复制

tutorial/ 
	scrapy.cfg        # 项目的配置文件 
	tutorial/         # 该项目的python模块。之后您将在此加入代码 
		__init__.py 
		items.py      # 项目中的item文件 
		pipelines.py  # 项目中的pipelines文件 
		settings.py   # 项目的设置文件 
		spiders/      # 放置spider代码的目录 __init__.py 
		...

复制

import scrapy

class KdlSpider(scrapy.spiders.Spider):
	name = "zdaye"

	def start_requests(self):
		url = "https://example.com"
		yield scrapy.Request(url, callback=self.parse)

	def parse(self, response):
		print(response.status)

复制

import time
import threading

import requests
from scrapy import signals

# 提取代理IP的api
api_url = 'http://www.***.com/ShortProxy/GetIP/?api=1234567890&akey=8a17ca305f683620&count=10×pan=3&type=3'
foo = True

class Proxy:

	def __init__(self, ):
		self._proxy_list=requests.get(api_url).json().get('data').get('proxy_list')

	@property
	def proxy_list(self):
		return self._proxy_list

	@proxy_list.setter
	def proxy_list(self,list):
		self._proxy_list=list


pro=Proxy()
print(pro.proxy_list)


class MyExtend:

	def__init__(self, crawler):
		self.crawler=crawler
		# 将自定义方法绑定到scrapy信号上,使程序与spider引擎同步启动与关闭
		# scrapy信号文档: https://www.osgeo.cn/scrapy/topics/signals.html
		# scrapy自定义拓展文档: https://www.osgeo.cn/scrapy/topics/extensions.html
		crawler.signals.connect(self.start,signals.engine_started)
		crawler.signals.connect(self.close,signals.spider_closed)

	@classmethod
	def from_crawler(cls,crawler):
		return cls(crawler)

	def start(self):
		t=threading.Thread(target=self.extract_proxy)
		t.start()

	def extract_proxy(self):
		while foo:
			pro.proxy_list=requests.get(api_url).json().get('data').get('proxy_list')
			#设置每15秒提取一次ip
			time.sleep(15)

	def close(self):
		global foo
		foo = False

复制

from scrapy import signals
from .myextend import pro
import random
# useful for handling different item types with a single interface
from itemadapter import is_item, ItemAdapter


class TutorialSpiderMiddleware:
	# 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, 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 Request 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 TutorialDownloaderMiddleware:
	# 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 ProxyDownloaderMiddleware:

	def process_request(self, request, spider):
		proxy = random.choice(pro.proxy_list)

		# 用户名密码授权
		username = "username"
		password = "password"
		request.meta['proxy'] = "http://%(user)s:%(pwd)s@%(proxy)s/" % {"user": username, "pwd": password, "proxy": proxy}

		# 终端IP授权
		# request.meta['proxy'] = "http://%(proxy)s/" % {"proxy": proxy}
		return None

复制

BOT_NAME = 'tutorial'

SPIDER_MODULES = ['tutorial.spiders']
NEWSPIDER_MODULE = 'tutorial.spiders'

ROBOTSTXT_OBEY = False

DOWNLOADER_MIDDLEWARES = {
	'tutorial.middlewares.ProxyDownloaderMiddleware': 100,
}
LOG_LEVEL = 'WARNING'

EXTENSIONS = {
	'tutorial.myextend.MyExtend': 300,
}