爬虫框架之Scrapy

全局命令：所有文件夹都使用的命令,可以不依赖与项目文件也可以执行
项目的文件夹下执行的命令
1、scrapy startproject Myproject #创建项目
cd Myproject
2、scrapy genspider baidu www.baidu.com #创建爬虫程序，baidu是爬虫名,定位爬虫的名字
#写完域名以后默认会有一个url,
3、scrapy settings --get BOT_NAME #获取配置文件
#全局：4、scrapy runspider budui.py
5、scrapy runspider AMAZON\spiders\amazon.py #执行爬虫程序
在项目下：scrapy crawl amazon #指定爬虫名，定位爬虫程序来运行程序
#robots.txt 反爬协议：在目标站点建一个文件，里面规定了哪些能爬，哪些不能爬
# 有的国家觉得是合法的，有的是不合法的，这就产生了反爬协议
# 默认是ROBOTSTXT_OBEY = True
# 修改为ROBOTSTXT_OBEY = False #默认不遵循反扒协议
6、scrapy shell https://www.baidu.com #直接超目标站点发请求
response
response.status
response.body
view(response)
7、scrapy view https://www.taobao.com #如果页面显示内容不全，不全的内容则是ajax请求实现的，以此快速定位问题
8、scrapy version #查看版本
9、scrapy version -v #查看scrapy依赖库锁依赖的版本
10、scrapy fetch --nolog http://www.logou.com #获取响应的内容
11、scrapy fetch --nolog --headers http://www.logou.com #获取响应的请求头
(venv3_spider) E:\twisted\scrapy框架\AMAZON>scrapy fetch --nolog --headers http://www.logou.com
> Accept: text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8
> Accept-Language: en
> User-Agent: Scrapy/1.5.0 (+https://scrapy.org)
> Accept-Encoding: gzip,deflate
>
< Content-Type: text/html; charset=UTF-8
< Date: Tue, 23 Jan 2018 15:51:32 GMT
< Server: Apache
>代表请求
<代表返回
10、scrapy shell http://www.logou.com #直接朝目标站点发请求
11、scrapy check #检测爬虫有没有错误
12、scrapy list #所有的爬虫名
13、scrapy parse http://quotes.toscrape.com/ --callback parse #验证回调函函数是否成功执行
14、scrapy bench #压力测试

import sys,os
sys.stdout=io.TextIOWrapper(sys.stdout.buffer,encoding='gb18030')

#1、name = 'amazon'
定义爬虫名，scrapy会根据该值定位爬虫程序
所以它必须要有且必须唯一（In Python 2 this must be ASCII only.） #2、allowed_domains = ['www.amazon.cn']
定义允许爬取的域名，如果OffsiteMiddleware启动（默认就启动），
那么不属于该列表的域名及其子域名都不允许爬取
如果爬取的网址为：https://www.example.com/1.html，那就添加'example.com'到列表. #3、start_urls = ['http://www.amazon.cn/']
如果没有指定url，就从该列表中读取url来生成第一个请求 #4、custom_settings
值为一个字典，定义一些配置信息，在运行爬虫程序时，这些配置会覆盖项目级别的配置
所以custom_settings必须被定义成一个类属性，由于settings会在类实例化前被加载 #5、settings
通过self.settings['配置项的名字']可以访问settings.py中的配置，如果自己定义了custom_settings还是以自己的为准 #6、logger
日志名默认为spider的名字
self.logger.debug('=============>%s' %self.settings['BOT_NAME']) #5、crawler：了解
该属性必须被定义到类方法from_crawler中 #6、from_crawler(crawler, *args, **kwargs)：了解
You probably won’t need to override this directly because the default implementation acts as a proxy to the __init__() method, calling it with the given arguments args and named arguments kwargs. #7、start_requests()
该方法用来发起第一个Requests请求，且必须返回一个可迭代的对象。它在爬虫程序打开时就被Scrapy调用，Scrapy只调用它一次。
默认从start_urls里取出每个url来生成Request(url, dont_filter=True) #针对参数dont_filter,请看自定义去重规则 如果你想要改变起始爬取的Requests，你就需要覆盖这个方法，例如你想要起始发送一个POST请求，如下
class MySpider(scrapy.Spider):
name = 'myspider' def start_requests(self):
return [scrapy.FormRequest("http://www.example.com/login",
formdata={'user': 'john', 'pass': 'secret'},
callback=self.logged_in)] def logged_in(self, response):
# here you would extract links to follow and return Requests for
# each of them, with another callback
pass #8、parse(response)
这是默认的回调函数，所有的回调函数必须返回an iterable of Request and/or dicts or Item objects. #9、log(message[, level, component])：了解
Wrapper that sends a log message through the Spider’s logger, kept for backwards compatibility. For more information see Logging from Spiders. #10、closed(reason)
爬虫程序结束时自动触发

