爬了个爬（三）Scrapy框架

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

# -*- coding: utf-8 -*-
import scrapyclass XiaohuarSpider(scrapy.Spider):
name = 'xiaohuar' #爬虫名称
allowed_domains = ['xiaohuar.com'] #允许的域名
start_urls = ['http://www.xiaohuar.com/hua/'] #起始URL def parse(self, response):
# 访问起始URL并获取结果后的回调函数
pass

class Request(object_ref): def __init__(self, url, callback=None, method='GET', headers=None, body=None,
cookies=None, meta=None, encoding='utf-8', priority=0,
dont_filter=False, errback=None, flags=None):
.........#url = 请求路由地址
#method 请求方法，默认GET
#headers 请求头
#body 传值
#cookies cookies#dont_filter 是否过滤，默认False url请求过滤

import scrapy
from scrapy.selector import HtmlXPathSelector
from scrapy.http.request import Requestclass DigSpider(scrapy.Spider):
# 爬虫应用的名称，通过此名称启动爬虫命令
name = "dig" # 允许的域名
allowed_domains = ["chouti.com"] # 起始URL
start_urls = [
'http://dig.chouti.com/',
] has_request_set = {} def parse(self, response):
print(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

# -*- coding: utf-8 -*-
import scrapy
from scrapy.selector import Selector
from scrapy.http import Requestclass XiaohuarSpider(scrapy.Spider):
name = 'xiaohuar' #爬虫名称
allowed_domains = ['xiaohuar.com'] #允许的域名
start_urls = ['http://www.xiaohuar.com/hua/'] #起始URL def parse(self, response):
# 访问起始URL并获取结果后的回调函数 #处理返回的字符串，转换成标签
hxs = Selector(response=response) user_list = hxs.xpath('//div[@class="item masonry_brick"]')
for item in user_list:
price = item.xpath('.//span[@class="price"]/text()').extract_first()
url = item.xpath('//div[@class="item_t"]/div[@class="img"]//a/@href').extract_first()
print(price, url) # 跨页获取
result = hxs.xpath('.//a[re:test(@href,"http://www.xiaohuar.com/list-1-\d+.html")]/@href')
print(result) # 规则，固定写法，在配置文件中指定递归层数
for url in result:
yield Request(url=url, callback=self.parse)

# -*- coding: utf-8 -*-
import scrapy
from scrapy.http import Request
from scrapy.selector import Selector
from scrapy.http.cookies import CookieJar
import urllib.parse as urlpsclass ChoutiSpider(scrapy.Spider):
name = 'chouti'
allowed_domains = ['chouti.com']
start_urls = ['http://chouti.com/'] #获取cookies
cookie_dict = {} def start_requests(self):
"""
自定义起始url,执行访问主页
:return:
"""
for url in self.start_urls:
yield Request(url, dont_filter=True,callback=self.parse_login) def parse_login(self, response):
#访问登录页面，登录并拿到新的cookies
cookies_jar = CookieJar() #对象，内部封装了cookies，scrapy框架可以直接使用，打印的话需要如下转换
cookies_jar.extract_cookies(response,response.request) #去响应中获取cookies for k, v in cookies_jar._cookies.items():
for i, j in v.items():
for m, n in j.items():
self.cookie_dict[m] = n.value url_info = "http://dig.chouti.com/login"
post_dict = {
'phone':'',
'password':'zyj13032025071',
'oneMonth':1,
} #POST登录
yield Request(
url=url_info,
method="POST",
cookies=self.cookie_dict,
body=urlps.urlencode(post_dict),
headers={"Content-Type":"application/x-www-form-urlencoded; charset=UTF-8",},
callback=self.get_message,
) def get_message(self,response):
# 获取消息列表
print(response.text)
yield Request(
url="http://dig.chouti.com/",
method="GET",
cookies=self.cookie_dict,
callback=self.parse_UP,
) def parse_UP(self,response):
#找到标签，点赞
#找div,class = part2, 获取share-linkid
print(11111)
hxs = Selector(response)
link_id_list = hxs.xpath('//div[@class="part2"]/@share-linkid').extract()
print(link_id_list) for link_id in link_id_list:
#获取每一个ID去点赞(仅在第一页点赞)
base_url = "http://dig.chouti.com/link/vote?linksId=%s"%(link_id,)
yield Request(
url=base_url,
method="POST",
cookies=self.cookie_dict,
callback=self.return_infos,
) #对所有的页面点赞
page_list = hxs.xpath('//div[@id="dig_lcpage"]//a/@href').extract()
for page in page_list:
page_url = "http://dig.chouti.com%s"%(page,)
yield Request(url=page_url,method="GET",dont_filter=False,callback=self.parse_UP)
page_list.remove(page) def return_infos(self,response):
#点赞之后，获取返回信息
print(response.text)

