review code

trafilatura/core.py

@@ -346,8 +346,7 @@ def handle_paragraphs(element, potential_tags, options):
         return processed_element
     if processed_element.text:
         return processed_element
-    if LOGGER.isEnabledFor(logging.DEBUG):
-        LOGGER.debug('discarding p-child: %s', tostring(processed_element))
+    LOGGER.debug('discarding p-child: %s', tostring(processed_element))
     return None
 
 

trafilatura/utils.py

@@ -313,9 +313,6 @@ def sanitize_tree(tree):
 @lru_cache(maxsize=1024)
 def trim(string):
     '''Remove unnecessary spaces within a text string'''
-    if string is None:
-        return None
-
     try:
         # remove newlines that are not related to punctuation or markup + proper trimming
         # return LINES_TRIMMING.sub(r' ', string).strip(' \t\n\r\v')

trafilatura/xml.py

@@ -280,8 +280,7 @@ def process_element(element, returnlist, include_formatting):
         returnlist.append(textelement)
 
     for child in element:
-        if child is not None:
-            process_element(child, returnlist, include_formatting)
+        process_element(child, returnlist, include_formatting)
 
     if element.text is None and element.tail is None:
         if element.tag == 'graphic':
@@ -309,6 +308,7 @@ def process_element(element, returnlist, include_formatting):
     if element.tail is not None:
         returnlist.append(element.tail)
 
+
 def xmltotxt(xmloutput, include_formatting):
     '''Convert to plain text format and optionally preserve formatting as markdown.'''
     returnlist = []
@@ -317,6 +317,7 @@ def xmltotxt(xmloutput, include_formatting):
 
     return unescape(sanitize(''.join(returnlist)))
 
+
 def xmltocsv(document, include_formatting, *, delim="\t", null="null"):
     "Convert the internal XML document representation to a CSV string."
     # preprocessing