一个简单的贴吧爬取

import urllib.request
import urllib.parse
import os
#ba_name = "python"
ba_name=input('吧名')
start_page=int(input('爬取起始页'))
end_page=int(input('请输入结束页码'))
#start_page= 1
#end_page= 2
if not os.path.isdir(ba_name):
	os.mkdir(ba_name)
url = "https://movie.douban.com/j/chart/top_list?type=13&interval_id=100%3A90&action=";
for page in range(start_page,end_page+1):
	data = {
		'kw':ba_name,
		'pn':(page-1)*50
	}
	data = urllib.parse.urlencode(data)
	url_t = url+data;
	headers = {
		'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/76.0.3809.132 Safari/537.36'
	}
	request = urllib.request.Request(url=url_t,headers=headers);
	print("%s页开始下载....." % page)
	response = urllib.request.urlopen(request);
	filename = ba_name+'_'+str(page)+'.html';
	filepath = ba_name+'/'+filename;
	with open(filepath,'wb') as fp:
		fp.write(response.read());
		print("%s页结束下载....." % page)
	print(response.read())