python爬虫篇之 Scrapy框架

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, 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)。或者发送新的请求
• 项目管道(Pipeline)
  在items被提取后负责处理它们，主要包括清理、验证、持久化（比如存到数据库）等操作
• 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。（最新版本，没有了）

 概括scrapy框架分成几部分：

爬虫，引擎,pipeline，调度器，下载器

持久化：通俗的讲，就是瞬时数据持久化为持久数据。主要应用是将内存中的对象存储在数据库中，或者存储在磁盘文件中、XML数据文件中等等

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.基本使用

1.基本命令

1. 创建爬虫项目
   scrapy startproject 项目名称
   - scrapy startproject sp1
 
2.创建爬虫应用
   cd sp1 
   scrapy genspider baidu baidu.com
   
   PS:
      查看所有命令：scrapy gensipider -l
      查看模板命令：scrapy gensipider -d 模板名称
 
3. scrapy crawl 爬虫应用名称
   - 运行单独爬虫应用

4. scrapy list
   - 展示爬虫应用列表

 2.项目结构以及爬虫应用简介

project_name/
   scrapy.cfg
   project_name/
       __init__.py
       items.py
       pipelines.py
       settings.py
       spiders/
           __init__.py
           爬虫1.py
           爬虫2.py
           爬虫3.py

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

import scrapy
 
class XiaoHuarSpider(scrapy.spiders.Spider):
    name = "xiaohuar"                            # 爬虫名称 *****
    allowed_domains = ["xiaohuar.com"]  # 允许的域名
    start_urls = [
        "http://www.xiaohuar.com/hua/",   # 其实URL
    ]
 
    def parse(self, response):
        # 访问起始URL并获取结果后的回调函数

import sys,os
sys.stdout=io.TextIOWrapper(sys.stdout.buffer,encoding='gb18030')

3.小试牛刀

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


class ChoutiSpider(scrapy.Spider):
    # scrapy crawl chouti --nolog,启动爬虫命令
    name = 'chouti'

    #允许的域名
    allowed_domains = ['chouti.com']

    #起始URL
    start_urls = ['http://chouti.com/']

    has_request_set = {}

    def parse(self, response):
        print('response.url',response.url)

        hxs = HtmlXPathSelector(response)
        page_list = hxs.select('//div[@id="dig_lcpage"]//a[re:test(@href,"/all/hot/recent/d+")]/@href').extract()

        for page in page_list:
            page_url = 'http://dig.chouti.com%s'%page
            key = self.md5(page_url)
            if key in self.has_request_set:
                pass
            else:
                self.has_request_set[key] = page_url
                obj = Request(url=page_url, method='GET', callback=self.parse)
                yield obj

    @staticmethod
    def md5(val):
        import hashlib
        ha = hashlib.md5()
        ha.update(bytes(val, encoding='utf-8'))
        key = ha.hexdigest()
        return key

对于上述代码重要之处：

• Request是一个封装用户请求的类，在回调函数中yield该对象表示继续访问
• HtmlXpathSelector用于结构化HTML代码并提供选择器功能

4.Scrapy定制起始URL函数

#-------------标配
import scrapy

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

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



#-------------自定制
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):        ##返回 可迭代对象或生成器
        for url in self.start_urls:
            yield Request(url, dont_filter=True, callback=self.parse1)

    def parse1(self, response):
        pass

5.POST请求，请求头，cookie

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

GET请求:
    url, 
    method='GET', 
    headers={}, 
    cookies={}, cookiejar
        
POST请求:
    url, 
    method='GET', 
    headers={}, 
    cookies={}, cookiejar
    body=None,

#请求头格式一
application/x-www-form-urlencoded; charset=UTF-8
    form_data = {
                'user':'Tom',
                'pwd': 123
               }
import urllib.parse
data = urllib.parse.urlencode({'k1':'v1','k2':'v2'})
                    
 结果："k1=v1&k2=v3"   
    

#请求头格式二                
application/json; charset=UTF-8

    json.dumsp()
    "{k1:'v1','k2':'v2'}"   





