added extra replace section to tidy up output when retaining tables

attardi · Jan 23, 2017 · 3701b77 · 3701b77
1 parent e835e8c
commit 3701b77
Showing 1 changed file with 2 additions and 1 deletion.
diff --git a/WikiExtractor.py b/WikiExtractor.py
@@ -688,7 +688,8 @@ def clean(self, text):
         text = re.sub(r'\n\W+?\n', '\n', text, flags=re.U)  # lines with only punctuations
         text = text.replace(',,', ',').replace(',.', '.')
         if keep_tables:
-            text = re.sub(r'!(?:\s)?style=\"width:(?:\d+)%;\"', r'', text)
+            text = re.sub(r'!(?:\s)?style=\"[a-z]+:(?:\d+)%;\"', r'', text)
+            text = re.sub(r'!(?:\s)?style="[a-z]+:(?:\d+)%;[a-z]+:(?:#)?(?:[0-9a-z]+)?"', r'', text)
             text = text.replace('|-', '')
             text = text.replace('|', '')
         if Extractor.toHTML: