27 lines
909 B
Python
27 lines
909 B
Python
from bs4 import BeautifulSoup
|
|
import html, re
|
|
|
|
def extract_post(post):
|
|
post = html.unescape(post) # convert HTML escape codes to text
|
|
soup = BeautifulSoup(post, "html.parser")
|
|
for lb in soup.select("br"): # replace <br> with linebreak
|
|
lb.insert_after("\n")
|
|
lb.decompose()
|
|
|
|
for p in soup.select("p"): # ditto for <p>
|
|
p.insert_after("\n")
|
|
p.unwrap()
|
|
|
|
for ht in soup.select("a.hashtag"): # convert hashtags from links to text
|
|
ht.unwrap()
|
|
|
|
for link in soup.select("a"): #ocnvert <a href='https://example.com>example.com</a> to just https://example.com
|
|
link.insert_after(link["href"])
|
|
link.decompose()
|
|
|
|
text = soup.get_text()
|
|
text = re.sub("https://([^/]+)/(@[^ ]+)", r"\2@\1", text) # put mastodon-style mentions back in
|
|
text = re.sub("https://([^/]+)/users/([^ ]+)", r"@\2@\1", text) # put pleroma-style mentions back in
|
|
text = text.rstrip("\n") # remove trailing newline(s)
|
|
return text
|