status_last = Person.get_person_lookup_status( person_last )
print( "status from both in last: " + status_last )
else:
# Name parsed as two words, so go with parsed name?
pass
#-- END check to see if both first and last name. --#
#-- END check to see if two-part name. --#
# look for people with same full-string name.
# get full name from parsed.
full_name_test = StringHelper.object_to_unicode_string( parsed )
print( "FULL NAME - looking for \"" + full_name_test + "\"" )
full_name_qs = Person.objects.filter( full_name_string__iexact = full_name_test )
full_name_count = full_name_qs.count()
if ( full_name_count > 0 ):
for full_name_match in full_name_qs:
print( "- FULL NAME - full name match: " + str( full_name_match ) )
#-- END loop over full name matches --#
else:
print( "- FULL NAME - no full name match for \"" + full_name_test + "\"" )
# see if name is br.
if ( current_name == "br" ):
# yes - paragraph break! output a message, and the string contents of the tag (just in case).
print( "=======> paragraph break! - End of paragraph " + str( paragraph_counter ) + ". HTML element Contents: \"" + str( current_content ) + "\"" )
# add previous paragraph to paragraph list.
paragraph_text_list = []
for paragraph_element in current_element_list:
# convert current element to just text. Is it NavigableString?
if ( isinstance( paragraph_element, NavigableString) ):
# it is text - convert it to string.
current_paragraph_text = StringHelper.object_to_unicode_string( paragraph_element )
else:
# not text - just grab all the text out of it.
#current_paragraph_text = ' '.join( paragraph_element.findAll( text = True ) )
current_paragraph_text = HTMLHelper.remove_html( str( paragraph_element ) )
#-- END check to see if current element is text. --#
# clean up - convert HTML entities
current_paragraph_text = bs_helper.convert_html_entities( current_paragraph_text )
# strip out extra white space
current_paragraph_text = StringHelper.replace_white_space( current_paragraph_text )