去重规则应该多个爬虫共享的，但凡一个爬虫爬取了，其他都不要爬了，实现方式如下 #方法一：
1、新增类属性
visited=set() #类属性 2、回调函数parse方法内：
def parse(self, response):
if response.url in self.visited:
return None
....... self.visited.add(response.url) #方法一改进：针对url可能过长，所以我们存放url的hash值
def parse(self, response):
url=md5(response.request.url)
if url in self.visited:
return None
....... self.visited.add(url) #方法二：Scrapy自带去重功能
配置文件：
DUPEFILTER_CLASS = 'scrapy.dupefilter.RFPDupeFilter' #默认的去重规则帮我们去重，去重规则在内存中
DUPEFILTER_DEBUG = False
JOBDIR = "保存范文记录的日志路径，如：/root/" # 最终路径为 /root/requests.seen，去重规则放文件中 scrapy自带去重规则默认为RFPDupeFilter，只需要我们指定
Request(...,dont_filter=False) ，如果dont_filter=True则告诉Scrapy这个URL不参与去重。 #方法三：
我们也可以仿照RFPDupeFilter自定义去重规则， from scrapy.dupefilter import RFPDupeFilter，看源码，仿照BaseDupeFilter #步骤一：在项目目录下自定义去重文件cumstomdupefilter.py
'''
if hasattr("MyDupeFilter",from_settings):
func = getattr("MyDupeFilter",from_settings)
obj = func()
else:
return MyDupeFilter()
'''
class MyDupeFilter(object):
def __init__(self):
self.visited = set() @classmethod
def from_settings(cls, settings):
'''读取配置文件'''
return cls() def request_seen(self, request):
'''请求看过没有，这个才是去重规则该调用的方法'''
if request.url in self.visited:
return True
self.visited.add(request.url) def open(self): # can return deferred
'''打开的时候执行'''
pass def close(self, reason): # can return a deferred
pass def log(self, request, spider): # log that a request has been filtered
'''日志记录'''
pass #步骤二：配置文件settings.py
# DUPEFILTER_CLASS = 'scrapy.dupefilter.RFPDupeFilter' #默认会去找这个类实现去重
#自定义去重规则
DUPEFILTER_CLASS = 'AMAZON.cumstomdupefilter.MyDupeFilter' # 源码分析：
from scrapy.core.scheduler import Scheduler
见Scheduler下的enqueue_request方法：self.df.request_seen(request)

