226 lines
8.5 KiB
Python
226 lines
8.5 KiB
Python
# -*- coding: utf-8 -*-
|
||
|
||
# Define here the models for your spider middleware
|
||
#
|
||
# See documentation in:
|
||
# https://docs.scrapy.org/en/latest/topics/spider-middleware.html
|
||
|
||
from scrapy import signals
|
||
import scrapy
|
||
from redisbloom.client import Client
|
||
from scrapy.exceptions import IgnoreRequest
|
||
from selenium import webdriver
|
||
from selenium.webdriver.chrome.options import Options
|
||
from scrapy.http import HtmlResponse
|
||
from scrapy import signals
|
||
from ShipSpiders.utils.http_utils import http_get
|
||
import os
|
||
from scrapy.exceptions import IgnoreRequest
|
||
import random
|
||
import time
|
||
from twisted.internet.error import ConnectionRefusedError
|
||
|
||
class ShipspidersSpiderMiddleware(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 Request, 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 ShipspidersDownloaderMiddleware(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 UserAgentDownloaderMiddleware(object):
|
||
@classmethod
|
||
def from_crawler(cls, crawler):
|
||
# This method is used by Scrapy to create your spiders.
|
||
s = cls()
|
||
s.uas = crawler.spider.settings['CUSTOM_USER_AGENT']
|
||
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
|
||
return s
|
||
|
||
def process_request(self, request, spider):
|
||
UA = random.choice(self.uas)
|
||
if request.headers is None:
|
||
request.headers = {}
|
||
request.headers['User-Agent'] = UA
|
||
return None
|
||
|
||
def spider_opened(self, spider):
|
||
spider.logger.info('Spider opened: %s' % spider.name)
|
||
|
||
class MyProxyDownloaderMiddleware(object):
|
||
@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.
|
||
if self.request_count == 0 or self.request_count >= int(spider.settings['PER_BATCH_IP_USE_TIMES']):
|
||
self.request_count = 0
|
||
self.proxyIpList = []
|
||
proxy_service = spider.settings['PROXY_SERVICE']
|
||
#调用自建Ip池api
|
||
self.proxyIpList = http_get(proxy_service + 'get_all')
|
||
while len(self.proxyIpList) == 0:
|
||
self.proxyIpList = http_get(proxy_service + 'get_all')
|
||
time.sleep(1)
|
||
|
||
proxy = random.choice(self.proxyIpList)
|
||
request.meta['proxy'] = 'http://%s'%proxy['proxy']
|
||
self.request_count += 1
|
||
return None
|
||
|
||
def process_exception(self, request, exception, spider):
|
||
if isinstance(exception,ConnectionRefusedError):
|
||
proxy_service = spider.settings['PROXY_SERVICE']
|
||
http_get(proxy_service + 'delete?proxy=' + request.meta['proxy'].split('/')[-1])
|
||
return request
|
||
return None
|
||
|
||
def spider_opened(self, spider):
|
||
self.request_count = 0
|
||
spider.logger.info('Spider opened: %s' % spider.name)
|
||
|
||
class DumpFilterDownloaderMiddleware(object):
|
||
@classmethod
|
||
def from_crawler(cls, crawler):
|
||
# This method is used by Scrapy to create your spiders.
|
||
s = cls()
|
||
redisHost = crawler.spider.settings['REDIS_HOST']
|
||
redisPort = crawler.spider.settings['REDIS_PORT']
|
||
pwd = crawler.spider.settings['REDIS_PWD']
|
||
s.bloomFilter = Client(host= redisHost, port= redisPort,password= pwd)
|
||
s.deepth = crawler.spider.settings['CRAWL_DEEPTH']
|
||
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
|
||
return s
|
||
|
||
def process_request(self, request, spider):
|
||
#判重
|
||
if 'CUSTOM_FILTER_KEY' in request.meta and 'CUSTOM_FILTER_VAL' in request.meta:
|
||
key = request.meta['CUSTOM_FILTER_KEY']
|
||
val = request.meta['CUSTOM_FILTER_VAL']
|
||
if self.bloomFilter.bfExists(key, val) == 1:
|
||
spider.logger.info("[KEY EXISTED] '%s' exists! Skip to next request." % val)
|
||
raise IgnoreRequest()
|
||
return None
|
||
def process_exception(self, request, exception, spider):
|
||
return None
|
||
|
||
def spider_opened(self, spider):
|
||
spider.logger.info('Spider opened: %s' % spider.name)
|
||
|
||
class DumpFiliterSpiderMiddleware(object):
|
||
@classmethod
|
||
def from_crawler(cls, crawler):
|
||
# This method is used by Scrapy to create your spiders.
|
||
s = cls()
|
||
redisHost = crawler.spider.settings['REDIS_HOST']
|
||
redisPort = crawler.spider.settings['REDIS_PORT']
|
||
pwd = crawler.spider.settings['REDIS_PWD']
|
||
s.bloomFilter = Client(host= redisHost, port= redisPort,password= pwd)
|
||
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
|
||
return s
|
||
|
||
def process_spider_output(self, response, result, spider):
|
||
for i in result:
|
||
#对于符合爬取条件的请求，加入判重
|
||
if isinstance(i, scrapy.Item):
|
||
if 'CUSTOM_FILTER_KEY' in response.request.meta and 'CUSTOM_FILTER_VAL' in response.request.meta:
|
||
key = response.request.meta['CUSTOM_FILTER_KEY']
|
||
val = response.request.meta['CUSTOM_FILTER_VAL']
|
||
if self.bloomFilter.bfAdd(key, val) <= 0:
|
||
continue
|
||
spider.logger.info("[KEY ADDED] '%s' added." % val)
|
||
yield i
|
||
|
||
def spider_opened(self, spider):
|
||
spider.logger.info('Spider opened: %s' % spider.name) |