Scarpy 起始url 自定义代理 自定义去重规则

- start_urls

    - 内部原理
            """
            scrapy引擎来爬虫中去起始的URL:
                1. 调用start_requests并获取返回值
                2. v = iter(返回值)
                3.
                    req1 = 执行 v.__next__()
                    req2 = 执行 v.__next__()
                    req3 = 执行 v.__next__()
                    ...
                4.req全部放到调度器中
            """

    - 编写
        class Pc1Spider(scrapy.Spider):
            name = 'pc1'
            allowed_domains = ['chouti.com']
            start_urls = ["https://dig.chouti.com"] #定制:可以去redis中获取

            def start_requests(self):
　　　　　　　　   # 添加内置代理
　　　　　　　　　　"""
　　　　　　　　　　import os
　　　　　　　　　　os.environ["HTTPS_PROXY"] = "https://root:password@192.168.1.3:9999/"
　　　　　　　　　　os.environ["HTTP_PROXY"] = "123.11.12.13"

　　　　　　　　　　"""

　　　　　　　　　# 方式一:
                # for url in self.start_urls:
                #        yield Request(url=url)
                # 方式二:
                # req_list = []
                # for url in self.start_urls:
                #     req_list.append(Request(url=url))
                # return req_list

            def parse(self,response):
                pass

自定义代理

import base64
import random
from six.moves.urllib.parse import unquote, urlunparse

try:
    from urllib2 import _parse_proxy
except ImportError:
    from urllib.request import _parse_proxy

from scrapy.utils.python import to_bytes

class AqlProxyMiddleware(object):

    def _basic_auth_header(self, username, password):
        user_pass = to_bytes(
            '%s:%s' % (unquote(username), unquote(password)),
            encoding='latin-1')
        return base64.b64encode(user_pass)

    def process_request(self, request, spider):

        PROXIES = [
            "http://root:password@192.168.1.3:9991/",
            "http://root:password@192.168.1.3:9991/",
            "http://root:password@192.168.1.3:9991/",
            "http://root:password@192.168.1.3:9991/",
            "http://root:password@192.168.1.3:9991/",

        ]

        url = random.choice(PROXIES)
        orig_type = ""
        proxt_type, user, password, hostport = _parse_proxy(url)
        proxt_url = urlunparse((proxt_type or orig_type, hostport,'','','',''))

        if user:
            creds = self._basic_auth_header(user,password)
        else:
            creds = None

        request.meta['proxy'] = proxt_url
        if creds :
            request.headers['Proxy-Authorization'] = b'Basic ' + creds

settings

# -*- coding: utf- -*-

# 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

# . 爬虫名称
BOT_NAME = 'step8_king'

# . 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
# . 客户端 user-agent请求头
# USER_AGENT = 'step8_king (+http://www.yourdomain.com)'

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

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

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

# The download delay setting will honor only one of:
# . 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 =
# 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 = 

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

# Disable Telnet Console (enabled by default)
# . 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 = [,]

# . 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
# . 定义pipeline处理请求
# ITEM_PIPELINES = {
#    'step8_king.pipelines.JsonPipeline': ,
#    'step8_king.pipelines.FilePipeline': ,
# }

# . 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': ,
# }

# . 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 = 

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

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

# . 调度器队列
# SCHEDULER = 'scrapy.core.scheduler.Scheduler'
# from scrapy.core.scheduler import Scheduler

# . 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

"""
. 自动限速算法
    from scrapy.contrib.throttle import AutoThrottle
    自动限速设置
    . 获取最小延迟 DOWNLOAD_DELAY
    . 获取最大延迟 AUTOTHROTTLE_MAX_DELAY
    . 设置初始下载延迟 AUTOTHROTTLE_START_DELAY
    . 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
    . 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 =
# The maximum download delay to be set in case of high latencies
# 最大下载延迟
# AUTOTHROTTLE_MAX_DELAY =
# 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

"""
. 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 = 

# 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'

"""
. 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': ,
    }

"""

"""
. Https访问
    Https访问时有两种情况：
    . 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"

    . 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

"""

"""
. 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': ,
        'scrapy.contrib.spidermiddleware.offsite.OffsiteMiddleware': ,
        'scrapy.contrib.spidermiddleware.referer.RefererMiddleware': ,
        'scrapy.contrib.spidermiddleware.urllength.UrlLengthMiddleware': ,
        'scrapy.contrib.spidermiddleware.depth.DepthMiddleware': ,

"""
# 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': ,
}

"""
. 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': ,
        'scrapy.contrib.downloadermiddleware.httpauth.HttpAuthMiddleware': ,
        'scrapy.contrib.downloadermiddleware.downloadtimeout.DownloadTimeoutMiddleware': ,
        'scrapy.contrib.downloadermiddleware.useragent.UserAgentMiddleware': ,
        'scrapy.contrib.downloadermiddleware.retry.RetryMiddleware': ,
        'scrapy.contrib.downloadermiddleware.defaultheaders.DefaultHeadersMiddleware': ,
        'scrapy.contrib.downloadermiddleware.redirect.MetaRefreshMiddleware': ,
        'scrapy.contrib.downloadermiddleware.httpcompression.HttpCompressionMiddleware': ,
        'scrapy.contrib.downloadermiddleware.redirect.RedirectMiddleware': ,
        'scrapy.contrib.downloadermiddleware.cookies.CookiesMiddleware': ,
        'scrapy.contrib.downloadermiddleware.httpproxy.HttpProxyMiddleware': ,
        'scrapy.contrib.downloadermiddleware.chunked.ChunkedTransferMiddleware': ,
        'scrapy.contrib.downloadermiddleware.stats.DownloaderStats': ,
        'scrapy.contrib.downloadermiddleware.httpcache.HttpCacheMiddleware': ,
    }

"""
# 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': ,
#    'step8_king.middlewares.DownMiddleware2': ,
# }

scrapy-redis 自定义去重规则

############### xxx.py  ######

from scrapy_redis.dupefilter import RFPDupeFilter
from scrapy_redis.connection import get_redis_from_settings
from scrapy_redis import defaults

class RdisDupeFilter(RFPDupeFilter):

    @classmethod
    def from_settings(cls, settings):

        server = get_redis_from_settings(settings)

        key = defaults.DUPEFILTER_KEY % {'timestamp':'myScrapy'}
        debug = settings.getbool('DUPEFILTER_DEBUG')
        return cls(server, key=key, debug=debug)

########################### settings.py ##########
# ######################### scrapy redis连接 ##############
REDIS_HOST = "129.28.96.43"  #主机名
REDIS_PORT = 6379            #端口
REDIS_PARAMS = {'password':"beta"}
REDIS_ENCODEING = "utf-8"    #redis编码类型

# REDIS_URL = 'redis://user:pwd@hostname:9001' #连接URL 优先上面配置

DUPEFILTER_KEY = 'dupefilter:%(timestamp)s'

# DUPEFLITER_CLASS = 'scrapy_redis.dupefilter.RFPDupeFilter'
DUPEFLITER_CLASS = 'myscrapy.xxx.RedisDupeFilter'