#例一：
import scrapy class MySpider(scrapy.Spider):
name = 'example.com'
allowed_domains = ['example.com']
start_urls = [
'http://www.example.com/1.html',
'http://www.example.com/2.html',
'http://www.example.com/3.html',
] def parse(self, response):
self.logger.info('A response from %s just arrived!', response.url) #例二：一个回调函数返回多个Requests和Items
import scrapy class MySpider(scrapy.Spider):
name = 'example.com'
allowed_domains = ['example.com']
start_urls = [
'http://www.example.com/1.html',
'http://www.example.com/2.html',
'http://www.example.com/3.html',
] def parse(self, response):
for h3 in response.xpath('//h3').extract():
yield {"title": h3} for url in response.xpath('//a/@href').extract():
yield scrapy.Request(url, callback=self.parse) #例三：在start_requests()内直接指定起始爬取的urls，start_urls就没有用了， import scrapy
from myproject.items import MyItem class MySpider(scrapy.Spider):
name = 'example.com'
allowed_domains = ['example.com'] def start_requests(self):
yield scrapy.Request('http://www.example.com/1.html', self.parse)
yield scrapy.Request('http://www.example.com/2.html', self.parse)
yield scrapy.Request('http://www.example.com/3.html', self.parse) def parse(self, response):
for h3 in response.xpath('//h3').extract():
yield MyItem(title=h3) for url in response.xpath('//a/@href').extract():
yield scrapy.Request(url, callback=self.parse) #例四：
# -*- coding: utf-8 -*-
from urllib.parse import urlencode
# from scrapy.dupefilter import RFPDupeFilter
# from AMAZON.items import AmazonItem
from AMAZON.items import AmazonItem
''' spiders会循环做下面几件事
1、生成初始请求来爬取第一个urls,并且绑定一个回调函数
2、在回调函数中，解析response并且返回值
3、在回调函数中，解析页面内容（可通过Scrapy自带的Seletors或者BeautifuSoup等）
4、最后、针对返回的Items对象（就是你从返回结果中筛选出来自己想要的数据）将会被持久化到数据库
Spiders总共提供了五种类：
#1、scrapy.spiders.Spider #scrapy.Spider等同于scrapy.spiders.Spider
#2、scrapy.spiders.CrawlSpider
#3、scrapy.spiders.XMLFeedSpider
#4、scrapy.spiders.CSVFeedSpider
#5、scrapy.spiders.SitemapSpider
'''
import scrapy
class AmazonSpider(scrapy.Spider):
def __init__(self,keyword=None,*args,**kwargs): #在entrypoint文件里面传进来的keyword，在这里接收了
super(AmazonSpider,self).__init__(*args,**kwargs)
self.keyword = keyword name = 'amazon' # 必须唯一
allowed_domains = ['www.amazon.cn'] # 允许域
start_urls = ['http://www.amazon.cn/'] # 如果你没有指定发送的请求地址，会默认使用只一个 custom_settings = { # 自定制配置文件，自己设置了用自己的，没有就找父类的
"BOT_NAME": 'HAIYAN_AMAZON',
'REQUSET_HEADERS': {},
} def start_requests(self):
url = 'https://www.amazon.cn/s/ref=nb_sb_noss_1/461-4093573-7508641?'
url+=urlencode({"field-keywords":self.keyword})
print(url)
yield scrapy.Request(
url,
callback = self.parse_index, #指定回调函数
dont_filter = True, #不去重，这个也可以自己定制
# dont_filter = False, #去重，这个也可以自己定制
# meta={'a':1} #meta代理的时候会用
)
#如果要想测试自定义的dont_filter，可多返回结果重复的即可 def parse_index(self, response):
'''获取详情页和下一页的链接'''
detail_urls = response.xpath('//*[contains(@id,"result_")]/div/div[3]/div[1]/a/@href').extract()
print(detail_urls)
# print("%s 解析 %s",(response.url,(len(response.body))))
for detail_url in detail_urls:
yield scrapy.Request(
url=detail_url,
callback=self.parse_detail #记得每次返回response的时候记得绑定一个回调函数
)
next_url = response.urljoin(response.xpath(response.xpath('//*[@id="pagnNextLink"]/@href').extract_first()))
# 因为下一页的url是不完整的，用urljoin就可以吧路径前缀拿到并且拼接
# print(next_url)
yield scrapy.Request(
url=next_url,
callback=self.parse_index #因为下一页也属于是索引页，让去解析索引页
)
def parse_detail(self,response):
'''详情页解析'''
name = response.xpath('//*[@id="productTitle"]/text()').extract_first().strip()#获取name
price = response.xpath('//*[@id="price"]//*[@class="a-size-medium a-color-price"]/text()').extract_first()#获取价格
delivery_method=''.join(response.xpath('//*[@id="ddmMerchantMessage"]//text()').extract()) #获取配送方式
print(name)
print(price)
print(delivery_method)
#上面是筛选出自己想要的项
#必须返回一个Item对象,那么这个item对象，是从item.py中来，和django中的model类似，
# 但是这里的item对象也可当做是一个字典，和字典的操作一样
item = AmazonItem()# 实例化
item["name"] = name
item["price"] = price
item["delivery_method"] = delivery_method
return item def close(spider, reason):
print("结束啦")

