import requestsfrom bs4 import BeautifulSoupimport time# 异步加载的网址规律url = 'https://knewone.com/discover?page='def get_page(url,data=None): respones = requests.get(url) soup = BeautifulSoup(respones.text,'lxml') Title = soup.select('section > h4 > a') img = soup.select('header > a > img') links = soup.select('header > a') if data==None: for Title,img,links in zip(Title,links): data = { 'Title' : Title.text, 'img' : img.get('src'), 'links': "https://knewone.com"+links.get('href') } print(data)def get_more_page(start,end): for i in range(start,end): get_page(url+str(i))get_more_page(1,10)
以上是内存溢出为你收集整理的python爬虫程序 异步加载爬虫knewone.com实例全部内容,希望文章能够帮你解决python爬虫程序 异步加载爬虫knewone.com实例所遇到的程序开发问题。
如果觉得内存溢出网站内容还不错,欢迎将内存溢出网站推荐给程序员好友。
欢迎分享,转载请注明来源:内存溢出
评论列表(0条)