import urllib.request
from bs4 import BeautifulSoup
import sys
request = urllib.request.Request('https://www.xxx.com"')
response = urllib.request.urlopen(request)
data = response.read()
soup = BeautifulSoup(data, 'html.parser')
soup = soup.prettify()
**non_bmp_map = dict.fromkeys(range(0x10000, sys.maxunicode + 1), 0xfffd)**
**soup = soup.translate(non_bmp_map)**
# 上面两句如果注释掉就会报标题的错误
print(soup)
UnicodeEncodeError: ‘UCS-2‘ codec can‘t encode characters in position... 2020.12.30
最新推荐文章于 2021-03-21 23:07:30 发布