import re
#1 todo 读文件替换 m 或者直接读网页
m = '<a target="_blank" title="3.29-3.31iPhone11领券立减200元,特惠机型推荐:XSMax低至5799元,XR低至4199元超值推荐!" href="//item.jd.com/100008348542.html" onclick="searchlog(1,100008348542,1,2,><a target="_blank" title="3.29-3.31iPhone11领券立减40元,特惠机型推荐:XSMax低至5799元,XR低至4199元超值推荐!" href="//item.jd.com/100008348542.html" onclick="searchlog(1,100008348542,1,2,>'
i = re.findall(r"\"_blank\" (.*?) onclick=",m)
#2 TODO 写个循环i
m1 = re.findall(r'title="(.*?)" href=',i[0])
print (m1)
m2 = re.findall(r'jd.com\/(.*?).html',i[0])
m3 = "https://club.jd.com/comment/productPageComments.action?callback=fetchJSON_comment98&productId=" + m2[0] + "&score=3&sortType=5",
print (m3)
# 3 TODO 写个字典 拼m1和m3
python正则获取字符串中某段不确定子串
最新推荐文章于 2024-06-05 21:26:51 发布