42 lines
916 B
Python
42 lines
916 B
Python
|
# -*- coding: utf-8 -*-
|
||
|
|
|
||
|
|
filename="test.rst"
|
||
|
|
|
||
|
|
# https://docutils.sourceforge.io/docs/api/publisher.html
|
||
|
|
|
||
|
|
import docutils.core
|
||
|
|
import dateutil.parser
|
||
|
|
import bs4
|
||
|
|
|
||
|
|
html = docutils.core.publish_parts(open(filename, mode="r").read(),
|
||
|
|
source_path=filename,
|
||
|
|
writer_name='html')
|
||
|
|
|
||
|
|
def find_date(d):
|
||
|
|
comments = d.find_all(string=lambda text: isinstance(text, bs4.Comment))
|
||
|
|
for c in comments:
|
||
|
|
for k in c.extract().split(" "):
|
||
|
|
try:
|
||
|
|
t = dateutil.parser.parse(k)
|
||
|
|
return t
|
||
|
|
except dateutil.parser.ParserError:
|
||
|
|
pass
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
|
||
|
|
print("TITRE:", html["title"])
|
||
|
|
|
||
|
|
soup = bs4.BeautifulSoup(html["body"], 'html.parser')
|
||
|
|
divs = soup.select("div")
|
||
|
|
|
||
|
|
for d in divs:
|
||
|
|
# don't handle subsections
|
||
|
|
if d.find_parent("div"): continue
|
||
|
|
|
||
|
|
print("="*40)
|
||
|
|
print(d)
|
||
|
|
print(find_date(d))
|