scrapy 中集成 selenium

• 因为在called for each request that goes through the downloader middleware。每一请求进过下载中间键时会被调用。在方法process_request 中集成。

from scrapy.http.response.html import HtmlResponse
from selenium import webdriver

class SeleniumSpiderDownloaderMiddleware(object):
    """继承selenium"""

    def __init__(self):
        option = webdriver.ChromeOptions()
        option.add_argument('User-Agent=Mozilla/5.0 (Macintosh; U; Intel Mac OS X 10_6_8; en-us) AppleWebKit/534.50 (KHTML, like Gecko) Version/5.1 Safari/534.50')
        option.add_experimental_option('excludeSwitches', ['enable-automation'])
        prefs = {
            "profile.managed_default_content_settings.images": 2
        }
        option.add_experimental_option('prefs',prefs) #设置不加载图片
        option.add_argument("--headless") # 设置无头

        self.driver = webdriver.Chrome(options=option)



    def process_request(self,request,spider):

        self.driver.get(request.url)
        time.sleep(1)
        source = self.driver.page_source
        if not source:
        	print("INFO: %s %s"%(datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S"),source)) 
        source =source.encode("utf-8")
        Response=HtmlResponse(url=self.driver.current_url,body=source,request=request,encoding="utf-8")
        return Response