diff options
| author | Daniel Behmer <behmer_d@yahoo.com> | 2022-09-01 11:46:48 -0700 |
|---|---|---|
| committer | Daniel Behmer <behmer_d@yahoo.com> | 2022-09-01 11:46:48 -0700 |
| commit | 491b2ea40ea21316c9ef3da72d865f369f6beafb (patch) | |
| tree | 747bd7a442c92ed05563e4a5ec2a336325ebaf72 | |
| parent | 0fcdbb3c378cc5f47db1a51dc781b9005f69daf0 (diff) | |
Added paragraph parser --in progress
| -rw-r--r-- | FBGM.py | 40 |
1 files changed, 37 insertions, 3 deletions
@@ -1,23 +1,57 @@ from ftplib import parse150 import os, sys +def paragraph_parser(contents): + paragraph_end = ['.\n', '?\n', '!\n', '"\n'] + paragraph_index = [0] + paragraph_number = 1 + paragraph = [] + x = 0 + while len(paragraph_end) > 1: + while x in range (len(paragraph_end)): + if contents[paragraph_index[paragraph_number-1]:].find(paragraph_end[x]) == -1: + paragraph_end.pop(x) + else: + x += 1 + minimum = contents[paragraph_index[paragraph_number-1]:].index(paragraph_end[0])+paragraph_index[paragraph_number-1] + x = 1 + for x in range (len(paragraph_end)): + if contents[paragraph_index[paragraph_number-1]:].index(paragraph_end[x]) < minimum: + minimum = contents[paragraph_index[paragraph_number-1]:].index(paragraph_end[x])+paragraph_index[paragraph_number-1] + paragraph_index.append(minimum) + print(minimum) + + + + #paragraph.append(contents[paragraph_index[paragraph_number-1]: paragraph_index[paragraph_number]+1]) + #print(paragraph_index[paragraph_number]) + paragraph_number +=1 + + + + def txthandler(path, htmlfile): + filename = path[path.rfind('/')+1: path.rfind('.')] f = open(path, "r") contents = f.read() + title = filename + main_header = contents[0:contents.find('\n')] + paragraph_parser(contents) + htmlfile.write('<!DOCTYPE html>' '<html lang ="en">' '<head>' - '<title>' +filename+ '</title>' + '<title>' +title+ '</title>' '<link rel="stylesheet" type="text/css" href="stylesheet.css">' '<link rel="icon" type="image/x-icon" href="images/favicon.ico">' '<meta charset="utf-8"/>' '</head>' '<body>' - '<h1>' +contents[0:contents.find('\n')]+ '</h1>' + '<h1>' +main_header+ '</h1>' '<article class="introduction">' '<h2>  Introduction  </h2>' - '<p>'+contents[contents.find('\n'):contents[contents.find('\n'):].find('.\n')+contents.find('\n')+1]+'</p>' + '<p>''</p>' '</article>' '</body>' '</html>') |