我们可能需要在命令行为爬虫程序传递参数，比如传递初始的url，像这样
#命令行执行
scrapy crawl myspider -a category=electronics #在__init__方法中可以接收外部传进来的参数
import scrapy class MySpider(scrapy.Spider):
name = 'myspider' def __init__(self, category=None, *args, **kwargs):
super(MySpider, self).__init__(*args, **kwargs)
self.start_urls = ['http://www.example.com/categories/%s' % category]
#... #注意接收的参数全都是字符串，如果想要结构化的数据，你需要用类似json.loads的方法

response.selector.css()
response.selector.xpath()
可简写为
response.css()
response.xpath() #1 //与/
response.xpath('//body/a/')#
response.css('div a::text') >>> response.xpath('//body/a') #开头的//代表从整篇文档中寻找,body之后的/代表body的儿子
[]
>>> response.xpath('//body//a') #开头的//代表从整篇文档中寻找,body之后的//代表body的子子孙孙
[<Selector xpath='//body//a' data='<a href="image1.html">Name: My image 1 <'>, <Selector xpath='//body//a' data='<a href="image2.html">Name: My image 2 <'>, <Selector xpath='//body//a' data='<a href="
image3.html">Name: My image 3 <'>, <Selector xpath='//body//a' data='<a href="image4.html">Name: My image 4 <'>, <Selector xpath='//body//a' data='<a href="image5.html">Name: My image 5 <'>] #2 text
>>> response.xpath('//body//a/text()')
>>> response.css('body a::text') #3、extract与extract_first:从selector对象中解出内容
>>> response.xpath('//div/a/text()').extract()
['Name: My image 1 ', 'Name: My image 2 ', 'Name: My image 3 ', 'Name: My image 4 ', 'Name: My image 5 ']
>>> response.css('div a::text').extract()
['Name: My image 1 ', 'Name: My image 2 ', 'Name: My image 3 ', 'Name: My image 4 ', 'Name: My image 5 '] >>> response.xpath('//div/a/text()').extract_first()
'Name: My image 1 '
>>> response.css('div a::text').extract_first()
'Name: My image 1 ' #4、属性：xpath的属性加前缀@
>>> response.xpath('//div/a/@href').extract_first()
'image1.html'
>>> response.css('div a::attr(href)').extract_first()
'image1.html' #4、嵌套查找
>>> response.xpath('//div').css('a').xpath('@href').extract_first()
'image1.html' #5、设置默认值
>>> response.xpath('//div[@id="xxx"]').extract_first(default="not found")
'not found' #4、按照属性查找
response.xpath('//div[@id="images"]/a[@href="image3.html"]/text()').extract()
response.css('#images a[@href="image3.html"]/text()').extract() #5、按照属性模糊查找
response.xpath('//a[contains(@href,"image")]/@href').extract()
response.css('a[href*="image"]::attr(href)').extract() response.xpath('//a[contains(@href,"image")]/img/@src').extract()
response.css('a[href*="imag"] img::attr(src)').extract() response.xpath('//*[@href="image1.html"]')
response.css('*[href="image1.html"]') #6、正则表达式
response.xpath('//a/text()').re(r'Name: (.*)')
response.xpath('//a/text()').re_first(r'Name: (.*)') #7、xpath相对路径
>>> res=response.xpath('//a[contains(@href,"3")]')[0]
>>> res.xpath('img')
[<Selector xpath='img' data='<img src="data:image3_thumb.jpg">'>]
>>> res.xpath('./img')
[<Selector xpath='./img' data='<img src="data:image3_thumb.jpg">'>]
>>> res.xpath('.//img')
[<Selector xpath='.//img' data='<img src="data:image3_thumb.jpg">'>]
>>> res.xpath('//img') #这就是从头开始扫描
[<Selector xpath='//img' data='<img src="data:image1_thumb.jpg">'>, <Selector xpath='//img' data='<img src="data:image2_thumb.jpg">'>, <Selector xpath='//img' data='<img src="data:image3_thumb.jpg">'>, <Selector xpa
th='//img' data='<img src="data:image4_thumb.jpg">'>, <Selector xpath='//img' data='<img src="data:image5_thumb.jpg">'>] #8、带变量的xpath
>>> response.xpath('//div[@id=$xxx]/a/text()',xxx='images').extract_first()
'Name: My image 1 '
>>> response.xpath('//div[count(a)=$yyy]/@id',yyy=5).extract_first() #求有5个a标签的div的id
'images'

