pipelines.py
chouti.py
import scrapy
from scrapy.http import Request
from ..items import XianglongItem
class ChoutiSpider(scrapy.Spider):
name = 'chouti'
allowed_domains = ['chouti.com']
start_urls = ['http://dig.chouti.com/',]
def start_requests(self):
for url in self.start_urls:
yield Request(url=url,callback=self.parse_pipeline)
def parse_pipeline(self,response):
items = response.xpath("//div[@id='content-list']/div[@class='item']")
for item in items:
href = item.xpath('.//div[@class="part1"]//a[1]/@href').extract_first()
text = item.xpath('.//div[@class="part1"]//a[1]/text()').extract_first()
item = XianglongItem(title=text, href=href)
yield item
items.py
import scrapy
class XianglongItem(scrapy.Item):
title = scrapy.Field()
href = scrapy.Field()
pipelines.py
"""
当根据配置文件:
ITEM_PIPELINES = {
'xianglong.pipelines.FilePipeline': 300,
'xianglong.pipelines.DBPipeline': 301,
}
找到相关的类:FilePipeline之后,会优先判断类中是否含有 from_crawler
如果有:
obj = FilePipeline.from_crawler()
没有则:
obj = FilePipeline()
obj.open_spider(..)
ob.process_item(..)
obj.close_spider(..)
"""
from scrapy.exceptions import DropItem
class FilePipeline(object):
def __init__(self,path):
self.path = path
self.filer = None
@classmethod
def from_crawler(cls, crawler):
path = crawler.settings.get('XL_FILE_PATH')
return cls(path)
def process_item(self, item, spider):
self.filer.write(item['href']+'\n')
return item
def open_spider(self, spider):
self.filer = open(self.path,'w')
def close_spider(self, spider):
self.filer.close()
class DBPipeline(object):
def process_item(self, item, spider):
print('数据库',item["href"])
return item
def open_spider(self, spider):
print('打开数据')
def close_spider(self, spider):
print('关闭数据库')
settings.py
ITEM_PIPELINES = {
'xianglong.pipelines.FilePipeline': 300,
'xianglong.pipelines.DBPipeline': 301,
}
XL_FILE_PATH = "xl.log"
测试如下:
E:\python\xx\xianglong - 1 - pipelines>scrapy crawl chouti --nolog
打开数据
数据库 http://www.bjnews.com.cn/news/2018/05/11/486583.html
数据库 https://weibo.com/2178985701/Gg8XsxlJd
数据库 http://tech.qq.com/a/20180511/025847.htm
数据库 http://finance.sina.com.cn/money/insurance/bxdt/2018-05-11/doc-ihamfahw3773053.shtml
数据库 https://www.zhihu.com/question/266252635/answer/344487421
数据库 http://dig.chouti.com/pic/show?nid=e7d46c243dc4958d6d1afb030420f381&lid=19446191
数据库 https://www.thepaper.cn/newsDetail_forward_2123987
数据库 https://www.thepaper.cn/newsDetail_forward_2123704
数据库 https://mp.weixin.qq.com/s/vcK5Ew1xCQuc4LlqjNCUFQ
数据库 https://dig.chouti.com/user/cdu_44476851294/submitted/1
数据库 https://www.miaopai.com/show/nTckVvYDtr1Jgwvg6tKBU8uZ5~fnmVSSbzkzmQ__.htm
数据库 https://www.thepaper.cn/newsDetail_forward_2124022
数据库 http://dig.chouti.com/pic/show?nid=c4f9cf6ad4bc861f11437ff6b9e2af6b&lid=19444656
数据库 http://tech.163.com/18/0510/22/DHFRA37S00097U7R.html
数据库 http://www.pearvideo.com/video_1341634
数据库 http://dig.chouti.com/pic/show?nid=fe50ff217fba43838eb85b894588a762&lid=19442361
数据库 https://weibo.com/tv/v/Gg8DF40SK?fid=1034:1adeec4f87115424b0f493f5f0a6f82c
数据库 http://tech.qq.com/a/20180511/021642.htm
数据库 https://www.jiemian.com/article/2115446.html
数据库 http://world.huanqiu.com/exclusive/2018-05/12013262.html
数据库 http://sports.sina.com.cn/g/seriea/2018-05-11/doc-ihamfahw0985498.shtml
数据库 http://www.vice.cn/read/the-vice-first-hand-report-hong-kong-is-running-out-of-space-to-bury-its-dead
数据库 http://tech.qq.com/a/20180511/021384.htm
数据库 https://mp.weixin.qq.com/s/Yko8396TRwzh1EuKi5Ymtw
数据库 http://www.pearvideo.com/video_1342215
关闭数据库
E:\python\xx\xianglong - 1 - pipelines>
手动操作cookie点赞
# -*- coding: utf-8 -*-
import scrapy
from bs4 import BeautifulSoup
from scrapy.selector import HtmlXPathSelector
from scrapy.http import Request
from ..items import XianglongItem
