2.pip install scrapy-splash
测试代码：
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'))
scrapy-splash接收到js请求：
版权声明：本文内容由互联网用户自发贡献，该文观点仅代表作者本人。本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌侵权/违法违规的内容， 请联系我们举报，一经查实，本站将立刻删除。
发布者：全栈程序员-站长，转载请注明出处：https://javaforall.net/219810.html原文链接：https://javaforall.net
![gcc离线安装 ubuntu 不用编译_「ubuntu安装gcc」ubuntu18.04安装gcc详细步骤（附问题集） – seo实验室…[通俗易懂]](https://javaforall.net/wp-content/uploads/2020/11/2020110817443450-480x300.jpg)