#一：可以写多个Pipeline类
#1、如果优先级高的Pipeline的process_item返回一个值或者None，会自动传给下一个pipline的process_item,
#2、如果只想让第一个Pipeline执行，那得让第一个pipline的process_item抛出异常raise DropItem() #3、可以用spider.name == '爬虫名' 来控制哪些爬虫用哪些pipeline 二：示范
from scrapy.exceptions import DropItem class CustomPipeline(object):
def __init__(self,v):
self.value = v @classmethod
def from_crawler(cls, crawler):
"""
Scrapy会先通过getattr判断我们是否自定义了from_crawler,有则调它来完
成实例化
"""
val = crawler.settings.getint('MMMM')
return cls(val) def open_spider(self,spider):
"""
爬虫刚启动时执行一次
"""
print('') def close_spider(self,spider):
"""
爬虫关闭时执行一次
"""
print('') 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()

'''
#1、settings.py
HOST="127.0.0.1"
PORT=27017
USER="root"
PWD="123"
DB="amazon"
TABLE="goods" '''
from scrapy.exceptions import DropItem
from pymongo import MongoClient class MongoPipeline(object):
'''2、把解析好的item对象做一个持久化，保存到数据库中'''
def __init__(self,db,collection,host,port,user,pwd):
self.db = db
self.collection = collection #文档(表)
self.host = host
self.port = port
self.user = user
self.pwd = pwd @classmethod
def from_crawler(cls,crawler):
'''1、Scrapy会先通过getattr判断我们是否自定义了from_crawler,有则调它来完
成实例化'''
db = crawler.settings.get("DB")
collection = crawler.settings.get("COLLECTION")
host = crawler.settings.get("HOST")
port = crawler.settings.get("PORT")
user = crawler.settings.get("USER")
pwd = crawler.settings.get("PWD")
return cls(db,collection,host,port,user,pwd) #cls是当前的类，类加括号执行__init__方法 def open_spider(self,spider):
'''3、爬虫刚启动时执行一次'''
print('==============>爬虫程序刚刚启动')
self.client = MongoClient('mongodb://%s:%s@%s:%s'%(
self.user,
self.pwd,
self.host,
self.port
)) def close_spider(self,spider):
'''5、关闭爬虫程序'''
print('==============>爬虫程序运行完毕')
self.client.close() def process_item(self, item, spider):
'''4、操作并执行持久化'''
# return表示会被后续的pipeline继续处理
d = dict(item)
if all(d.values()):
self.client[self.db][self.collection].save(d) #保存到数据库
return item
# 表示将item丢弃，不会被后续pipeline处理
# raise DropItem() class FilePipeline(object):
def __init__(self, file_path):
self.file_path=file_path @classmethod
def from_crawler(cls, crawler):
"""
Scrapy会先通过getattr判断我们是否自定义了from_crawler,有则调它来完
成实例化
"""
file_path = crawler.settings.get('FILE_PATH') return cls(file_path) def open_spider(self, spider):
"""
爬虫刚启动时执行一次
"""
print('==============>爬虫程序刚刚启动')
self.fileobj=open(self.file_path,'w',encoding='utf-8') def close_spider(self, spider):
"""
爬虫关闭时执行一次
"""
print('==============>爬虫程序运行完毕')
self.fileobj.close() 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
d = dict(item)
if all(d.values()):
self.fileobj.write(r"%s\n" %str(d)) return item # 表示将item丢弃，不会被后续pipeline处理
# raise DropItem()

