|
|
# 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
|
|
|
from scrapy.http.response.html import HtmlResponse
|
|
|
# 改造返回类
|
|
|
|
|
|
#selenium
|
|
|
from selenium import webdriver
|
|
|
from selenium.webdriver.support import expected_conditions as EC
|
|
|
from selenium.webdriver.support.ui import WebDriverWait
|
|
|
from selenium.webdriver.common.by import By
|
|
|
from selenium.webdriver.firefox.firefox_profile import FirefoxProfile
|
|
|
#自定义
|
|
|
import logging
|
|
|
# useful for handling different item types with a single interface
|
|
|
from itemadapter import is_item, ItemAdapter
|
|
|
|
|
|
import time
|
|
|
|
|
|
|
|
|
|
|
|
class TestSpiderMiddleware:
|
|
|
# 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 TestDownloaderMiddleware(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.
|
|
|
def __init__(self,timeout = 25):
|
|
|
# 初始化参数
|
|
|
options = webdriver.FirefoxOptions()
|
|
|
# 使用该参数就不会看到启动，无头
|
|
|
# options.add_argument('-headless')
|
|
|
self.browser = webdriver.Firefox(options=options,executable_path=r"C:\Users\cookie\Desktop\Test\Test\spiders\geckodriver.exe")
|
|
|
profile = FirefoxProfile()
|
|
|
#设置火狐具体配置
|
|
|
self.timeout = timeout
|
|
|
#self.browser = webdriver.Firefox(profile)
|
|
|
self.browser.set_page_load_timeout(self.timeout)
|
|
|
# self.browser.implicitly_wait(self.timeout)
|
|
|
# 隐式等待
|
|
|
|
|
|
#每次爬取都初始化
|
|
|
def __del__(self):
|
|
|
self.browser.close()
|
|
|
#关闭
|
|
|
@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
|
|
|
"""
|
|
|
selenium 下载中间件
|
|
|
"""
|
|
|
|
|
|
logging.info('******WebDriver is Starting******')
|
|
|
print('使用selenium请求页面:{}'.format(request.url))
|
|
|
#page = request.meta.get('page', 1)
|
|
|
try:
|
|
|
self.browser.get(request.url)
|
|
|
#if page > 1:
|
|
|
self.browser.implicitly_wait(self.timeout)
|
|
|
return HtmlResponse(url=request.url, body=self.browser.page_source, request=request, encoding='utf-8',
|
|
|
status=200)
|
|
|
except TimeoutError:
|
|
|
return HtmlResponse(url=request.url, status=500, request=request)
|
|
|
# self.browser.get(request.url)
|
|
|
# time.sleep(1)
|
|
|
# try:
|
|
|
# while True:
|
|
|
# show_more = self.browser.find_element_by_class_name('show-more')
|
|
|
# show_more.click()
|
|
|
# time.sleep(3)
|
|
|
# if not show_more:
|
|
|
# break
|
|
|
# except:
|
|
|
# pass
|
|
|
# # 获得网页源代码
|
|
|
# source = self.browser.page_source
|
|
|
# # 构造response对象 | 进行返回
|
|
|
# response = HtmlResponse(url=self.browser.current_url, body=source, request=request, encoding='utf-8')
|
|
|
# return response
|
|
|
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)
|
