Python 学习 Day33

def parse_index(html):
all_url = re.findall(r’<a href="(/films/\d+)"target=“blank"data_get=“movies-click"data-vel=”{movieId:\d+}“class=””>.+,
html])
return [http://www.movie.com{}.format(url) for url in all_url]

def parse_info(html):
name = re.findall(r’

(.+)

types = re.findall(r’

• (.+)
• 
  actors = re.findall(r’<li class = “celebrity actor”.+>\s+<a self = "/films/cel.+>\s+.html

  actors = e,xpath('//li[@class = "celebrity actor"]/div['class = "info"]/a/text()')
  actors = format_actor(	actor)
  return{
  			"name":name,
  			"types":types,
  			"actor":actor
  			}