mirror of
https://github.com/ail-project/ail-framework.git
synced 2024-11-10 08:38:28 +00:00
fix: [PgpDump] catch bs4 error
This commit is contained in:
parent
3ec72b0430
commit
0ec56cf1ed
1 changed files with 12 additions and 9 deletions
|
@ -41,16 +41,19 @@ def save_in_file(message, pgp_content):
|
|||
r_serv_db.sadd('pgpdumb:uuid', '{};{}'.format(UUID, message))
|
||||
|
||||
def remove_html(item_content):
|
||||
if bool(BeautifulSoup(item_content, "html.parser").find()):
|
||||
soup = BeautifulSoup(item_content, 'html.parser')
|
||||
# kill all script and style elements
|
||||
for script in soup(["script", "style"]):
|
||||
script.extract() # remove
|
||||
try:
|
||||
if bool(BeautifulSoup(item_content, "html.parser").find()):
|
||||
soup = BeautifulSoup(item_content, 'html.parser')
|
||||
# kill all script and style elements
|
||||
for script in soup(["script", "style"]):
|
||||
script.extract() # remove
|
||||
|
||||
# get text
|
||||
text = soup.get_text()
|
||||
return text
|
||||
else:
|
||||
# get text
|
||||
text = soup.get_text()
|
||||
return text
|
||||
else:
|
||||
return item_content
|
||||
except TypeError:
|
||||
return item_content
|
||||
|
||||
def extract_all_id(message, item_content, regex=None, is_file=False):
|
||||
|
|
Loading…
Reference in a new issue