#引用包
import requests
#因为一页有25部电影,所以有10页,页差距为25
page_indexs = range(0, 250, 25)
#爬取函数
def download_all_htmls():
"""
下载所有列表页面的HTML,用于后续的分析
"""
htmls = []
for idx in page_indexs:
url = f"https://movie.douban.com/top250?start={idx}&filter="
print("craw html:", url)
r = requests.get(url,