1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
| import re
import requests
import os
def find_url(path):
'''Find old img url'''
old_url = []
for root, _, files in os.walk(path):
for file in files:
if file == ".DS_Store":
continue
with open(os.path.join(root, file), "r") as f:
content = f.read()
res = re.findall("https:(.+?)jpg", content)
if res:
for each_img in res:
old_url.append("https:" + each_img + "jpg")
return old_url
def download_img(urls):
'''Download img files from old img url'''
for url in urls:
print("Downloading: {}".format(url))
img = requests.get(url)
with open("/Users/suixin/temp/imgs/" + url[-36:], "wb") as f:
f.write(img.content)
def replace_urls(path, urls_old):
'''Replace url by new url and write to new files'''
urls_new = []
for each_url_old in urls_old:
urls_new.append("https://raw.githubusercontent.com/ShaneTian/blogimages/master/images/" + each_url_old[-36:])
for root, _, files in os.walk(path):
for file in files:
if file == ".DS_Store":
continue
with open(os.path.join(root, file), "r") as f:
content = f.read()
for idx, each_url_old in enumerate(urls_old):
res = re.search(pattern=each_url_old, string=content)
if res:
print("Replace {} to {}\n".format(each_url_old, "https://raw.githubusercontent.com/ShaneTian/blogimages/master/images/" + each_url_old[-36:]))
content = content.replace(each_url_old, urls_new[idx])
with open("/Users/suixin/temp/posts_new/" + file, "w") as f_write:
f_write.write(content)
if __name__ == '__main__':
urls_old = find_url("/Users/suixin/blog/source/_posts")
replace_urls("/Users/suixin/temp/_posts", urls_old)
|