selenium 在爬虫中的应用

 大多数在主体内容放在js代码里，想要爬取网页的整个内容

在scrapy里面应用selenium

wangyiPro.py  通过spider传递

# -*- coding: utf-8 -*-
import scrapy
from selenium import webdriver
from handle5 import items


class WangyiproSpider(scrapy.Spider):
    name = 'wangyiPro'
    # allowed_domains = ['www.xxx.com']
    start_urls = ['https://news.163.com/']

    def __init__(self):
        self.browser = webdriver.Chrome(r"D:\chromedriver_win\chromedriver")

middleware.py 里面加入selenium操作

class Handle5DownloaderMiddleware(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.

    @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
        return None

    def process_response(self, request, response, spider):
        # Called with the response returned from the downloader.
        # print("这是下载中间件", request.url)
        # Must either;
        url_list = ['http://news.163.com/world/', 'http://news.163.com/domestic/', 'http://war.163.com/', 'http://news.163.com/air/']
        # print("url", request.url)
        if request.url in url_list:
            # print(1)
            spider.browser.get(url=request.url)

            import time
            time.sleep(2)
            page_text = spider.browser.page_source
            # print("page_text", page_text)
            # time.sleep(2)
            return HtmlResponse(url=spider.browser.current_url, body=page_text, encoding='utf-8', request=request)
        # - return a Response object
        # - return a Request object
        # - or raise IgnoreRequest
        return response