在我们爬取网页的时候,可能会遇到乱码的问题,解决这种的乱码的问题有一种通用的方法
import requests
from lxml import etree
url = 'http://pic.netbian.com/4kqiche/'
headers = {
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/73.0.3683.86 Safari/537.36'
}
response = requests.get(url=url,headers=headers)
#手动设置响应数据的编码
# response.encoding = 'utf-8'
page_text = response.text
tree = etree.HTML(page_text)
li_list = tree.xpath('//div[@class="slist"]/ul/li')
for li in li_list:
img_src = li.xpath('./a/img/@src')[0]
img_name = li.xpath('./a/b/text()')[0]
#通用性
img_name = img_name.encode('iso-8859-1').decode('gbk')
print(img_src,img_name)