精英联盟总队|带大家写一波微信公众号的爬取!谁说微信爬不了的( 四 )

<', '').replace('>', '').replace('|', '_')pdfkit.from_url(value, os.path.join(self.savedir, key+'.pdf'), configuration=pdfkit.configuration(wkhtmltopdf=self.cfg.wkhtmltopdf_path))print('[INFO]: 已成功爬取目标公众号的所有文章内容...')'''类初始化'''def __initialize(self):self.headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.116 Safari/537.36 QBCore/4.0.1295.400 QQBrowser/9.0.2524.400 Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2875.116 Safari/537.36 NetType/WIFI MicroMessenger/7.0.5 WindowsWechat'}self.cookies = {'wxuin': '913366226','devicetype': 'iPhoneiOS13.3.1','version': '17000c27','lang': 'zh_CN','pass_ticket': self.cfg.pass_ticket,'wap_sid2': 'CNK5w7MDElxvQU1fdWNuU05qNV9lb2t3cEkzNk12ZHBsNmdXX3FETlplNUVTNzVfRmwyUUtKZzN4QkxJRUZIYkMtMkZ1SDU5S0FWQmtSNk9mTTQ1Q1NDOXpUYnJQaDhFQUFBfjDX5LD0BTgNQJVO'}self.profile_url = ''self.savedir = 'articles'self.session.headers.update(self.headers)self.session.cookies.update(self.cookies)'''run'''if __name__ == '__main__':import cfgspider = articlesSpider(cfg)spider.run()简单吧 。 不会的话就加我企鹅群领取视频教程和源代码 私信小编01


推荐阅读