from scrapy.http import HtmlResponse
from scrapy.http.response.html import HtmlResponse
class ChoutiSpider(scrapy.Spider):
name = 'chouti'
allowed_domains = ['chouti.com']
start_urls = ['http://dig.chouti.com/',]
cookie_dict = {}
def start_requests(self):
for url in self.start_urls:
yield Request(url=url,callback=self.parse_index)
def parse_index(self,response):
# 原始cookie
# print(response.headers.getlist('Set-Cookie'))
# 解析后的cookie
from scrapy.http.cookies import CookieJar
cookie_jar = CookieJar()
cookie_jar.extract_cookies(response, response.request)
print("cookie_jar._cookies",cookie_jar._cookies)
for k, v in cookie_jar._cookies.items():
for i, j in v.items():
for m, n in j.items():
self.cookie_dict[m] = n.value
req = Request(
url='http://dig.chouti.com/login',
method='POST',
headers={'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8'},
body='phone=xxx&password=xxx&oneMonth=1',
cookies=self.cookie_dict,
callback=self.parse_check_login
)
yield req
def parse_check_login(self,response):
print("parse_check_login",response.text)
yield Request(
url='https://dig.chouti.com/link/vote?linksId=19440976',
method='POST',
cookies=self.cookie_dict,
callback=self.parse_show_result
)
def parse_show_result(self,response):
print("parse_show_result",response.text)
print(“cookie_jar._cookies”,cookie_jar._cookies)输出
{
'.chouti.com': {
'/': {
'gpsd': Cookie(version = 0, name = 'gpsd', value = '8a6ae8658f1da53e542b965ad272fc91', port = None, port_specified = False, domain = '.chouti.com', domain_specified = True, domain_initial_dot = False, path = '/', path_specified = True, secure = False, expires = 1528621744, discard = False, comment = None, comment_url = None, rest = {}, rfc2109 = False)
}
},
'dig.chouti.com': {
'/': {
'JSESSIONID': Cookie(version = 0, name = 'JSESSIONID', value = 'aaaRJBpM5sKcScZiw_fmw', port = None, port_specified = False, domain = 'dig.chouti.com', domain_specified = False, domain_initial_dot = False, path = '/', path_specified = True, secure = False, expires = None, discard = True, comment = None, comment_url = None, rest = {}, rfc2109 = False),
'route': Cookie(version = 0, name = 'route', value = '37316285ff8286c7a96cd0b03d38e13b', port = None, port_specified = False, domain = 'dig.chouti.com', domain_specified = False, domain_initial_dot = False, path = '/', path_specified = True, secure = False, expires = None, discard = True, comment = None, comment_url = None, rest = {}, rfc2109 = False)
}
}
}
print(“parse_check_login”,response.text)输出如下:
{"result":{"code":"9999", "message":"", "data":{"complateReg":"0","destJid":"cdu_49803354421"}}}
print(“parse_show_result”,response.text)输出如下:
{"result":{"code":"30010", "message":"你已经推荐过了", "data":""}}
自动操作cookie点赞
# -*- coding: utf-8 -*-
import scrapy
from scrapy.http import Request
class ChoutiSpider(scrapy.Spider):
name = 'chouti'
allowed_domains = ['chouti.com']
start_urls = ['http://dig.chouti.com/',]
def start_requests(self):
for url in self.start_urls:
yield Request(url=url,callback=self.parse_index,meta={'cookiejar':True})
def parse_index(self,response):
req = Request(
url='http://dig.chouti.com/login',
method='POST',
headers={'Content-Type': 'application/x-www-form-urlencoded; charset=UTF-8'},
body='phone=8613121758648&password=woshiniba&oneMonth=1',
callback=self.parse_check_login,
meta={'cookiejar': True}
)
yield req
def parse_check_login(self,response):
# print(response.text)
yield Request(
url='https://dig.chouti.com/link/vote?linksId=19440976',
method='POST',
callback=self.parse_show_result,
meta={'cookiejar': True}
)
def parse_show_result(self,response):
print(response.text)
去重
scrapy默认使用 scrapy.dupefilter.RFPDupeFilter 进行去重,相关配置有:
DUPEFILTER_CLASS = 'scrapy.dupefilter.RFPDupeFilter'