示例：
Request(
    url='http://dig.chouti.com/login',
    method='POST',
    headers={'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8'},
    body='phone=861517243291&password=pppppppp&oneMonth=1',
    callback=self.check_login
)

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
       
    3. 为所欲为，携带cookie
    """
    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
        from scrapy.http.cookies import CookieJar
        cookie_jar = CookieJar() # 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,
            body=urllib.parse.urlencode(post_dict),
            headers={'Content-Type':'application/x-www-form-urlencoded; charset=UTF-8'},
            callback=self.parse2
        )

5.选择器

5.格式化处理

　　上述实例只是简单的处理，所以在parse方法中直接处理。如果对于想要获取更多的数据处理，则可以利用Scrapy的items将数据格式化，然后统一交由pipelines来处理。

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)
        # 获取页码 [url,url]
        """
        for url in url_list:
            yield Request(url=url,callback=self.parse1)
        """

import scrapy


class Sp2Item(scrapy.Item):
    # define the fields for your item here like:
    # name = scrapy.Field()
    url = scrapy.Field()
    text = scrapy.Field()

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')    #settings 设置 数据库
        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()





#再加个一个
class Sp3Pipeline(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

    @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()

ITEM_PIPELINES = {
   'sp2.pipelines.Sp2Pipeline': 300,
   'sp2.pipelines.Sp3Pipeline': 100,
}

# 每行后面的整型值，确定了他们运行的顺序，item按数字从低到高的顺序，通过pipeline，通常将这些数字定义在0-1000范围内。（越小越优先）

对于pipeline可以做更多，如下：

from scrapy.exceptions import DropItem

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

    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.getint('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from_crawler方法，yield item
    obj.process_item()

obj.close_spider()    

"""

6.去重

　　scrapy默认使用 scrapy.dupefilter.RFPDupeFilter 进行去重，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

自定义URL去重：

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)
        

在settings.py配置：

DUPEFILTER_CLASS = 'sp1.rep.RepeatUrl'

7.基于信号自定义扩展

利用信号在指定位置注册制定操作

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)
        # 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('基于信号：open')

    def closed(self, spider):
        print('基于信号：close')
  
  
        
#settings.py 配置      
# EXTENSIONS = {
#    'sp1.extends.MyExtension': 100,
# }

#Django的信号：给我们预留的扩展功能。

就是一些动作发生的时候，信号允许特定的发送者去提醒一些接受者。

8.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

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
        """


        #最重要的两种情况
        """
        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
         """

    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')
        # from scrapy.http import Response
        # response.encoding = 'utf-8'
        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

9.自定制命令

• 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）

from scrapy.commands import ScrapyCommand
    from scrapy.utils.project import get_project_settings


    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):
            spider_list = self.crawler_process.spiders.list()
            for name in spider_list:
                self.crawler_process.crawl(name, **opts.__dict__)
            self.crawler_process.start()

• 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

10.代理

本质就是设置请求头

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,
    }
    
"""

#源码（了解）

从模块 进入源码：
from scrapy.downloadermiddlewares.httpproxy import HttpProxyMiddleware

源码：
 def _set_proxy(self, request, scheme):
        creds, proxy = self.proxies[scheme]  #第一个 授权，第二个 代理
        request.meta['proxy'] = proxy
        if creds:
            request.headers['Proxy-Authorization'] = b'Basic ' + creds



from urllib.request import getproxies
源码：
# Proxy handling
def getproxies_environment():

    proxies = {}
  
    for name, value in os.environ.items():
        name = name.lower()
        if value and name[-6:] == '_proxy':
            proxies[name[:-6]] = value
   
   
    if 'REQUEST_METHOD' in os.environ:
        proxies.pop('http', None)
    for name, value in os.environ.items():
        if name[-6:] == '_proxy':        #------》【-6】
            name = name.lower()
            if value:
                proxies[name[:-6]] = value
            else:
                proxies.pop(name[:-6], None)
    return proxies

