret.addBoth(all_done)        # task中二个yield都执行完了会执行all_done

reactor.run()
s3.py：基于装饰器（二）
from twisted.web.client import getPage, defer
from twisted.internet import reactor

def all_done(arg):
    reactor.stop()


def onedone(response):
    print(response)


@defer.inlineCallbacks
def task():
    deferred2 = getPage(bytes("http://www.baidu.com", encoding='utf8'))
    deferred2.addCallback(onedone)                    
    yield deferred2

    stop_deferred = defer.Deferred()        # 创建了空的Deferred对象，永远夯住不终止
    # stop_deferred.callback(None)            # 人为中止调用callback
    yield stop_deferred


ret = task()
ret.addBoth(all_done)

reactor.run()                # 事件循环不停的运行不终止
s4.py：基于装饰器，永恒循环
# reactor.callLater(0) # 结束当前Deferred，事件循环也会终止

from twisted.web.client import getPage, defer
from twisted.internet import reactor

running_list = []
stop_deferred = None

def all_done(arg):
    reactor.stop()

def onedone(response,url):
    print(response)
    running_list.remove(url)

def check_empty(response):
    if not running_list:
        stop_deferred.callback(None)

@defer.inlineCallbacks
def open_spider(url):
    deferred2 = getPage(bytes(url, encoding='utf8'))
    deferred2.addCallback(onedone, url)
    deferred2.addCallback(check_empty)
    yield deferred2

@defer.inlineCallbacks
def stop(url):
    global stop_deferred
    stop_deferred = defer.Deferred()
    yield stop_deferred

@defer.inlineCallbacks
def task(url):
    yield open_spider(url)
    yield stop(url)


running_list.append("http://www.baidu.com")
ret = task("http://www.baidu.com")
ret.addBoth(all_done)

reactor.run()
s5.py：基于装饰器，执行完毕后停止事件循环
from twisted.web.client import getPage, defer
from twisted.internet import reactor

class ExecutionEngine(object):
    def __init__(self):
        self.stop_deferred = None
        self.running_list = []

    def onedone(self,response,url):
        print(response)
        self.running_list.remove(url)

    def check_empty(self,response):
        if not self.running_list:
            self.stop_deferred.callback(None)

    @defer.inlineCallbacks
    def open_spider(self,url):
        deferred2 = getPage(bytes(url, encoding='utf8'))
        deferred2.addCallback(self.onedone, url)
        deferred2.addCallback(self.check_empty)
        yield deferred2

    @defer.inlineCallbacks
    def stop(self,url):
        self.stop_deferred = defer.Deferred()
        yield self.stop_deferred

@defer.inlineCallbacks
def task(url):
    engine = ExecutionEngine()
    engine.running_list.append(url)

    yield engine.open_spider(url)
    yield engine.stop(url)

def all_done(arg):
    reactor.stop()

if __name__ == '__main__':

    ret = task("http://www.baidu.com")
    ret.addBoth(all_done)

    reactor.run()
s6.py：基于装饰器，执行完毕后停止事件循环，将 s5.py封装成类

2. 模拟scrapy

#!/usr/bin/env python
# -*- coding:utf-8 -*-
from twisted.web.client import getPage, defer
from twisted.internet import reactor
import queue


class Request(object):
    def __init__(self, url, callback):
        self.url = url
        self.callback = callback


class Scheduler(object):
    def __init__(self, engine):
        self.q = queue.Queue()
        self.engine = engine

    def enqueue_request(self, request):
        self.q.put(request)

    def next_request(self):
        try:
            req = self.q.get(block=False)
        except Exception as e:
            req = None

        return req

    def size(self):
        return self.q.qsize()


class ExecutionEngine(object):
    def __init__(self):
        self._closewait = None
        self.running = True
        self.start_requests = None
        self.scheduler = Scheduler(self)

        self.inprogress = set()

    def check_empty(self, response):
        if not self.running:
            self._closewait.callback('......')

    def _next_request(self):
        while self.start_requests:
            try:
                request = next(self.start_requests)
            except StopIteration:
                self.start_requests = None
            else:
                self.scheduler.enqueue_request(request)

        print(len(self.inprogress), self.scheduler.size())
        while len(self.inprogress) < 5 and self.scheduler.size() > 0:  # 最大并发数为5

            request = self.scheduler.next_request()
            if not request:
                break

            self.inprogress.add(request)
            d = getPage(bytes(request.url, encoding='utf-8'))
            d.addBoth(self._handle_downloader_output, request)
            d.addBoth(lambda x, req: self.inprogress.remove(req), request)
            d.addBoth(lambda x: self._next_request())
        
        if len(self.inprogress) == 0 and self.scheduler.size() == 0:
            self._closewait.callback(None)

    def _handle_downloader_output(self, response, request):
        """
        获取内容，执行回调函数，并且把回调函数中的返回值获取，并添加到队列中
        :param response: 
        :param request: 
        :return: 
        """
        import types

        gen = request.callback(response)
        if isinstance(gen, types.GeneratorType):
            for req in gen:
                self.scheduler.enqueue_request(req)

    @defer.inlineCallbacks
    def start(self):
        self._closewait = defer.Deferred()
        yield self._closewait

