check also spans in "id" attr check

Author: tangledhelix

pphtml.py

@@ -484,10 +484,10 @@ def findPageRanges(self):
         pages_arabic = []
         pages_roman = []
 
-        # Look for <a> or <div> with 'id' attribute; \3 is the match
-        pat1 = re.compile(r"""<(a|div)\s+[^>]*\bid=["'](page|pg)_?([\divxlcdm]+)["']""",
+        # Look for <a>, <div>, <span> with 'id' attribute; \3 is the match
+        pat1 = re.compile(r"""<(a|div|span)\s+[^>]*\bid=["'](page|pg)_?([\divxlcdm]+)["']""",
                           re.IGNORECASE)
-        # Look for span class=pagenum; \1 is the match
+        # Alternately: look for span class=pagenum; \1 is the match
         pat2 = re.compile(r"""<span\s+[^>]*\bclass=["']pagenum['"].*>([^<]+)</span""",
                           re.IGNORECASE)