python解析css文件_在Python中解析CSS

这是我降落的地方。使用了恶报的策略，用一个劈开绳子。在from bs4 import BeautifulSoup

import re

class RichText(BeautifulSoup):

"""

subclass BeautifulSoup

add behavior for generating selectors and declaration_blocks from

"""

def __init__(self, html_page):

super().__init__(html_page)

@property

def rules_as_str(self):

return str(self.style.string)

def rules(self):

split_rules = re.split('(\.c[0-9]*)', self.rules_as_str)

# side effect of split, first element is null

assert(split_rules[0] == '')

# enforce that it MUST be null, then pass over it

for i in range(1, len(split_rules), 2):

yield (split_rules[i].strip(), split_rules[i+1].strip())

if __name__ == '__main__':

with open('rich-text.html', 'r') as f:

html_file = f.read()

rich_text = RichText(html_file)

for selector, declaration_block in rich_text.rules():

print(selector)

print(declaration_block)

>>> with open("test.py") as f:

... code = compile(f.read(), "test.py", 'exec')

... exec(code)

...

.c0

{ padding: 1px 0px 0px; font-size: 11px }

.c1

{ margin: 0px; font-size: 11px }

.c2

{ font-size: 11px }

.c3

{ font-size: 11px; font-style: italic; font-weight: bold }

>>>