scrapy 高級

piplines  5個 方法 

import json
import os
import requests


class JsonPipeline(object):
    def __init__(self):
        self.file = open('xiaohua.txt', 'w')

    def process_item(self, item, spider):
        v = json.dumps(dict(item), ensure_ascii=False)
        self.file.write(v)
        self.file.write('\n')
        self.file.flush()
        return item


class FilePipeline(object):
    def __init__(self):
        if not os.path.exists('imgs'):
            os.makedirs('imgs')

    def process_item(self, item, spider):
        response = requests.get(item['url'], stream=True)
        file_name = '%s_%s.jpg' % (item['name'], item['school'])
        with open(os.path.join('imgs', file_name), mode='wb') as f:
            f.write(response.content)
        return item

pipelines

piplines

 

ITEM_PIPELINES = {
   'spider1.pipelines.JsonPipeline': 100,
   'spider1.pipelines.FilePipeline': 300,
}
# 每行後面的整型值，肯定了他們運行的順序，item按數字從低到高的順序，經過pipeline，一般將這些數字定義在0-1000範圍內。

setiings中要打開

對於pipeline能夠作更多，以下：

from scrapy.exceptions import DropItem

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

    def process_item(self, item, spider):
        # 操做並進行持久化

        # return表示會被後續的pipeline繼續處理
        return item

        # 表示將item丟棄，不會被後續pipeline處理
        # raise DropItem()


    @classmethod
    def from_crawler(cls, crawler):
        """
        初始化時候，用於建立pipeline對象
        :param crawler: 
        :return: 
        """
        val = crawler.settings.getint('MMMM')
        return cls(val)

    def open_spider(self,spider):
        """
        爬蟲開始執行時，調用
        :param spider: 
        :return: 
        """
        print('000000')

    def close_spider(self,spider):
        """
        爬蟲關閉時，被調用
        :param spider: 
        :return: 
        """
        print('111111')

自定義pipeline

標準寫法4+1

 

********************中間件****************************

class SpiderMiddleware(object):

    def process_spider_input(self,response, spider):
        """
        下載完成，執行，而後交給parse處理
        :param response: 
        :param spider: 
        :return: 
        """
        pass

    def process_spider_output(self,response, result, spider):
        """
        spider處理完成，返回時調用
        :param response:
        :param result:
        :param spider:
        :return: 必須返回包含 Request 或 Item 對象的可迭代對象(iterable)
        """
        return result

    def process_spider_exception(self,response, exception, spider):
        """
        異常調用
        :param response:
        :param exception:
        :param spider:
        :return: None,繼續交給後續中間件處理異常；含 Response 或 Item 的可迭代對象(iterable)，交給調度器或pipeline
        """
        return None


    def process_start_requests(self,start_requests, spider):
        """
        爬蟲啓動時調用
        :param start_requests:
        :param spider:
        :return: 包含 Request 對象的可迭代對象
        """
        return start_requests

爬蟲中間件

爬蟲中間件

class DownMiddleware1(object):
    def process_request(self, request, spider):
        """
        請求須要被下載時，通過全部下載器中間件的process_request調用
        :param request: 
        :param spider: 
        :return:  
            None,繼續後續中間件去下載；
            Response對象，中止process_request的執行，開始執行process_response
            Request對象，中止中間件的執行，將Request從新調度器
            raise IgnoreRequest異常，中止process_request的執行，開始執行process_exception
        """
        pass



    def process_response(self, request, response, spider):
        """
        spider處理完成，返回時調用
        :param response:
        :param result:
        :param spider:
        :return: 
            Response 對象：轉交給其餘中間件process_response
            Request 對象：中止中間件，request會被從新調度下載
            raise IgnoreRequest 異常：調用Request.errback
        """
        print('response1')
        return response

    def process_exception(self, request, exception, spider):
        """
        當下載處理器(download handler)或 process_request() (下載中間件)拋出異常
        :param response:
        :param exception:
        :param spider:
        :return: 
            None：繼續交給後續中間件處理異常；
            Response對象：中止後續process_exception方法
            Request對象：中止中間件，request將會被從新調用下載
        """
        return None

