summaryrefslogtreecommitdiffstats
path: root/krebs/5pkgs
diff options
context:
space:
mode:
authorlassulus <lass@blue.r>2018-07-06 17:42:04 +0200
committerlassulus <lass@blue.r>2018-07-06 17:44:32 +0200
commit92aa5bb2329c39cf97d4399839989e7401820ae4 (patch)
tree896a5e81402ebe4e9e4cda083c6b4988b845b691 /krebs/5pkgs
parent70e8c4b0a4255a989bf93fe6fca96244ee617eee (diff)
Reaktor url-title: fix some issues with weird urls
ref: https://irc-bot-science.clsr.net/
Diffstat (limited to 'krebs/5pkgs')
-rw-r--r--krebs/5pkgs/simple/Reaktor/plugins.nix24
1 files changed, 15 insertions, 9 deletions
diff --git a/krebs/5pkgs/simple/Reaktor/plugins.nix b/krebs/5pkgs/simple/Reaktor/plugins.nix
index cd389366e..4a7917b68 100644
--- a/krebs/5pkgs/simple/Reaktor/plugins.nix
+++ b/krebs/5pkgs/simple/Reaktor/plugins.nix
@@ -121,21 +121,27 @@ rec {
pattern = "^.*(?P<args>http[s]?://(?:[a-zA-Z]|[0-9]|[$-_@.&+]|[!*\(\),]|(?:%[0-9a-fA-F][0-9a-fA-F]))+).*$$";
path = with pkgs; [ curl perl ];
script = pkgs.writePython3 "url-title" [ "beautifulsoup4" "lxml" ] ''
+ import cgi
import sys
import urllib.request
from bs4 import BeautifulSoup
try:
- soup = BeautifulSoup(urllib.request.urlopen(sys.argv[1]), "lxml")
- title = soup.find('title').string
+ resp = urllib.request.urlopen(sys.argv[1])
+ if resp.headers['content-type'].find('text/html') >= 0:
+ soup = BeautifulSoup(resp.read(16000), "lxml")
+ title = soup.find('title').string
- if title:
- if len(title) > 512:
- print('message to long, skipped')
- elif len(title.split('\n')) > 5:
- print('to many lines, skipped')
- else:
- print(title)
+ if title:
+ if len(title) > 450:
+ print('message to long, rest skipped')
+ elif len(title.split('\n')) > 5:
+ print('to many lines, skipped')
+ else:
+ print(title)
+ else:
+ cd_header = resp.headers['content-disposition']
+ print(cgi.parse_header(cd_header)[1]['filename'])
except: # noqa: E722
pass
'';