forked from BSVino/docs.gl
-
Notifications
You must be signed in to change notification settings - Fork 0
/
Copy pathstrip.py
99 lines (74 loc) · 2.05 KB
/
strip.py
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
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
#!/usr/bin/python
# This utility was used to strip the header and footer from the 4.3 docs xhtml files.
import os
import re
def strip_gl2():
f = []
for (dirpath, dirnames, filenames) in os.walk("gl2/"):
f.extend(filenames)
for filename in f:
print "Processing " + filename
fp = open ("gl2/" + filename)
content = fp.readlines()
fp.close()
# First two lines are junk.
while not "xml-stylesheet" in content[0]:
content.pop(0)
m = re.search("body>(.*)", content[0])
firstline = m.group(1)
content.pop(0)
content.insert(0, firstline + "\n")
# The last line is junk
content.pop()
content.append(" </p></div></div>")
fp = open("gl2/" + filename, "w")
for line in content:
fp.write("%s" % line)
fp.close()
def strip_gl3():
f = []
for (dirpath, dirnames, filenames) in os.walk("gl3/"):
f.extend(filenames)
for filename in f:
print "Processing " + filename
fp = open ("gl3/" + filename)
content = fp.readlines()
fp.close()
# First two lines are junk.
while not "xml-stylesheet" in content[0]:
content.pop(0)
m = re.search("body>(.*)", content[0])
firstline = m.group(1)
content.pop(0)
content.insert(0, firstline + "\n")
# The last line is junk
content.pop()
content.append(" </p></div></div>")
fp = open("gl3/" + filename, "w")
for line in content:
fp.write("%s" % line)
fp.close()
def strip_gl4():
f = []
for (dirpath, dirnames, filenames) in os.walk("gl4/"):
f.extend(filenames)
for filename in f:
print "Processing " + filename
fp = open ("gl4/" + filename)
content = fp.readlines()
fp.close()
while not "header" in content[0]:
content.pop(0)
# One more time to pop the header
content.pop(0)
# The last three lines are <footer /> </body> </html>
content.pop()
content.pop()
content.pop()
fp = open("gl4/" + filename, "w")
for line in content:
fp.write("%s" % line)
fp.close()
strip_gl2()
strip_gl3()
strip_gl4()