下載器中間件

下載器中間件

 

=======================自定製命令=========================================

• 在spiders同級建立任意目錄，如：commands
• 在其中建立 crawlall.py 文件 （此處文件名就是自定義的命令）

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()

crawlall.py

crawlall 執行全部爬蟲

• 在settings.py 中添加配置 COMMANDS_MODULE = '項目名稱.目錄名稱'
• 在項目目錄執行命令：scrapy crawlall 

 

----------------------------------------------自定義擴展-------------------------------------------------

自定義擴展時，利用信號在指定位置註冊制定操做

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)

        crawler.signals.connect(ext.spider_opened, signal=signals.spider_opened)
        crawler.signals.connect(ext.spider_closed, signal=signals.spider_closed)

        return ext

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

    def spider_closed(self, spider):
        print('close')

經過scrapy 預留的信號 進行處理

 

******************************************避免重複訪問***********************************************

scrapy默認使用 scrapy.dupefilter.RFPDupeFilter 進行去重，相關配置有：

DUPEFILTER_CLASS = 'scrapy.dupefilter.RFPDupeFilter'

DUPEFILTER_DEBUG  =  False

JOBDIR  =  "保存範文記錄的日誌路徑，如：/root/"   # 最終路徑爲 /root/requests.seen

class RepeatUrl:
    def __init__(self):
        self.visited_url = set()

    @classmethod
    def from_settings(cls, settings):
        """
        初始化時，調用
        :param settings: 
        :return: 
        """
        return cls()

    def request_seen(self, request):
        """
        檢測當前請求是否已經被訪問過
        :param request: 
        :return: True表示已經訪問過；False表示未訪問過
        """
        if request.url in self.visited_url:
            return True
        self.visited_url.add(request.url)
        return False

    def open(self):
        """
        開始爬去請求時，調用
        :return: 
        """
        print('open replication')

    def close(self, reason):
        """
        結束爬蟲爬取時，調用
        :param reason: 
        :return: 
        """
        print('close replication')

    def log(self, request, spider):
        """
        記錄日誌
        :param request: 
        :param spider: 
        :return: 
        """
        print('repeat', request.url)

自定義URL去重操做

自定義URL 去重

 

_------------------------------其餘-------------------

# -*- 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. 爬蟲名稱
BOT_NAME = 'step8_king'

# 2. 爬蟲應用路徑
SPIDER_MODULES = ['step8_king.spiders']
NEWSPIDER_MODULE = 'step8_king.spiders'

# Crawl responsibly by identifying yourself (and your website) on the user-agent
# 3. 客戶端 user-agent請求頭
# USER_AGENT = 'step8_king (+http://www.yourdomain.com)'

# Obey robots.txt rules
# 4. 禁止爬蟲配置
# ROBOTSTXT_OBEY = False

# Configure maximum concurrent requests performed by Scrapy (default: 16)
# 5. 併發請求數
# 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. 延遲下載秒數
# DOWNLOAD_DELAY = 2


# The download delay setting will honor only one of:
# 7. 單域名訪問併發數，而且延遲下次秒數也應用在每一個域名
# CONCURRENT_REQUESTS_PER_DOMAIN = 2
# 單IP訪問併發數，若是有值則忽略：CONCURRENT_REQUESTS_PER_DOMAIN，而且延遲下次秒數也應用在每一個IP
# CONCURRENT_REQUESTS_PER_IP = 3

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

# Disable Telnet Console (enabled by default)
# 9. Telnet用於查看當前爬蟲的信息，操做爬蟲等...
#    使用telnet ip port ，而後經過命令操做
# TELNETCONSOLE_ENABLED = True
# TELNETCONSOLE_HOST = '127.0.0.1'
# TELNETCONSOLE_PORT = [6023,]


