Scrapy爬虫框架
一、Scrapy五大基本构成:
Scrapy框架主要由五大组件组成，它们分别是调度器(Scheduler)、下载器(Downloader)、爬虫（Spider）和实体管道(Item Pipeline)、Scrapy引擎(Scrapy Engine)。下面我们分别介绍各个组件的作用。
(1)、调度器(Scheduler):
调度器，说白了把它假设成为一个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（不做无用功）。用户可以自己的需求定制调度器。
(2)、下载器(Downloader):
下载器，是所有组件中负担最大的，它用于高速地下载网络上的资源。Scrapy的下载器代码不会太复杂，但效率高，主 要的原因是Scrapy下载器是建立在twisted这个高效的异步模型上的(其实整个框架都在建立在这个模型上的)。
(3)、 爬虫（Spider）:
爬虫，是用户最关心的部份。用户定制自己的爬虫，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。
(4)、 实体管道(Item Pipeline):
实体管道，用于处理爬虫提取的实体。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。
(5)、Scrapy引擎(Scrapy Engine):
Scrapy引擎是整个框架的核心.它用来控制调试器、下载器、爬虫。实际上，引擎相当于计算机的CPU,它控制着整个流程。
二、Scrapy请求发出去的整个流程
Scrapy运行时,请求发出去的整个流程大概如下：
1.首先爬虫将需要发送请求的url(requests)经引擎交给调度器;
2.排序处理后，经ScrapyEngine，DownloaderMiddlewares(有User_Agent, Proxy代理)交给Downloader;
3.Downloader向互联网发送请求，并接收下载响应.将响应经ScrapyEngine，可选交给Spiders;
4.Spiders处理response，提取数据并将数据经ScrapyEngine交给ItemPipeline保存;
5.提取url重新经ScrapyEngine交给Scheduler进行下一个循环。直到无Url请求程序停止结束。
三、Scrapy去重原理
1.Scrapy本身自带有一个中间件;
2.scrapy源码中可以找到一个dupefilters.py去重器;
3.需要将dont_filter设置为False开启去重，默认是True，没有开启去重；
4 .对于每一个url的请求，调度器都会根据请求得相关信息加密得到一个指纹信息，并且将指纹信息和set()集合中的指纹信息进 行 比对，如果set()集合中已经存在这个数据，就不在将这个Request放入队列中;
5.如果set()集合中没有存在这个加密后的数据，就将这个Request对象放入队列中，等待被调度。
dupefilters.py部分源码
class RFPDupeFilter(BaseDupeFilter
):
"""Request Fingerprint duplicates filter"""
def __init__(self
, path
=None, debug
=False):
self
.file = None
self
.fingerprints
= set()
self
.logdupes
= True
self
.debug
= debug
self
.logger
= logging
.getLogger
(__name__
)
if path
:
self
.file = open(os
.path
.join
(path
, 'requests.seen'), 'a+')
self
.file.seek
(0)
self
.fingerprints
.update
(x
.rstrip
() for x
in self
.file)
@
classmethod
def from_settings(cls
, settings
):
debug
= settings
.getbool
('DUPEFILTER_DEBUG')
return cls
(job_dir
(settings
), debug
)
def request_seen(self
, request
):
fp
= self
.request_fingerprint
(request
)
if fp
in self
.fingerprints
:
return True
self
.fingerprints
.add
(fp
)
if self
.file:
self
.file.write
(fp
+ os
.linesep
)
def request_fingerprint(self
, request
):
return request_fingerprint
(request
)
def close(self
, reason
):
if self
.file:
self
.file.close
()
def log(self
, request
, spider
):
if self
.debug
:
msg
= "Filtered duplicate request: %(request)s"
self
.logger
.debug
(msg
, {'request': request
}, extra
={'spider': spider
})
elif self
.logdupes
:
msg
= ("Filtered duplicate request: %(request)s"
" - no more duplicates will be shown"
" (see DUPEFILTER_DEBUG to show all duplicates)")
self
.logger
.debug
(msg
, {'request': request
}, extra
={'spider': spider
})
self
.logdupes
= False
spider
.crawler
.stats
.inc_value
('dupefilter/filtered', spider
=spider
)
scrapy框架默认的去重类RFPDupeFilter
请求进来以后，会先执行from_settings方法，从settings文件中找一个DUPEFILTER_DEBUG的配置，再执行init初始化方法，生成一个集合 self.fingerprints = set()，然后在执行request_seen方法，所以我们可以自定制去重规则，只要继承BaseDupeFilter即可
scrapy中settings.py文件解析
BOT_NAME
= 'step8_king'
SPIDER_MODULES
= ['step8_king.spiders']
NEWSPIDER_MODULE
= 'step8_king.spiders'
"""
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
"""
"""
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
"""
"""
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,
"""
SPIDER_MIDDLEWARES
= {
}
"""
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,
}
"""
settings
