快速理解简单的短链接生成原理
原理
计算长链接整体为一个十进制数,将其映射成一个62进制数。这个62进制由26个小写字母,26个大写字母和10个数字表示。
假设有long-url这么一个长网址,其10进制数 108+111+110+103+45+117+114+108=816, 其62进制表示就是kna。
为了解决相同值冲突的问题,可以在最后加入自增ID或者先通过摘要函数取得长网址的hash再映射来降低冲突概率。
代码实现
DB部分是来实现从短网址到原始网址的步骤,从而实现重定向。
import string
import pickle
import random
from functools import reduce
from operator import add
class DB:
def __init__(self):
self._long2short_db = {}
self._short2long_db = {}
self.load()
def add_data(self, s_url, l_url):
self._long2short_db[s_url] = l_url
self._short2long_db[l_url] = s_url
def remove_data(self, s_url):
self._short2long_db.pop(self._long2short_db.pop(s_url, None), None)
def get_origin_long_url(self, s_url):
return self._long2short_db.get(s_url)
def get_existed_short_url(self, l_url):
return self._short2long_db.get(l_url)
def save(self):
with open("short2long.db", "wb") as f:
pickle.dump(self._short2long_db, f)
with open("long2short.db", "wb") as f:
pickle.dump(self._long2short_db, f)
def load(self):
try:
with open("short2long.db", "rb") as f:
self._short2long_db = pickle.load(f)
with open("long2short.db", "rb") as f:
self._long2short_db = pickle.load(f)
except (pickle.PickleError, FileNotFoundError):
self._long2short_db = {}
self._short2long_db = {}
def long2short(l_url):
if s := db.get_existed_short_url(l_url):
return s
convert_space = tuple(map(str, string.ascii_letters + string.digits))
arr = []
count = reduce(add, map(ord, l_url))
while count >= 0:
arr.append(convert_space[count % 62])
count //= 62
# Random instead of a auto increment ID
arr.append(convert_space[random.randint(100000, 999999) % 62])
s_url = "".join(arr)
db.add_data(s_url, l_url)
return s_url
def short2long(s_url):
return db.get_origin_long_url(s_url)
if __name__ == "__main__":
db = DB()
short_url = long2short("http://long-domain/long-level1-path/long-level2-path/?long-query-string=long-query-value")
print(short_url)
long_url = short2long(short_url)
print(long_url)
db.save()