Scrapy框架中结合splash 解析js ——环境配置

#--
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‘
import scrapy
from scrapy_splash import SplashRequest

class MySpider(scrapy.Spider):
    start_urls = ["http://example.com", "http://example.com/foo"]

    def start_requests(self):
        for url in self.start_urls:
            yield SplashRequest(url, self.parse, args={‘wait‘: 0.5})

    def parse(self, response):
        # response.body is a result of render.html call; it
        # contains HTML processed by a browser.
        # ...       
参考链接：　https://germey.gitbooks.io/python3webspider/content/7.2-Splash%E7%9A%84%E4%BD%BF%E7%94%A8.html
　　　　　　http://blog.csdn.net/qq_23849183/article/details/51287935
　　　　　　http://ae.yyuap.com/pages/viewpage.action?pageId=919763