File size: 1,272 Bytes
4309ee9
4cf70e0
d465175
 
097e81a
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
4cf70e0
097e81a
d465175
0b4b0ed
4cf70e0
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
from bs4 import BeautifulSoup, Comment

import logger

def cleanup(soup):

    # Remove all HTML comments
    for comment in soup.find_all(string=lambda text: isinstance(text, Comment)):
        comment.extract()

    # Remove unnecessary <meta> tags from the <head>
    for meta in soup.select('head meta'):
        if not meta.has_attr('charset') and not meta.has_attr('http-equiv'):
            meta.decompose()

    # Remove all inline CSS styles
    for tag in soup.find_all(True):
        if tag.has_attr('style'):
            del tag['style']

    # Remove any empty <b>, <i>, <u>, <sup> elements
    for tag in soup.select('b:empty, i:empty, u:empty, sup:empty'):
        tag.decompose()

    # Remove unnecessary attributes like valign and align from tags
    for tag in soup.find_all(True):
        for attr in ['valign', 'align']:
            if tag.has_attr(attr):
                del tag[attr]

    # Remove all <span class="page"> elements that just contain page numbers
    for span in soup.select('span.page'):
        if span.get_text(strip=True).isdigit():
            span.decompose()

    return soup

def parse(filepath):
    soup = cleanup(BeautifulSoup(open(filepath).read(), 'html.parser'))
    logger.info(f"Parsed {filepath}")
    return soup