SPLASH_URL = 'http://localhost:8050'
  DOWNLOADER_MIDDLEWARES = {
    'scrapy_splash.SplashCookiesMiddleware': 723,
    'scrapy_splash.SplashMiddleware': 725,
    'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
  }
  SPIDER_MIDDLEWARES = {
    'scrapy_splash.SplashDeduplicateArgsMiddleware': 100,
  }
  DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter'
  HTTPCACHE_STORAGE = 'scrapy_splash.SplashAwareFSCacheStorage'

from scrapy_splash import SplashRequest
yield SplashRequest(self.start_urls[0], callback=self.parse, args={'wait': 0.5})

import datetime
import os
 
import scrapy
from scrapy_splash import SplashRequest
 
from ..settings import LOG_DIR
 
 
class SplashSpider(scrapy.Spider):
  name = 'splash'
  allowed_domains = ['biqugedu.com']
  start_urls = ['http://www.biqugedu.com/0_25/']
 
  custom_settings = {
    'LOG_FILE': os.path.join(LOG_DIR, '%s_%s.log' % (name, datetime.date.today().strftime('%Y-%m-%d'))),
    'LOG_LEVEL': 'INFO',
    'CONCURRENT_REQUESTS': 8,
    'AUTOTHROTTLE_ENABLED': True,
    'AUTOTHROTTLE_TARGET_CONCURRENCY': 8,
 
    'SPLASH_URL': 'http://localhost:8050',
    'DOWNLOADER_MIDDLEWARES': {
      'scrapy_splash.SplashCookiesMiddleware': 723,
      'scrapy_splash.SplashMiddleware': 725,
      'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
    },
    'SPIDER_MIDDLEWARES': {
      'scrapy_splash.SplashDeduplicateArgsMiddleware': 100,
    },
    'DUPEFILTER_CLASS': 'scrapy_splash.SplashAwareDupeFilter',
    'HTTPCACHE_STORAGE': 'scrapy_splash.SplashAwareFSCacheStorage',
 
  }
 
  def start_requests(self):
    yield SplashRequest(self.start_urls[0], callback=self.parse, args={'wait': 0.5})
 
  def parse(self, response):
    """
    :param response:
    :return:
    """
    response_str = response.body.decode('utf-8', 'ignore')
    self.logger.info(response_str)
    self.logger.info(response_str.find('http://www.biqugedu.com/files/article/image/0/25/25s.jpg'))