diff options
| author | 2019-10-31 15:17:39 +0000 | |
|---|---|---|
| committer | 2019-10-31 15:17:39 +0000 | |
| commit | 5d08a496a45040ffed968e2484090ba807a566c6 (patch) | |
| tree | 633eedac7e87373d299b9d1ca8bea504883c9ba0 /modules | |
| parent | fix bitbotd `database.servers.delete` type hint issue (diff) | |
| signature | ||
use lxml for parsing fedi Notes. html.parse is bad and unpredictable
Diffstat (limited to 'modules')
| -rw-r--r-- | modules/fediverse/ap_utils.py | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/modules/fediverse/ap_utils.py b/modules/fediverse/ap_utils.py index 934959e7..8d8dfa6e 100644 --- a/modules/fediverse/ap_utils.py +++ b/modules/fediverse/ap_utils.py @@ -61,7 +61,7 @@ def find_actor(username, instance): KNOWN_TAGS = ["p", "br"] def _normalise_note(content): - soup = bs4.BeautifulSoup(content, "html.parser") + soup = bs4.BeautifulSoup(content, "lxml").body lines = [] for element in soup.find_all(): if element.text.strip() == "": |
