Big cleanup part 2 (#58)

* Cleanup little-boxes stuff * Force html5lib for parsing OG data * Bugfixes
2019-08-04 16:34:30 +02:00
parent d38c43ebe8
commit a21121308f
11 changed files with 402 additions and 125 deletions
--- a/utils/opengraph.py
+++ b/utils/opengraph.py
@@ -23,7 +23,7 @@ def links_from_note(note):

    links = set()
    if "content" in note:
-        soup = BeautifulSoup(note["content"])
+        soup = BeautifulSoup(note["content"], "html5lib")
        for link in soup.find_all("a"):
            h = link.get("href")
            if h.startswith("http") and h not in tags_href and is_url_valid(h):