爬虫进阶-JS自动渲染之Scrapy_splash组件的使用

{ 
"registry-mirrors": ["https://registry.docker-cn.com"] 
}

sudo docker ps -a
sudo docker stop CONTAINER_ID
sudo docker rm CONTAINER_ID

scrapy startproject test_splash
cd test_splash
scrapy genspider no_splash baidu.com
scrapy genspider with_splash baidu.com

# 渲染服务的url
SPLASH_URL = 'http://127.0.0.1:8050'
# 下载器中间件
DOWNLOADER_MIDDLEWARES = {
    'scrapy_splash.SplashCookiesMiddleware': 723,
    'scrapy_splash.SplashMiddleware': 725,
    'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
}
# 去重过滤器
DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter'
# 使用Splash的Http缓存
HTTPCACHE_STORAGE = 'scrapy_splash.SplashAwareFSCacheStorage'

# Obey robots.txt rules
ROBOTSTXT_OBEY = False

import scrapy

class NoSplashSpider(scrapy.Spider):
    name = 'no_splash'
    allowed_domains = ['baidu.com']
    start_urls = ['https://www.baidu.com/s?wd=13161933309']

    def parse(self, response):
        with open('no_splash.html', 'w') as f:
            f.write(response.body.decode())

import scrapy
from scrapy_splash import SplashRequest # 使用scrapy_splash包提供的request对象

class WithSplashSpider(scrapy.Spider):
    name = 'with_splash'
    allowed_domains = ['baidu.com']
    start_urls = ['https://www.baidu.com/s?wd=13161933309']

    def start_requests(self):
        yield SplashRequest(self.start_urls[0],
                            callback=self.parse_splash,
                            args={'wait': 10}, # 最大超时时间，单位：秒
                            endpoint='render.html') # 使用splash服务的固定参数

    def parse_splash(self, response):
        with open('with_splash.html', 'w') as f:
            f.write(response.body.decode())

scrapy crawl no_splash
scrapy crawl with_splash

SPLASH_URL = 'http://127.0.0.1:8050'
DOWNLOADER_MIDDLEWARES = {
    'scrapy_splash.SplashCookiesMiddleware': 723,
    'scrapy_splash.SplashMiddleware': 725,
    'scrapy.downloadermiddlewares.httpcompression.HttpCompressionMiddleware': 810,
}
DUPEFILTER_CLASS = 'scrapy_splash.SplashAwareDupeFilter'
HTTPCACHE_STORAGE = 'scrapy_splash.SplashAwareFSCacheStorage'