爬虫之scrapy扩展
针对pipelines的扩展
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')
针对爬虫中间件的扩展
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,
}
针对下载中间件的扩展
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,
# }
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) 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')
url去重扩展
class RepeatUrl: def __init__(self): self.visited_url = set() @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)
代理扩展
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, }
Https访问证书扩展
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