# 10. 默認請求頭
# 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. 定義pipeline處理請求
# ITEM_PIPELINES = {
#    'step8_king.pipelines.JsonPipeline': 700,
#    'step8_king.pipelines.FilePipeline': 500,
# }



# 12. 自定義擴展，基於信號進行調用
# Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
# EXTENSIONS = {
#     # 'step8_king.extensions.MyExtension': 500,
# }


# 13. 爬蟲容許的最大深度，能夠經過meta查看當前深度；0表示無深度
# DEPTH_LIMIT = 3

# 14. 爬取時，0表示深度優先Lifo(默認)；1表示廣度優先FiFo

# 後進先出，深度優先
# DEPTH_PRIORITY = 0
# SCHEDULER_DISK_QUEUE = 'scrapy.squeue.PickleLifoDiskQueue'
# SCHEDULER_MEMORY_QUEUE = 'scrapy.squeue.LifoMemoryQueue'
# 先進先出，廣度優先

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

# 15. 調度器隊列
# SCHEDULER = 'scrapy.core.scheduler.Scheduler'
# from scrapy.core.scheduler import Scheduler


# 16. 訪問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. 自動限速算法
    from scrapy.contrib.throttle import AutoThrottle
    自動限速設置
    1. 獲取最小延遲 DOWNLOAD_DELAY
    2. 獲取最大延遲 AUTOTHROTTLE_MAX_DELAY
    3. 設置初始下載延遲 AUTOTHROTTLE_START_DELAY
    4. 當請求下載完成後，獲取其"鏈接"時間 latency，即：請求鏈接到接受到響應頭之間的時間
    5. 用於計算的... AUTOTHROTTLE_TARGET_CONCURRENCY
    target_delay = latency / self.target_concurrency
    new_delay = (slot.delay + target_delay) / 2.0 # 表示上一次的延遲時間
    new_delay = max(target_delay, new_delay)
    new_delay = min(max(self.mindelay, new_delay), self.maxdelay)
    slot.delay = new_delay
"""

# 開始自動限速
# AUTOTHROTTLE_ENABLED = True
# The initial download delay
# 初始下載延遲
# AUTOTHROTTLE_START_DELAY = 5
# The maximum download delay to be set in case of high latencies
# 最大下載延遲
# AUTOTHROTTLE_MAX_DELAY = 10
# The average number of requests Scrapy should be sending in parallel to each remote server
# 平均每秒併發數
# AUTOTHROTTLE_TARGET_CONCURRENCY = 1.0

# Enable showing throttling stats for every response received:
# 是否顯示
# 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. 啓用緩存
    目的用於將已經發送的請求或相應緩存下來，以便之後使用
    
    from scrapy.downloadermiddlewares.httpcache import HttpCacheMiddleware
    from scrapy.extensions.httpcache import DummyPolicy
    from scrapy.extensions.httpcache import FilesystemCacheStorage
"""
# 是否啓用緩存策略
# HTTPCACHE_ENABLED = True

# 緩存策略：全部請求均緩存，下次在請求直接訪問原來的緩存便可
# HTTPCACHE_POLICY = "scrapy.extensions.httpcache.DummyPolicy"
# 緩存策略：根據Http響應頭：Cache-Control、Last-Modified 等進行緩存的策略
# HTTPCACHE_POLICY = "scrapy.extensions.httpcache.RFC2616Policy"

# 緩存超時時間
# HTTPCACHE_EXPIRATION_SECS = 0

# 緩存保存路徑
# HTTPCACHE_DIR = 'httpcache'

# 緩存忽略的Http狀態碼
# HTTPCACHE_IGNORE_HTTP_CODES = []

# 緩存存儲的插件
# HTTPCACHE_STORAGE = 'scrapy.extensions.httpcache.FilesystemCacheStorage'


"""
19. 代理，須要在環境變量中設置
    from scrapy.contrib.downloadermiddleware.httpproxy import HttpProxyMiddleware
    
