diff options
| -rw-r--r-- | FBGM.py | 30 |
1 files changed, 12 insertions, 18 deletions
@@ -12,7 +12,6 @@ def paragraph_parser(contents): paragraph=[] article=[] x = 0 - output = '' contents=contents.strip() contents+="|E" while x in range (len(paragraph_end)): @@ -26,13 +25,11 @@ def paragraph_parser(contents): if contents[paragraph_index[paragraph_number-1]:].index(x)+paragraph_index[paragraph_number-1]+1 < minimum: minimum = contents[paragraph_index[paragraph_number-1]:].index(x)+paragraph_index[paragraph_number-1] paragraph_index.append(minimum+1) - paragraph.append(contents[paragraph_index[paragraph_number-1]:paragraph_index[paragraph_number]]) + paragraph.append(contents[paragraph_index[paragraph_number-1]:paragraph_index[paragraph_number]]+'</p>') for x in paragraph_end: if contents[paragraph_index[paragraph_number]:].find(x) == -1: paragraph_end.remove(x) - if contents[paragraph_index[paragraph_number-1]+2:paragraph_index[paragraph_number]].find(article_end) != -1: - first_nl =contents[paragraph_index[paragraph_number-1]+2:paragraph_index[paragraph_number]].index(article_end)+paragraph_index[paragraph_number-1]+2 - print(contents[first_nl-1:first_nl]) + first_nl =contents[paragraph_index[paragraph_number-1]+2:paragraph_index[paragraph_number]].index(article_end)+paragraph_index[paragraph_number-1]+2 if contents[first_nl-1:first_nl] not in punctuation: article_index.append(contents[paragraph_index[paragraph_number-1]+2:paragraph_index[paragraph_number]].index(article_end)+paragraph_index[paragraph_number-1]) paragraph_number +=1 @@ -42,19 +39,16 @@ def paragraph_parser(contents): if contents[article_index[x-1]:article_index[x]-2].rfind('\n') != -1: article.append(contents[contents[:article_index[x]].rfind('\n')+1:article_index[x]+2]) elif x==1: - article.append(contents[:article_index[x]+2]) - output+='<article class="bodysection">' - output+="<h2>"+article[x-1]+'</h2>' - while paragraph_index[paragraph_number] < article_index[x]: - if article_index[x] in range(paragraph_index[paragraph_number],paragraph_index[paragraph_number+1]): - paragraph[paragraph_number]=paragraph[paragraph_number][article_index[x]-paragraph_index[paragraph_number]+3:] - output+=paragraph[paragraph_number] - paragraph_number+=1 - output+='</article>' - #contents=contents[:contents[:x-1].rfind('\n')]+'<article class="bodysection"> '+contents[x:] - - print(output) - return output + article.append(contents[contents[:article_index[x]].rfind('\n')+1:article_index[x]+2]) + for x in article_index[1:]: + while x not in range(paragraph_index[paragraph_number],paragraph_index[paragraph_number+1]): + paragraph[paragraph_number]="<p>"+paragraph[paragraph_number] + paragraph_number +=1 + paragraph[paragraph_number]=paragraph[paragraph_number].replace("\n"," ") + paragraph[paragraph_number]=paragraph[paragraph_number].strip() + paragraph[paragraph_number]="<h2>"+article[article_index.index(x)-1]+"</h2>\n<p>"+paragraph[paragraph_number][len(article[article_index.index(x)-1]):] + print("Header "+str(x)+" is in paragraph "+str(paragraph_number)) + return ''.join(paragraph) |