process_article.py

def process_article(title, text, timestamp, template = 'Infobox book'):
    """Process a wikipedia article looking for template"""
    
    # Create a parsing object
    wikicode = mwparserfromhell.parse(text)
    
    # Search through templates for the template
    matches = wikicode.filter_templates(matches = template)
    
    if len(matches) >= 1:
        # Extract information from infobox
        properties = {param.name.strip_code().strip(): param.value.strip_code().strip() 
                      for param in matches[0].params
                      if param.value.strip_code().strip()}
        
        # Extract internal wikilinks
        wikilinks = [x.title.strip_code().strip() for x in wikicode.filter_wikilinks()]
        # Extract external links
        exlinks = [x.url.strip_code().strip() for x in wikicode.filter_external_links()]
        return (title, properties, wikilinks, exlinks, timestamp)