import urllib.request
import urllib.parse
#401 Unauthorized客户试图未经授权访问受密码保护的页面 所以爬取失败了
url = 'https://www.zhihu.com/api/v3/feed/topstory/recommend?session_token=5ad2f1226d859b5abf6d7d214140e78f&desktop=true&page_number=4&limit=6&action=down&after_id=17 '
page = int(input('请输入你要查找的页数：'))

# page  5    2
# page  11   3
# page  17   4
# page  23   5


form_data={
    'session_token': '5ad2f1226d859b5abf6d7d214140e78f',
    'desktop': 'true',
    'page_number': page+1,
    'limit': '6',
    'action': 'down',
    'after_id': (page*6)-1,
}
headers={
    'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/74.0.3729.131 Safari/537.36',

}

request = urllib.request.Request(url = url,headers = headers)
form_data = urllib.parse.urlencode(form_data).encode()
response = urllib.request.urlopen(request,data=form_data)
print(response.read().decode())
# with open('北京大学微博.html','wb')as fp:
#     fp.write(response.read())