skorotkiewicz/rDrama
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

titles: use rdrama's title finding code (#425)

Browse source 
* titles: use rdrama's title finding code
this fixes a potential DoS in some really weird pages (seems to be a bug with BS4)
we're not parsing arbitrary HTML
in addition we make some nice checks

* unescape title to fix bug from upstream

* fix nameerror

* Do not proxy requests, since no proxy available.

On the upstream, the `proxies` dict was intended to use a local SOCKS
proxy running on port 18080 with the express purpose of masking the
server IP address. TheMotte isn't running behind a reverse proxy, so
this purpose is moot. Additionally, we don't have a proxy running in
Docker nor do we appear to have one on prod, which breaks autotitle
and thumbnailing regardless--not sure it matters for TheMotte's
use case, but both codepaths have been inoperative because of it.

* use gevent to timeout the function to prevent a
second theoretical DoS by sending data rly slowly
ref: 816389cf28

Co-authored-by: TLSM <duolsm@outlook.com>
This commit is contained in:
justcool393 2022-11-28 07:52:15 -08:00 • committed by GitHub
parent c3f4b540d0
commit 8a9e1bc54a
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
2 changed files with 29 additions and 10 deletions
Download patch file Download diff file Expand all files Collapse all files

10
files/helpers/const.py
View file

@ -44,6 +44,12 @@ COLORS = {'ff66ac','805ad5','62ca56','38a169','80ffff','2a96f3','eb4963','ff0000
LOGGEDIN_ACTIVE_TIME = 15 * 60
IMAGE_FORMATS = ['png','gif','jpg','jpeg','webp']
VIDEO_FORMATS = ['mp4','webm','mov','avi','mkv','flv','m4v','3gp']
AUDIO_FORMATS = ['mp3','wav','ogg','aac','m4a','flac']
NO_TITLE_EXTENSIONS = IMAGE_FORMATS + VIDEO_FORMATS + AUDIO_FORMATS
AWARDS = {
"lootbox": {
"kind": "lootbox",
@ -250,7 +256,7 @@ utm_regex2 = re.compile('[?&]utm_[a-z]+=[a-z0-9_]+', flags=re.A)
YOUTUBE_KEY = environ.get("YOUTUBE_KEY", "").strip()
proxies = {"http":"http://127.0.0.1:18080","https":"http://127.0.0.1:18080"}
proxies = {}
approved_embed_hosts = [
'rdrama.net',
@ -324,4 +330,6 @@ procoins_li = (0,2500,5000,10000,25000,50000,125000,250000)
linefeeds_regex = re.compile("([^\\n])\\n([^\\n])", flags=re.A)
html_title_regex = re.compile("<title>(.{1,200})</title>", flags=re.I)
def make_name(*args, **kwargs): return request.base_url

27
files/routes/posts.py
View file

@ -1139,21 +1139,32 @@ def api_pin_post(post_id, v):
else: return {"message": "Post unpinned!"}
return {"error": "Post not found!"}
@app.get("/submit/title")
@limiter.limit("6/minute")
@auth_required
def get_post_title(v):
POST_TITLE_TIMEOUT = 5
url = request.values.get("url")
if not url: abort(400)
if not url or '\\' in url: abort(400)
url = url.strip()
if not url.startswith('http'): abort(400)
try: x = requests.get(url, headers=titleheaders, timeout=5, proxies=proxies)
checking_url = url.lower().split('?')[0].split('%3F')[0]
if any((checking_url.endswith(f'.{x}') for x in NO_TITLE_EXTENSIONS)):
abort(400)
try:
x = gevent.with_timeout(POST_TITLE_TIMEOUT, requests.get,
url, headers=titleheaders, timeout=POST_TITLE_TIMEOUT,
proxies=proxies)
except: abort(400)
soup = BeautifulSoup(x.content, 'lxml')
content_type = x.headers.get("Content-Type")
if not content_type or "text/html" not in content_type: abort(400)
title = soup.find('title')
if not title: abort(400)
match = html_title_regex.search(x.text)
if match and match.lastindex >= 1:
title = html.unescape(match.group(1))
else: abort(400)
return {"url": url, "title": title.string}
return {"url": url, "title": title}