|
|
# 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, Request
|
|
|
from scrapy.http import HtmlResponse
|
|
|
from spider.utils import create_chrome_driver, add_cookies
|
|
|
|
|
|
|
|
|
# useful for handling different item types with a single interface
|
|
|
|
|
|
class SpiderSpiderMiddleware:
|
|
|
# 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 SpiderDownloaderMiddleware:
|
|
|
# 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 __init__(self): # 初始化数据管道时模拟用户登录
|
|
|
self.browser = create_chrome_driver(headless=True) #headless=True
|
|
|
self.browser.get('https://www.bilibili.com/v/popular/rank/all')
|
|
|
add_cookies(self.browser, "../cookies.txt")
|
|
|
|
|
|
def __del__(self): # 销毁时执行该方法
|
|
|
self.browser.close()
|
|
|
|
|
|
def process_request(self, request: 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.cookies = COOKIES_DICT[randint(0, len(COOKIES_DICT))]
|
|
|
# request.meta = {'proxy': 'http://127.0.0.1:7080'} # 使用代理,防封ip
|
|
|
self.browser.get(request.url)
|
|
|
return HtmlResponse(url=request.url, body=self.browser.page_source, # 获取动态内容
|
|
|
request=request, encoding='utf-8')
|
|
|
|
|
|
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 ProxyMiddleware(object):
|
|
|
def process_request(self, request, spider):
|
|
|
proxy = "http://172.20.10.2:7080"
|
|
|
request.meta["proxy"] = proxy
|
|
|
print(f"ProxyMiddleware --> {proxy}")
|
|
|
|
