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
|
#!/usr/bin/python
from bs4 import BeautifulSoup
import sys
import re
from sets import Set
FILE_MAPPING = {
r"^\.\./blockly/blocks/.+\.js" : "js/blocks_compressed.js",
r"^\.\./blockly/generators/([a-z]+)(?:/.+)?\.js" : r"js/\1_compressed.js",
r"^\.\./blockly/overrides/.+\.js" : "js/overrides_compressed.js",
r"^\.\./blockly/blockly_uncompressed\.js" : "js/blockly_compressed.js",
r"^\.\./blockly/msg/js/([a-z]{2}).js" : r"js/i18n/\1.js",
r"^\.\./blockly/msg/messages.js" : r"js/i18n/en.js"
}
def replace_node_path(dom):
found = Set()
lst = dom.find_all("script", src=re.compile(r"^\.\./blockly"))
for node in lst:
for pattern, replacement in FILE_MAPPING.iteritems():
pattern = re.compile(pattern)
node_path = node.get("src")
found.add(node_path)
if re.match(pattern, node_path):
print(node.get(node_path), replacement)
res = re.sub(pattern, replacement, node_path)
if res in found:
node.decompose()
else:
node["src"] = res
found.add(res)
break
def main():
try:
file = sys.argv[1]
with open(file, "r") as handle:
dom = BeautifulSoup(handle, "lxml")
replace_node_path(dom)
html = ''.join([line.strip() for line in unicode(dom).split('\n')])
with open(file, "w") as handle:
handle.write(html.encode('UTF-8'))
exit(0)
except Exception as e:
print(e)
import traceback
traceback.print_exc()
exit(1)
if __name__ == "__main__":
main()
|
