ALPHABET = "0123456789abcdefghijklmnopqrstuvwxyzABCDEFGHIJKLMNOPQRSTUVWXYZ"

def rsplit(s, count):
    f = lambda x: x > 0 and x or 0
    return [s[f(i - count):i] for i in range(len(s), 0, -count)]

def id2mid(id):
    result = ''
    for i in rsplit(id, 7):
        str62 = base62_encode(int(i))
        result = str62.zfill(4) + result
    return result.lstrip('0')

def mid2id(mid):
    result = ''
    for i in rsplit(mid, 4):
        str10 = str(base62_decode(i)).zfill(7)
        result = str10 + result
    return result.lstrip('0')

def base62_encode(num, alphabet=ALPHABET):
    """Encode a number in Base X
    `num`: The number to encode
    `alphabet`: The alphabet to use for encoding
    """
    if (num == 0):
        return alphabet[0]
    arr = []
    base = len(alphabet)
    while num:
        rem = num % base
        num = num // base
        arr.append(alphabet[rem])
    arr.reverse()
    return ''.join(arr)

def base62_decode(string, alphabet=ALPHABET):
    """Decode a Base X encoded string into the number
    Arguments:
    - `string`: The encoded string
    - `alphabet`: The alphabet to use for encoding
    """
    base = len(alphabet)
    strlen = len(string)
    num = 0

    idx = 0
    for char in string:
        power = (strlen - (idx + 1))
        num += alphabet.index(char) * (base ** power)
        idx += 1
    return num

if __name__ == '__main__':
    print mid2id('CeaOU15IT')
    print id2mid('3833781880260331')

# -*- coding: utf-8 -*-
import requests
from bs4 import BeautifulSoup
import re
import opencc
import base62

rawurl = "http://weibo.com/2803301701/CeaOU15IT"
cc = opencc.OpenCC("t2s")

p = re.compile(r"weibo\.com/(\d+)/(\w+)")
m = re.findall(p,rawurl)
if m:
    uid = m[0][0]
    mid = m[0][1]
    id = base62.mid2id(mid)
url = "http://tw.weibo.com/{0}/{1}".format(uid,id)
print u"微博台湾站链接:{0}".format(url)

user_agent = {'User-agent': 'Mozilla/5.0 (compatible; Googlebot/2.1; +http://www.google.com/bot.html)'}
r = requests.get(url,headers=user_agent)
soup = BeautifulSoup(r.text)
name = soup.find("div","name")
t_name = name.h1.a.text
s_name = cc.convert(name.h1.a.text)
link = name.h1.a["href"]
weibotext = soup.find("p",id="original_text")
t_weibotext = weibotext.text.strip()
s_weibotext = cc.convert(weibotext.text.strip())

print u"繁体中文版-->\n用户:{0}\t用户主页:{1}\n微博内容:{2}".format(t_name,link,t_weibotext)
print u"简体中文版-->\n用户:{0}\t用户主页:{1}\n微博内容:{2}".format(s_name,link,s_weibotext)

# 输出
# 微博台湾站链接:http://tw.weibo.com/2803301701/3833781880260331
# 繁体中文版-->
# 用户:人民日報    用户主页:http://tw.weibo.com/rmrb
# 微博内容:【「最有情懷辭職信」當事人：辭職非衝動 會對未來負責】「世界那麼大，我想去看看。」10字辭職信當事人、河南省實驗中學女教師顧少強19日表示，辭職並非衝動之舉，而是經過理性考慮。「我會對未來的人生負責。」採訪中，顧少強不時強調「每個人都有選擇自己生活方式的權利」。http://t.cn/RAOeU6q
# 简体中文版-->
# 用户:人民日报    用户主页:http://tw.weibo.com/rmrb
# 微博内容:【「最有情怀辞职信」当事人：辞职非冲动 会对未来负责】「世界那么大，我想去看看。」10字辞职信当事人、河南省实验中学女教师顾少强19日表示，辞职并非冲动之举，而是经过理性考虑。「我会对未来的人生负责。」采访中，顾少强不时强调「每个人都有选择自己生活方式的权利」。http://t.cn/RAOeU6q