Created
November 13, 2016 23:23
-
-
Save altendky/92f4323bfd94e67cfbdc710a6393b318 to your computer and use it in GitHub Desktop.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
diff --git a/wiki2html.py b/wiki2html.py | |
index 542ed9d..f31580b 100644 | |
--- a/wiki2html.py | |
+++ b/wiki2html.py | |
@@ -17,13 +17,16 @@ import traceback | |
tree = ET.parse('your.xml', encoding='utf8') | |
root = tree.getroot() | |
-items = (['Category:', 'User talk:', 'Template:', 'User:', 'Shadowrun talk:', 'File:', 'Talk:', | |
- 'Shadowrun Wiki:', 'User blog:', 'User blog comment:']) | |
+items = ['Category', 'User talk', 'Template', 'User', 'Shadowrun talk', 'File', 'Talk', | |
+ 'Shadowrun Wiki', 'User blog', 'User blog comment'] | |
for elem in root.iter(): | |
- if ('export-0.6/}title' in elem.tag and elem.text is not None and items not in elem.text.split(':')[0]): | |
+ if elem.text is None: | |
+ continue | |
+ | |
+ if ('export-0.6/}title' in elem.tag and elem.text.split(':')[0] not in items): | |
filestrip = re.sub(r'[\;*?!<>|/:"]', '', elem.text) | |
- fname = (os.path.join(filestrip.strip().replace(' ', '_')+'.html')) | |
+ fname = os.path.join(filestrip.strip().replace(' ', '_')+'.html') | |
title = re.sub('[/:"]', '', elem.text) | |
try: | |
hfile = open(fname, 'ab') | |
@@ -32,7 +35,7 @@ for elem in root.iter(): | |
except Exception as e: | |
print(str(e)) | |
- if 'export-0.6/}text' in elem.tag and elem.text is not None: | |
+ if 'export-0.6/}text' in elem.tag: | |
hfile.write('<link rel="stylesheet" href="style.css" type="text/css" media="screen" />') | |
hfile.write('<pre>') | |
hfile.write(elem.text.replace('[', '<b>').replace(']', '</b>').replace('\'', '')) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment