You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
145 lines
4.6 KiB
145 lines
4.6 KiB
5 years ago
|
# -*- coding: utf-8 -*-
|
||
|
|
||
|
# Define here the models for your spider middleware
|
||
|
#
|
||
|
# See documentation in:
|
||
|
# https://doc.scrapy.org/en/latest/topics/spider-middleware.html
|
||
|
|
||
|
from scrapy import signals
|
||
|
|
||
|
# ! -*- encoding:utf-8 -*-
|
||
|
import base64
|
||
|
import sys
|
||
|
import random
|
||
|
|
||
|
PY3 = sys.version_info[0] >= 3
|
||
|
|
||
|
|
||
|
def base64ify(bytes_or_str):
|
||
|
if PY3 and isinstance(bytes_or_str, str):
|
||
|
input_bytes = bytes_or_str.encode('utf8')
|
||
|
else:
|
||
|
input_bytes = bytes_or_str
|
||
|
|
||
|
output_bytes = base64.urlsafe_b64encode(input_bytes)
|
||
|
if PY3:
|
||
|
return output_bytes.decode('ascii')
|
||
|
else:
|
||
|
return output_bytes
|
||
|
|
||
|
|
||
|
class ProxyMiddleware(object):
|
||
|
def process_request(self, request, spider):
|
||
|
# 代理服务器
|
||
|
proxyHost = "n10.t.16yun.cn"
|
||
|
proxyPort = "31111"
|
||
|
|
||
|
# 代理隧道验证信息
|
||
|
proxyUser = "username"
|
||
|
proxyPass = "password"
|
||
|
|
||
|
request.meta['proxy'] = "http://{0}:{1}".format(proxyHost, proxyPort)
|
||
|
|
||
|
# 添加验证头
|
||
|
encoded_user_pass = base64ify(proxyUser + ":" + proxyPass)
|
||
|
request.headers['Proxy-Authorization'] = 'Basic ' + encoded_user_pass
|
||
|
|
||
|
# 设置IP切换头(根据需求)
|
||
|
tunnel = random.randint(1, 10000)
|
||
|
request.headers['Proxy-Tunnel'] = str(tunnel)
|
||
|
|
||
|
|
||
|
class TutorialSpiderMiddleware(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 TutorialDownloaderMiddleware(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)
|