11、其他

# -*- 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)'

# Obey robots.txt rules
# 4. 禁止爬虫配置
# ROBOTSTXT_OBEY = False

# 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:
# 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...
#    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
# 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'
# 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/wupeiqi/client.key.unsecure', mode='r').read())
                v2 = crypto.load_certificate(crypto.FILETYPE_PEM, open('/Users/wupeiqi/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,
# }

12.TinyScrapy

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



class Request(object):
    def __init__(self, url, callback):
        self.url = url
        self.callback = callback
        self.priority = 0


class HttpResponse(object):
    def __init__(self, content, request):
        self.content = content
        self.request = request


class ChouTiSpider(object):

    def start_requests(self):
        url_list = ['http://www.cnblogs.com/', 'http://www.bing.com']
        for url in url_list:
            yield Request(url=url, callback=self.parse)

    def parse(self, response):
        print(response.request.url)
        # yield Request(url="http://www.baidu.com", callback=self.parse)




from queue import Queue
Q = Queue()


class CallLaterOnce(object):
    def __init__(self, func, *a, **kw):
        self._func = func
        self._a = a
        self._kw = kw
        self._call = None

    def schedule(self, delay=0):
        if self._call is None:
            self._call = reactor.callLater(delay, self)

    def cancel(self):
        if self._call:
            self._call.cancel()

    def __call__(self):
        self._call = None
        return self._func(*self._a, **self._kw)


class Engine(object):
    def __init__(self):
        self.nextcall = None
        self.crawlling = []
        self.max = 5
        self._closewait = None

    def get_response(self,content, request):
        response = HttpResponse(content, request)
        gen = request.callback(response)
        if isinstance(gen, types.GeneratorType):
            for req in gen:
                req.priority = request.priority + 1
                Q.put(req)


    def rm_crawlling(self,response,d):
        self.crawlling.remove(d)

    def _next_request(self,spider):
        if Q.qsize() == 0 and len(self.crawlling) == 0:
            self._closewait.callback(None)

        if len(self.crawlling) >= 5:
            return
        while len(self.crawlling) < 5:
            try:
                req = Q.get(block=False)
            except Exception as e:
                req = None
            if not req:
                return
            d = getPage(req.url.encode('utf-8'))
            self.crawlling.append(d)
            d.addCallback(self.get_response, req)
            d.addCallback(self.rm_crawlling,d)
            d.addCallback(lambda _: self.nextcall.schedule())


    @defer.inlineCallbacks
    def crawl(self):
        spider = ChouTiSpider()
        start_requests = iter(spider.start_requests())
        flag = True
        while flag:
            try:
                req = next(start_requests)
                Q.put(req)
            except StopIteration as e:
                flag = False

        self.nextcall = CallLaterOnce(self._next_request,spider)
        self.nextcall.schedule()

        self._closewait = defer.Deferred()
        yield self._closewait

    @defer.inlineCallbacks
    def pp(self):
        yield self.crawl()

_active = set()
obj = Engine()
d = obj.crawl()
_active.add(d)

li = defer.DeferredList(_active)
li.addBoth(lambda _,*a,**kw: reactor.stop())

reactor.run()

#额外拿出--注释

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


class Request(object):
    """
    封装请求相关信息
    """
    def __init__(self, url, callback):
        self.url = url
        self.callback = callback
        self.priority = 0


class HttpResponse(object):
    """
    封装相应相关信息
    """
    def __init__(self, content, request):
        self.content = content
        self.request = request


class Scheduler(object):
    """
    任务调度器
    """
    def __init__(self):
        self.q = Queue()

    def open(self):
        pass

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

        return request

    def enqueue_request(self, request):
        self.q.put(request,block=False)

