|
| 1 | +from bs4 import BeautifulSoup |
| 2 | + |
| 3 | + |
| 4 | + |
| 5 | + |
| 6 | + |
| 7 | + |
| 8 | + |
| 9 | + |
| 10 | + |
| 11 | + |
| 12 | +def file_replace_rext(filename, toreplace, replacement): |
| 13 | + with open(filename, 'r', encoding='utf-8') as file: |
| 14 | + filedata = file.read() |
| 15 | + # Replace the text in file |
| 16 | + filedata = filedata.replace(toreplace, replacement) |
| 17 | + # Write the file out again |
| 18 | + with open(filename, 'w') as file: |
| 19 | + file.write(filedata) |
| 20 | + |
| 21 | +# Read in the file |
| 22 | +with open('todo.html', 'r', encoding='utf-8') as file: |
| 23 | + filedata = file.read() |
| 24 | +# Replace the “smart quotes” |
| 25 | +filedata = filedata.replace('“', '"').replace('”', '"') |
| 26 | +# Write the file out again |
| 27 | +with open('todo.html', 'w') as file: |
| 28 | + file.write(filedata) |
| 29 | + |
| 30 | +#TODO: verify if removing entire style tag is good or no |
| 31 | + |
| 32 | + |
| 33 | +with open("todo.html", encoding='utf-8') as fp: |
| 34 | + soup = BeautifulSoup(fp, "html.parser") |
| 35 | + |
| 36 | + |
| 37 | +title = soup.title.get_text() |
| 38 | +print(title) |
| 39 | + |
| 40 | +#remove style tag from header |
| 41 | +soup.find('style').extract() |
| 42 | + |
| 43 | +for tag in soup(): |
| 44 | + for attribute in ['class', 'id', 'name', 'style']: |
| 45 | + del tag[attribute] |
| 46 | + |
| 47 | +#do string processing after here |
| 48 | +soup_string = str(soup) |
| 49 | + |
| 50 | +#removes all <p><br/></p> tags |
| 51 | +soup_string = soup_string.replace('<p><br/></p>', '<br/>') |
| 52 | + |
| 53 | +#encapsulates <p> tags in <body> with a <div> |
| 54 | +soup_string = soup_string.replace('<body>', '<body>\n<div>') |
| 55 | +soup_string = soup_string.replace('</body>', '</div>\n</body>') |
| 56 | + |
| 57 | +#exports file |
| 58 | +with open('done.html', 'w') as file: |
| 59 | + file.write(str(soup_string)) |
0 commit comments