    方式一：使用默認
        os.environ
        {
            http_proxy:http://root:woshiniba@192.168.11.11:9999/
            https_proxy:http://192.168.11.11:9999/
        }
    方式二：使用自定義下載中間件
    
    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訪問
    Https訪問時有兩種狀況：
    1. 要爬取網站使用的可信任證書(默認支持)
        DOWNLOADER_HTTPCLIENTFACTORY = "scrapy.core.downloader.webclient.ScrapyHTTPClientFactory"
        DOWNLOADER_CLIENTCONTEXTFACTORY = "scrapy.core.downloader.contextfactory.ScrapyClientContextFactory"
        
    2. 要爬取網站使用的自定義證書
        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對象
                    certificate=v2,  # X509對象
                    verify=False,
                    method=getattr(self, 'method', getattr(self, '_ssl_method', None))
                )
    其餘：
        相關類
            scrapy.core.downloader.handlers.http.HttpDownloadHandler
            scrapy.core.downloader.webclient.ScrapyHTTPClientFactory
            scrapy.core.downloader.contextfactory.ScrapyClientContextFactory
        相關配置
            DOWNLOADER_HTTPCLIENTFACTORY
            DOWNLOADER_CLIENTCONTEXTFACTORY

"""



"""
21. 爬蟲中間件
    class SpiderMiddleware(object):

        def process_spider_input(self,response, spider):
            '''
            下載完成，執行，而後交給parse處理
            :param response: 
            :param spider: 
            :return: 
            '''
            pass
    
        def process_spider_output(self,response, result, spider):
            '''
            spider處理完成，返回時調用
            :param response:
            :param result:
            :param spider:
            :return: 必須返回包含 Request 或 Item 對象的可迭代對象(iterable)
            '''
            return result
    
        def process_spider_exception(self,response, exception, spider):
            '''
            異常調用
            :param response:
            :param exception:
            :param spider:
            :return: None,繼續交給後續中間件處理異常；含 Response 或 Item 的可迭代對象(iterable)，交給調度器或pipeline
            '''
            return None
    
    
        def process_start_requests(self,start_requests, spider):
            '''
            爬蟲啓動時調用
            :param start_requests:
            :param spider:
            :return: 包含 Request 對象的可迭代對象
            '''
            return start_requests
    
    內置爬蟲中間件：
        '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. 下載中間件
    class DownMiddleware1(object):
        def process_request(self, request, spider):
            '''
            請求須要被下載時，通過全部下載器中間件的process_request調用
            :param request:
            :param spider:
            :return:
                None,繼續後續中間件去下載；
                Response對象，中止process_request的執行，開始執行process_response
                Request對象，中止中間件的執行，將Request從新調度器
                raise IgnoreRequest異常，中止process_request的執行，開始執行process_exception
            '''
            pass
    
    
    
        def process_response(self, request, response, spider):
            '''
            spider處理完成，返回時調用
            :param response:
            :param result:
            :param spider:
            :return:
                Response 對象：轉交給其餘中間件process_response
                Request 對象：中止中間件，request會被從新調度下載
                raise IgnoreRequest 異常：調用Request.errback
            '''
            print('response1')
            return response
    
        def process_exception(self, request, exception, spider):
            '''
            當下載處理器(download handler)或 process_request() (下載中間件)拋出異常
            :param response:
            :param exception:
            :param spider:
            :return:
                None：繼續交給後續中間件處理異常；
                Response對象：中止後續process_exception方法
                Request對象：中止中間件，request將會被從新調用下載
            '''
            return None

    
    默認下載中間件
    {
        '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

View Code

 

***********************************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()

參考版

View Code

 

***********************************scrapy-redis***********************