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


class CallLaterOnce(object):
    """
    用于封装：执行下次nextcall.schedule()时，可以携带spider参数
    """
    def __init__(self, func, *a, **kw):
        self._func = func
        self._a = a
        self._kw = kw
        self._call = None

    def schedule(self, delay=0):
        if self._call is None:
            self._call = reactor.callLater(delay, self)

    def cancel(self):
        if self._call:
            self._call.cancel()

    def __call__(self):
        self._call = None
        return self._func(*self._a, **self._kw)


class ExecutionEngine(object):
    def __init__(self, crawler):
        self.crawler = crawler
        self.nextcall = None
        self.crawlling = []
        self.max = 5
        self._closewait = None
        self.scheduler = None

    def get_response(self, content, request):
        response = HttpResponse(content, request)
        gen = request.callback(response)
        if isinstance(gen, types.GeneratorType):
            for req in gen:
                req.priority = request.priority + 1
                self.scheduler.enqueue_request(req)

    def _next_request(self, spider):
        if self.scheduler.size() == 0 and len(self.crawlling) == 0:
            self._closewait.callback(None)
        if len(self.crawlling) >= 5:
            return
        while len(self.crawlling) < 5:
            req = self.scheduler.next_request()
            if not req:
                return
            d = getPage(req.url.encode('utf-8'))
            self.crawlling.append(d)


            #执行回调函数且向调度器中添加yield返回的request对象
            d.addCallback(self.get_response, req)

            #去掉
            d.addCallback(lambda _,d:self.crawlling.remove(d), d)

            #再去调度器中获取一个人物，继续执行下载(递归执行_next_request:这里的递归是说，执行一次在执行一次)
            d.addCallback(lambda _: self.nextcall.schedule())

    @defer.inlineCallbacks
    def open_spider(self, spider, start_requests):
        self.scheduler = Scheduler()

        flag = True
        while flag:
            try:
                req = next(start_requests)
                self.scheduler.enqueue_request(req)
            except StopIteration as e:
                flag = False
        self.nextcall = CallLaterOnce(self._next_request, spider)
        self.nextcall.schedule()
        yield None

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


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

        self.spider = None
        self.engine = None

    def _create_spider(self):
        """
        创建爬虫对象
        :return: 
        """
        module_path, cls_name = self.spider_cls_path.rsplit('.', maxsplit=1)
        import importlib

        m = importlib.import_module(module_path)
        cls = getattr(m, cls_name)
        return cls()

    def _create_engine(self):
        """
        创建引擎
        :return: 
        """
        return ExecutionEngine(self)

    @defer.inlineCallbacks
    def crawl(self):
        """
        :param args: 
        :param kwargs: 
        :return: 
        """
        self.spider = self._create_spider()
        self.engine = self._create_engine()
        start_requests = iter(self.spider.start_requests())

        #去获取数据
        yield self.engine.open_spider(self.spider, start_requests)

        #hold住请求，不终止
        yield self.engine.start()

        # _closewait.callback(None)  直到有此操作，才全部结束


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

    def crawl(self, spider_cls_path):
        """
        创建Crawler对象
        :param spider_cls_path: 爬虫spider路径
        :param args: 
        :param kwargs: 
        :return: 
        """
        crawler = Crawler(spider_cls_path, self.settings) #实例化对象


        d = crawler.crawl()     # defer.Deferred() ----返回defer对象
        self._active.add(d)  #d 加到 _active。若执行完，_active里只有一个值，一个 defer对象

        def _done(result):
            self.crawlers.discard(crawler)
            self._active.discard(d)
            return result

        return d.addBoth(_done)

    def start(self):
        """
        所有爬虫开始工作
        :return: 
        """
        dl = defer.DeferredList(self._active)
        dl.addBoth(self._stop_reactor)

        reactor.run()

    def _stop_reactor(self, _=None):
        """
        爬虫爬去数据完毕
        :return: 
        """
        reactor.stop()


class Commond(object):
    def __init__(self):
        self.crawl_process = CrawlerProcess({})

    def run(self):
        # spider_path_list = [
        #     "spider.chouti.ChoutiSpider",
        #     "spider.cnblogs.CnblogsSpider",
        # ]
        # for spider_cls_path in spider_path_list:
        #     self.crawl_process.crawl(spider_cls_path)

        self.crawl_process.crawl('spider.chouti.ChoutiSpider')  #只是当做 字符串，并未 实例化
        self.crawl_process.start()


if __name__ == '__main__':
    cmd = Commond()      #如果是主函数，实例化一个对象
    cmd.run()