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
dupe.py
from scrapy.dupefilter import BaseDupeFilter
from scrapy.utils.request import request_fingerprint
"""
1. 根据配置文件找到 DUPEFILTER_CLASS = 'xianglong.dupe.MyDupeFilter'
2. 判断是否存在from_settings
如果有:
obj = MyDupeFilter.from_settings()
否则:
obj = MyDupeFilter()
"""
class MyDupeFilter(BaseDupeFilter):
def __init__(self):
self.record = set()
@classmethod
def from_settings(cls, settings):
return cls()
#:return: True表示已经访问过;False表示未访问过
def request_seen(self, request):
ident = request_fingerprint(request)
if ident in self.record:
print('已经访问过了', request.url)
return True
self.record.add(ident)
def open(self): # can return deferred
pass
def close(self, reason): # can return a deferred
pass
配置如下:
DUPEFILTER_CLASS = 'xianglong.dupe.MyDupeFilter'
测试代码如下:
import scrapy
from scrapy.http import Request
class ChoutiSpider(scrapy.Spider):
name = 'chouti'
allowed_domains = ['chouti.com']
start_urls = ['https://dig.chouti.com/',]
def start_requests(self):
for url in self.start_urls:
yield Request(url=url,callback=self.parse)
def parse(self, response):
pages = response.xpath('//div[@id="page-area"]//a[@class="ct_pagepa"]/@href').extract()
for page_url in pages:
page_url = "https://dig.chouti.com" + page_url
yield Request(url=page_url,callback=self.parse)
效果:
E:\python\xx\xianglong - 4 - 去重>scrapy crawl chouti --nolog
已经访问过了 https://dig.chouti.com/all/hot/recent/3
已经访问过了 https://dig.chouti.com/all/hot/recent/4
已经访问过了 https://dig.chouti.com/all/hot/recent/5
已经访问过了 https://dig.chouti.com/all/hot/recent/6
已经访问过了 https://dig.chouti.com/all/hot/recent/7
已经访问过了 https://dig.chouti.com/all/hot/recent/8
已经访问过了 https://dig.chouti.com/all/hot/recent/9
已经访问过了 https://dig.chouti.com/all/hot/recent/10
已经访问过了 https://dig.chouti.com/all/hot/recent/1
已经访问过了 https://dig.chouti.com/all/hot/recent/7
已经访问过了 https://dig.chouti.com/all/hot/recent/8
已经访问过了 https://dig.chouti.com/all/hot/recent/9
已经访问过了 https://dig.chouti.com/all/hot/recent/1
已经访问过了 https://dig.chouti.com/all/hot/recent/2
已经访问过了 https://dig.chouti.com/all/hot/recent/3
已经访问过了 https://dig.chouti.com/all/hot/recent/4
已经访问过了 https://dig.chouti.com/all/hot/recent
中间件
在SpiderMiddleware
中
process_spider_input 是SpiderMiddleware下载完成,执行,然后交给parse处理
process_spider_output spider处理完成,返回时调用,必须返回包含 Request 或 Item 对象的可迭代对象(iterable)
process_spider_exception 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
process_start_requests 爬虫启动时调用
在DownMiddleware1
中
process_request
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
process_response
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
process_exception
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
自定义中间件
class UserAgentDownloaderMiddleware(object):
@classmethod
def from_crawler(cls, crawler):
# This method is used by Scrapy to create your spiders.
s = cls()
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
request.headers['User-Agent'] = "Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36"
# return None # 继续执行后续的中间件的process_request
# from scrapy.http import Request
# return Request(url='www.baidu.com') # 重新放入调度器中,当前请求不再继续处理
# from scrapy.http import HtmlResponse # 执行从最后一个开始执行所有的process_response
# return HtmlResponse(url='www.baidu.com',body=b'asdfuowjelrjaspdoifualskdjf;lajsdf')
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
DOWNLOADER_MIDDLEWARES = {
'xianglong.middlewares.UserAgentDownloaderMiddleware': 543,
}
其他
# -*- 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
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:[email protected]: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,
"""
# 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,
# }
settings