爬取豆瓣电影

1. 代码

   # _*_ coding::utf_8 _*_
   import re
   import urllib.parse
   import urllib.request
   url='https://movie.douban.com/j/search_subjects?type=movie&tag=%E7%A7%91%E5%B9%BB&sort=rank&'
   # page=int(input("请输入要查询的页数："))
   formdata={
   'page_limit':30000,
   'page_start':(2-1)*30,
   }
   headers={
   'user-agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/75.0.3770.100 Safari/537.36',
   }
   formdata=urllib.parse.urlencode(formdata)
   url=url+formdata
   request=urllib.request.Request(url=url,headers=headers)
   response=urllib.request.urlopen(request).read().decode()
   print(response)
   film={}
   film['name']=re.findall(r'"title":"(.*?)","url":',response)
   # film['name']=re.sub(r'"title":"([A-Za-z0-9!\%[]\,。])","url":"https:\/\/movie.douban.com\'," ",response)
   print(film['name'])

2. 补充