requests re 简单使用
程序员文章站
2022-07-10 08:22:31
...
import requests
import re
url = 'https://www.dianping.com/shop/12600401'
header = {
'User-Agent':'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'
}
html = requests.get(url=url,headers=header).text
import pdb;pdb.set_trace()
shopName = re.findall(r'(?<=shopName: ").+(?=", address)',html) # 以列表类型返回全部能匹配的子串
print(shopName)