# -*- coding: utf-8 -*-
import scrapy
from scrapy.selector import Selector
from scrapy.http import Request
from items import Sp1Itemclass JandanSpider(scrapy.Spider):
name = 'jandan'
allowed_domains = ['jandan.net']
start_urls = ['http://jandan.net/ooxx/'] def start_requests(self):
for url in self.start_urls:
yield Request(url=url,dont_filter=True,callback=self.parse1) def parse1(self, response): hxs = Selector(response)
text_list = hxs.xpath('//div[@class="indexs"]/h2/a/text()').extract()
for item in text_list:
yield Sp1Item(text=item,name="jiandan")

import scrapy
class Sp1Item(scrapy.Item):
# define the fields for your item here like:
# name = scrapy.Field()
"""
注意只有Field字段
"""
name = scrapy.Field()
text = scrapy.Field()

class Sp2Pipeline(object):
def __init__(self):
self.f = None
self.val = 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('....')
#将item 传递给下一个pipeline 的 process_item 方法
return item #把对象传递给下一个pipeline # 如果不想让下一个pipline中process_item方法不执行，使用如下，抛出异常不再执行
# 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: 爬虫相关的所有信息，可以去配置文件取值
:return:
"""
#从配置文件中取值，实例化传给__init__方法。【一般是通过这种方式连接数据库】
# 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: 爬虫对象
:return:
"""
print('打开爬虫') #打开文件
self.f = open('a.log','a+') #连接数据库
self.val = 数据库连接操作 def close_spider(self,spider):
"""
爬虫关闭时，被调用
:param spider:
:return:
"""
#关闭文件
self.f.close() #关闭数据库

class RepeatUrl:
def __init__(self):
#可以把要检测的url写在数据库 or 放在另一台服务器的内存，或是缓存
self.visited_url = set()#结合 # @classmethod
def from_settings(cls, settings):
"""
初始化时，调用
:param settings:配置文件，可以取东西
:return:
"""
return cls() def request_seen(self, request):
"""
检测当前请求是否已经被访问过
:param request:请求
: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)

from scrapy import signalsclass 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： ext.opened 注册触发信号时执行的函数，爬虫执行自动触发
crawler.signals.connect(ext.opened, signal=signals.spider_opened)
# 在scrapy中注册信号： 同上
crawler.signals.connect(ext.closed, signal=signals.spider_closed) return ext #自定义触发信号时执行的函数
def opened(self, spider):
print('open') def closed(self, spider):
print('close')

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
"""
"""
#自定义请求方式，添加或是修改请求头
from scrapy.http import Request
# print(request)
# request.method = "POST"
request.headers['proxy'] = "{'ip_port': '111.11.228.75:80', 'user_pass': ''},"
return None
"""
"""
#自定义请求地址，返回响应信息
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
"""
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')
#在响应回来时，我们可以对响应体进行某些处理
# 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

from scrapy.commands import ScrapyCommand
from scrapy.utils.project import get_project_settingsclass 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): # 爬虫列表
spider_list = self.crawler_process.spiders.list()
for name in spider_list:
# 初始化爬虫
self.crawler_process.crawl(name, **opts.__dict__)
# 开始执行所有的爬虫
self.crawler_process.start()

# -*- 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【没有网络，但是数据已经缓存下来，可以测试使用】 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/
} 例如:我们可以在自定义命令中引入，可以在爬虫执行的时候，使用代理IP。
from scrapy.contrib.downloadermiddleware.httpproxy import HttpProxyMiddleware
import os os.environ['http_proxy'] = "http://root:woshiniba@192.168.11.11:9999/"
os.environ['https_proxy'] = "http://192.168.11.11:9999/"
os.environ['xx_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']) # 配置文件中注册
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,
# }