    @defer.inlineCallbacks
    def open_spider(self, start_requests):
        self.start_requests = start_requests
        yield None
        reactor.callLater(0, self._next_request)


@defer.inlineCallbacks
def crawl(start_requests):
    engine = ExecutionEngine()

    start_requests = iter(start_requests)
    yield engine.open_spider(start_requests)
    yield engine.start()


def _stop_reactor(_=None):
    reactor.stop()


def parse(response):
    for i in range(10):
        yield Request("http://dig.chouti.com/all/hot/recent/%s" % i, callback)

if __name__ == '__main__':
    start_requests = [Request("http://www.baidu.com", parse),Request("http://www.baidu1.com", parse),]


    ret = crawl(start_requests)
    
    ret.addBoth(_stop_reactor)

    reactor.run()
模拟scrapy.py简易版
#!/usr/bin/env python
# -*- coding:utf-8 -*-
from twisted.web.client import getPage, defer
from twisted.internet import reactor
import queue


class Response(object):
    def __init__(self, body, request):
        self.body = body
        self.request = request
        self.url = request.url

    @property
    def text(self):
        return self.body.decode('utf-8')


class Request(object):                                    # 封装url调度器
    def __init__(self, url, callback=None):
        self.url = url
        self.callback = callback


class Scheduler(object):                                # 调度器
    def __init__(self, engine):
        self.q = queue.Queue()
        self.engine = engine

    def enqueue_request(self, request):
        self.q.put(request)

    def next_request(self):
        try:
            req = self.q.get(block=False)
        except Exception as e:
            req = None

        return req

    def size(self):
        return self.q.qsize()


class ExecutionEngine(object):
    def __init__(self):
        self._closewait = None
        self.running = True
        self.start_requests = None
        self.scheduler = Scheduler(self)

        self.inprogress = set()

    def check_empty(self, response):
        if not self.running:
            self._closewait.callback('......')

    def _next_request(self):
        while self.start_requests:
            try:
                request = next(self.start_requests)
            except StopIteration:
                self.start_requests = None
            else:
                self.scheduler.enqueue_request(request)

        while len(self.inprogress) < 5 and self.scheduler.size() > 0:  # 最大并发数为5

            request = self.scheduler.next_request()
            if not request:
                break

            self.inprogress.add(request)
            d = getPage(bytes(request.url, encoding='utf-8'))
            d.addBoth(self._handle_downloader_output, request)
            d.addBoth(lambda x, req: self.inprogress.remove(req), request)
            d.addBoth(lambda x: self._next_request())

        if len(self.inprogress) == 0 and self.scheduler.size() == 0:
            self._closewait.callback(None)

    def _handle_downloader_output(self, body, request):
        """
        获取内容，执行回调函数，并且把回调函数中的返回值获取，并添加到队列中
        :param response: 
        :param request: 
        :return: 
        """
        import types

        response = Response(body, request)
        func = request.callback or self.spider.parse
        gen = func(response)
        if isinstance(gen, types.GeneratorType):
            for req in gen:
                self.scheduler.enqueue_request(req)

    @defer.inlineCallbacks
    def start(self):
        self._closewait = defer.Deferred()
        yield self._closewait

    @defer.inlineCallbacks
    def open_spider(self, spider, start_requests):
        self.start_requests = start_requests
        self.spider = spider
        yield None
        reactor.callLater(0, self._next_request)


class Crawler(object):
    def __init__(self, spidercls):
        self.spidercls = spidercls

        self.spider = None
        self.engine = None

    @defer.inlineCallbacks
    def crawl(self):
        self.engine = ExecutionEngine()
        self.spider = self.spidercls()
        start_requests = iter(self.spider.start_requests())
        yield self.engine.open_spider(self.spider, start_requests)
        yield self.engine.start()


class CrawlerProcess(object):
    def __init__(self):
        self._active = set()
        self.crawlers = set()

    def crawl(self, spidercls, *args, **kwargs):
        crawler = Crawler(spidercls)
        self.crawlers.add(crawler)
        
        d = crawler.crawl(*args, **kwargs)
        self._active.add(d)
        return d

    def start(self):
        dl = defer.DeferredList(self._active)
        dl.addBoth(self._stop_reactor)
        reactor.run()

    def _stop_reactor(self, _=None):
        reactor.stop()


class Spider(object):
    def start_requests(self):
        for url in self.start_urls:
            yield Request(url)


class ChoutiSpider(Spider):
    name = "chouti"
    start_urls = [
        'http://dig.chouti.com/',
    ]

    def parse(self, response):
        print(response.text)


class CnblogsSpider(Spider):
    name = "cnblogs"
    start_urls = [
        'http://www.cnblogs.com/',
    ]

    def parse(self, response):
        print(response.text)


if __name__ == '__main__':

    spider_cls_list = [ChoutiSpider, CnblogsSpider]

    crawler_process = CrawlerProcess()
    for spider_cls in spider_cls_list:
        crawler_process.crawl(spider_cls)

    crawler_process.start()
模拟scrapy.py

 

 

 

posted @ 2016-10-05 18:07  许二哈哈哈  阅读(3093)  评论(0)  编辑  收藏  举报