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

from scrapy import signals
from scrapy.http import Response
from scrapy.exceptions import IgnoreRequest
from AMAZON.proxy_handle import get_proxy,delete_proxy
class AmazonSpiderMiddleware(object):
# Not all methods need to be defined. If a method is not defined,
# scrapy acts as if the spider middleware does not modify the
# passed objects. @classmethod
def from_crawler(cls, crawler):
# This method is used by Scrapy to create your spiders.
s = cls()
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
return s def process_spider_input(self, response, spider):
# Called for each response that goes through the spider
# middleware and into the spider. # Should return None or raise an exception.
return None def process_spider_output(self, response, result, spider):
# Called with the results returned from the Spider, after
# it has processed the response. # Must return an iterable of Request, dict or Item objects.
for i in result:
yield i def process_spider_exception(self, response, exception, spider):
# Called when a spider or process_spider_input() method
# (from other spider middleware) raises an exception. # Should return either None or an iterable of Response, dict
# or Item objects.
pass def process_start_requests(self, start_requests, spider):
# Called with the start requests of the spider, and works
# similarly to the process_spider_output() method, except
# that it doesn’t have a response associated. # Must return only requests (not items).
for r in start_requests:
yield r def spider_opened(self, spider):
spider.logger.info('Spider opened: %s' % spider.name) class AmazonDownloaderMiddleware(object):
# Not all methods need to be defined. If a method is not defined,
# scrapy acts as if the downloader middleware does not modify the
# passed objects. @classmethod
def from_crawler(cls, crawler):
# This method is used by Scrapy to create your spiders.
s = cls()
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
return s def process_request(self, request, spider):
# Called for each request that goes through the downloader
# middleware. # Must either:
# - return None: continue processing this request
# - or return a Response object
# - or return a Request object
# - or raise IgnoreRequest: process_exception() methods of
# installed downloader middleware will be called
return None def process_response(self, request, response, spider):
# Called with the response returned from the downloader. # Must either;
# - return a Response object
# - return a Request object
# - or raise IgnoreRequest
return response def process_exception(self, request, exception, spider):
# Called when a download handler or a process_request()
# (from other downloader middleware) raises an exception. # Must either:
# - return None: continue processing this exception
# - return a Response object: stops process_exception() chain
# - return a Request object: stops process_exception() chain
pass def spider_opened(self, spider):
spider.logger.info('Spider opened: %s' % spider.name) 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，会先打印response2,后打印response1
Request对象，停止中间件的执行，将Request重新调度器(无论在那个阶段，只要返回request，就丢给引擎了。)
raise IgnoreRequest异常，停止process_request的执行，开始执行process_exception
"""
# spider.name
print('下载中间件1')
# request.meta['proxy']='http://user:pwd@ip:port'
request.meta['download_timeout']=10 #设置超时时间
request.meta['proxy']='http://'+get_proxy() #request.meta加代理,注意这里的key必须叫proxy
print(request.meta)
# return Response('http://www.xxx.com')
# print(request.dont_filter)
# return request
# raise IgnoreRequest
# raise TimeoutError 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
"""
print('异常1')
# return None # 删旧代理 delelte request.meta['proxy']
old_proxy=request.meta['proxy'].split("//")[-1]
delete_proxy(old_proxy) #删除就代理， request.meta['proxy']='http://'+get_proxy() #换新代理
return request

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

#1、在与settings同级目录下新建一个文件，文件名可以为extentions.py,内容如下
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')
obj = cls(val) crawler.signals.connect(obj.spider_opened, signal=signals.spider_opened)
crawler.signals.connect(obj.spider_closed, signal=signals.spider_closed) return obj def spider_opened(self, spider):
print('=============>open') def spider_closed(self, spider):
print('=============>close') #2、配置生效
EXTENSIONS = {
"Amazon.extentions.MyExtension":200
}

