为什么加上add_header就不行了

幽梦三影

from bs4 import BeautifulSoup
import urllib.request
import re

def get_html(url):
    rep = urllib.request.Request(url)
    #rep.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; …) Gecko/20100101 Firefox/61.0')
    html = urllib.request.urlopen(rep).read().decode('utf-8')
    return html

url = 'https://baike.baidu.com/item/%E7%BD%91%E7%BB%9C%E7%88%AC%E8%99%AB'
html = get_html(url)
s = BeautifulSoup(html,'lxml')
link = s.find_all('a',href = re.compile('/item'))
count = 0
for i in link[:3]:
    l = get_html('https://baike.baidu.com' + i['href'])
    with open('%d.txt'%count,'w',encoding = 'utf-8') as f:
        f.write(l)
    count += 1

ba21

我敢保证，rep.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; …) Gecko/20100101 Firefox/61.0')这里面有   中文字符   自己慢慢找，琢磨吧