bs_div_docBody = bs.find( "div", NewsBankHelper.HTML_CLASS_DOC_BODY )
# Got a <div id="docBody"> tag?
if ( bs_div_docBody != None ):
# get nested <div> that contains article content.
bs_div_mainText = bs_div_docBody.find( "div", NewsBankHelper.HTML_CLASS_MAIN_TEXT )
# print the original HTML
if ( DEBUG_FLAG == True ):
print( "Original HTML:" )
print( str( bs_div_mainText ) )
#-- END DEBUG --#
# clean it up with NewsBankHelper
my_newsbank_helper = NewsBankHelper()
cleaned_article_body = my_newsbank_helper.clean_article_body( bs_div_mainText )
# print the original HTML
if ( DEBUG_FLAG == True ):
# output
print( "\n\n\nCleaned article body:" )
print( cleaned_article_body )
# retrieve and print the original
original_text = article_text.get_content()
print( "\n\n\nOriginal content:" )
print( original_text )
# same?
if ( cleaned_article_body == original_text ):
# load raw content into a BeautifulSoup instance bs = BeautifulSoup( test_raw.content ) # retrieve main content <div> for a NewsBank HTML article. bs_div_docBody = bs.find( "div", NewsBankHelper.HTML_CLASS_DOC_BODY ) # get nested <div> that contains article content. bs_temp_tag = bs_div_docBody.find( "div", NewsBankHelper.HTML_CLASS_MAIN_TEXT ) # print the original HTML print( "Original HTML:" ) print( str( bs_temp_tag ) ) # clean it up with NewsBankHelper my_newsbank_helper = NewsBankHelper() cleaned_article_body = my_newsbank_helper.clean_article_body( bs_temp_tag ) # output print( "\n\n\nCleaned article body:" ) print( cleaned_article_body ) # retrieve Article_Text for this article. test_article_text = Article_Text.objects.get( id = 2 ) # retrieve and print the original original_text = test_article_text.get_content() print( "\n\n\nOriginal content:" ) print( original_text ) # set text
