Python 抓取网页数据乱码时, 设置编码
headers = {'referer': referer, 'user-agent': user_agent}
r = requests.get(url, headers=headers, proxies=proxies)
# print(r.encoding) # gb2312
r.encoding = 'GBK'
text = r.text
html = BeautifulSoup(text, "lxml")