#==>第一部分：基本配置<===
#1、项目名称，默认的USER_AGENT由它来构成，也作为日志记录的日志名
BOT_NAME = 'Amazon' #2、爬虫应用路径
SPIDER_MODULES = ['Amazon.spiders']
NEWSPIDER_MODULE = 'Amazon.spiders' #3、客户端User-Agent请求头
#USER_AGENT = 'Amazon (+http://www.yourdomain.com)' #4、是否遵循爬虫协议
# Obey robots.txt rules
ROBOTSTXT_OBEY = False #5、是否支持cookie，cookiejar进行操作cookie，默认开启
#COOKIES_ENABLED = False #6、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 = False
#TELNETCONSOLE_HOST = '127.0.0.1'
#TELNETCONSOLE_PORT = [6023,] #7、Scrapy发送HTTP请求默认使用的请求头
#DEFAULT_REQUEST_HEADERS = {
# 'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
# 'Accept-Language': 'en',
#} #===>第二部分：并发与延迟<===
#1、下载器总共最大处理的并发请求数,默认值16
#CONCURRENT_REQUESTS = 32 #2、每个域名能够被执行的最大并发请求数目，默认值8
#CONCURRENT_REQUESTS_PER_DOMAIN = 16 #3、能够被单个IP处理的并发请求数，默认值0，代表无限制，需要注意两点
#I、如果不为零，那CONCURRENT_REQUESTS_PER_DOMAIN将被忽略，即并发数的限制是按照每个IP来计算，而不是每个域名
#II、该设置也影响DOWNLOAD_DELAY，如果该值不为零，那么DOWNLOAD_DELAY下载延迟是限制每个IP而不是每个域
#CONCURRENT_REQUESTS_PER_IP = 16 #4、如果没有开启智能限速，这个值就代表一个规定死的值，代表对同一网址延迟请求的秒数
#DOWNLOAD_DELAY = 3 #===>第三部分：智能限速/自动节流：AutoThrottle extension<===
#一：介绍
from scrapy.contrib.throttle import AutoThrottle #http://scrapy.readthedocs.io/en/latest/topics/autothrottle.html#topics-autothrottle
设置目标：
1、比使用默认的下载延迟对站点更好
2、自动调整scrapy到最佳的爬取速度，所以用户无需自己调整下载延迟到最佳状态。用户只需要定义允许最大并发的请求，剩下的事情由该扩展组件自动完成 #二：如何实现？
在Scrapy中，下载延迟是通过计算建立TCP连接到接收到HTTP包头(header)之间的时间来测量的。
注意，由于Scrapy可能在忙着处理spider的回调函数或者无法下载，因此在合作的多任务环境下准确测量这些延迟是十分苦难的。 不过，这些延迟仍然是对Scrapy(甚至是服务器)繁忙程度的合理测量，而这扩展就是以此为前提进行编写的。 #三：限速算法
自动限速算法基于以下规则调整下载延迟
#1、spiders开始时的下载延迟是基于AUTOTHROTTLE_START_DELAY的值
#2、当收到一个response，对目标站点的下载延迟=收到响应的延迟时间/AUTOTHROTTLE_TARGET_CONCURRENCY
#3、下一次请求的下载延迟就被设置成：对目标站点下载延迟时间和过去的下载延迟时间的平均值
#4、没有达到200个response则不允许降低延迟
#5、下载延迟不能变的比DOWNLOAD_DELAY更低或者比AUTOTHROTTLE_MAX_DELAY更高 #四：配置使用
#开启True，默认False
AUTOTHROTTLE_ENABLED = True
#起始的延迟
AUTOTHROTTLE_START_DELAY = 5
#最小延迟
DOWNLOAD_DELAY = 3
#最大延迟
AUTOTHROTTLE_MAX_DELAY = 10
#每秒并发请求数的平均值，不能高于 CONCURRENT_REQUESTS_PER_DOMAIN或CONCURRENT_REQUESTS_PER_IP，调高了则吞吐量增大强奸目标站点，调低了则对目标站点更加”礼貌“
#每个特定的时间点，scrapy并发请求的数目都可能高于或低于该值，这是爬虫视图达到的建议值而不是硬限制
AUTOTHROTTLE_TARGET_CONCURRENCY = 16.0
#调试
AUTOTHROTTLE_DEBUG = True
CONCURRENT_REQUESTS_PER_DOMAIN = 16
CONCURRENT_REQUESTS_PER_IP = 16 #===>第四部分：爬取深度与爬取方式<===
#1、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 #2、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' #3、调度器队列
# SCHEDULER = 'scrapy.core.scheduler.Scheduler'
# from scrapy.core.scheduler import Scheduler #4、访问URL去重
# DUPEFILTER_CLASS = 'step8_king.duplication.RepeatUrl' #===>第五部分：中间件、Pipelines、扩展<===
#1、Enable or disable spider middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/spider-middleware.html
#SPIDER_MIDDLEWARES = {
# 'Amazon.middlewares.AmazonSpiderMiddleware': 543,
#} #2、Enable or disable downloader middlewares
# See http://scrapy.readthedocs.org/en/latest/topics/downloader-middleware.html
DOWNLOADER_MIDDLEWARES = {
# 'Amazon.middlewares.DownMiddleware1': 543,
} #3、Enable or disable extensions
# See http://scrapy.readthedocs.org/en/latest/topics/extensions.html
#EXTENSIONS = {
# 'scrapy.extensions.telnet.TelnetConsole': None,
#} #4、Configure item pipelines
# See http://scrapy.readthedocs.org/en/latest/topics/item-pipeline.html
ITEM_PIPELINES = {
# 'Amazon.pipelines.CustomPipeline': 200,
} #===>第六部分：缓存<===
"""
1. 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 = 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'