python 爬虫自适应编码解决网页乱码问题

8,445次阅读

import io
#
sys.stdout=io.TextIOWrapper(sys.stdout.buffer,encoding='utf-8')

#方式1
response = requests.get(self.url, headers=self.head)

bm = response.encoding
 #获取网页编码

html = response.text

html = html.encode(bm) # 用网页编码 解码

html = BeautifulSoup(html, 'lxml')

#方式2
response.encoding = response.apparent_encoding
html = BeautifulSoup(response.text,'lxml')

发表于：代码编程

2022-04-03