常用正则表达式

URL

获取URL参数中的数字

import re
url = 'https://www.amazon.com/sports-outdoors/b/ref=dp_bc_aui_C_1?ie=UTF8&node=3375251'
t = re.findall('node=(\d+)', url)[0]

获取价格字符串的数值

import re
# price='$1,000.3'
# price='2.000,3€'
price='¥50.3'
a = str.replace(price, ',', '.')
price = re.findall('([\d,.]+)[,.](\d+)$', a)
if len(price):
    price = price[0]
    price = '.'.join(price)
    price = float(price)

获取亚马逊评分

# star = '0 out of 5'
star = '1.4 out of 5'
# star = '5 out of 5'
star = str.replace(star, ',', '.')
t = re.findall('(\d+[,.]*\d*)', star)
star = float(min(t))