需求背景
最近刚搭了个markdown静态博客,想把博客的图片放到云存储中。
经过调研觉得七牛可以满足我个人的需求,就选它了。
博客要引用图片就要先将图片上传到云上。
虽然七牛网站后台可以上传文件,但每次上传都需要先登录,然后选择图片,设置连接地址,才能上传。
这个过程有些繁琐,所以我便想用七牛云提供的SDK写个一同步工具,方便增量同步文件。
有了这个想法,就马上行动。花了大概一个上午的时间,总算把这个工具给写出来,
并放到GitOSC和github上。
实现
(博客园的markdown代码区显示不友好,可以到我的个人博客中浏览)
#!/usr/bin/env python
#-*- coding:utf-8 -*-
#
# AUTHOR = "heqingpan"
# AUTHOR_EMAIL = "heqingpan@126.com"
# URL = "http://git.oschina.net/hqp/qiniu_sync"
import qiniu
from qiniu import Auth
from qiniu import BucketManager
import os
import re
access_key = ''
secret_key = ''
bucket_name = ''
bucket_domain = ''
q = Auth(access_key, secret_key)
bucket = BucketManager(q)
basedir=os.path.realpath(os.path.dirname(__file__))
filename=__file__
ignore_paths=[filename,"{0}c".format(filename)]
ignore_names=[".DS_Store",".git",".gitignore"]
charset="utf8"
diff_time=2*60
def list_all(bucket_name, bucket=None, prefix="", limit=100):
rlist=[]
if bucket is None:
bucket = BucketManager(q)
marker = None
eof = False
while eof is False:
ret, eof, info = bucket.list(bucket_name, prefix=prefix, marker=marker, limit=limit)
marker = ret.get('marker', None)
for item in ret['items']:
rlist.append(item["key"])
if eof is not True:
# 错误处理
#print "error"
pass
return rlist
def get_files(basedir="",fix="",rlist=None,ignore_paths=[],ignore_names=[]):
if rlist is None:
rlist=[]
for subfile in os.listdir(basedir):
temp_path=os.path.join(basedir,subfile)
tp=os.path.join(fix,subfile)
if tp in ignore_names:
continue
if tp in ignore_paths:
continue
if os.path.isfile(temp_path):
rlist.append(tp)
elif os.path.isdir(temp_path):
get_files(temp_path,tp,rlist,ignore_paths,ignore_names)
return rlist
def get_valid_key_files(subdir=""):
basedir=subdir or basedir
files = get_files(basedir=basedir,ignore_paths=ignore_paths,ignore_names=ignore_names)
return map(lambda f:(f.replace("\\","/"),f),files)
def sync():
qn_keys=list_all(bucket_name,bucket)
qn_set=set(qn_keys)
l_key_files=get_valid_key_files(basedir)
k2f={}
update_keys=[]
u_count=500
u_index=0
for k,f in l_key_files:
k2f[k]=f
str_k=k
if isinstance(k,str):
k=k.decode(charset)
if k in qn_set:
update_keys.append(str_k)
u_index+=1
if u_index > u_count:
u_index-=u_count
update_file(k2f,update_keys)
update_keys=[]
else:
# upload
upload_file(k,os.path.join(basedir,f))
if update_keys:
update_file(k2f,update_keys)
print "sync end"
def update_file(k2f,ulist):
ops=qiniu.build_batch_stat(bucket_name,ulist)
rets,infos = bucket.batch(ops)
for i in xrange(len(ulist)):
k=ulist[i]
f=k2f.get(k)
ret=rets[i]["data"]
size=ret.get("fsize",None)
put_time = int(ret.get("putTime")/10000000)
local_size=os.path.getsize(f)
local_time=int(os.path.getatime(f))
if local_size==size:
continue
if put_time >= local_time - diff_time:
# is new
continue
# update
upload_file(k,os.path.join(basedir,f))
def upload_file(key,localfile):
print "upload_file:"
print key
token = q.upload_token(bucket_name, key)
mime_type = get_mime_type(localfile)
params = {'x:a': 'a'}
progress_handler = lambda progress, total: progress
ret, info = qiniu.put_file(token, key, localfile, params, mime_type, progress_handler=progress_handler)
def get_mime_type(path):
mime_type = "text/plain"
return mime_type
def main():
sync()
if __name__=="__main__":
main()
这个同步脚本支持批量比较文件,差异增量更新、批量更新。
使用方式
安装七牛Python SDK
pip install qiniu
- 填写脚本文件(qiniusync.py)的配置信息
access_key = ''
secret_key = ''
bucket_name = ''
注册后可以拿到对应的信息
将脚本文件(qiniusync.py)拷贝到待同步根目录
- 运行脚本
python qiniusync.py
后记
写完提交之后才发现,七牛已经提供相应的工具,我这个算是重复造轮子吧。
既然已经写,就发出来,当做熟悉一下七牛的SDK也不错,说不定以后还能用的上。
博客园的markdown代码区显示不友好,可以到我的个人博客中浏览