urls - remove broken APIs

[erebus.git] / modules / urls.py

diff --git a/modules/urls.py b/modules/urls.py
index 901d191c3aa78f8f77fd187c3b26b8b9fcd1b124..ae80a4e92e3c3424b9642300ff5d19fa7ae6a06b 100644 (file)
--- a/modules/urls.py
+++ b/modules/urls.py
@@ -1,4 +1,4 @@
-# Erebus IRC bot - Author: Erebus Team
+# Erebus IRC bot - Author: Conny Sjoblom
 # vim: fileencoding=utf-8
 # URL Checker
 # This file is released into the public domain; see http://unlicense.org/
@@ -23,20 +23,21 @@ modstop = lib.modstop
 # module code
 import sys
 if sys.version_info.major < 3:
+       stringbase = basestring
        import urllib2
        import urlparse
        import HTMLParser
+       html = HTMLParser.HTMLParser()
        from BeautifulSoup import BeautifulSoup
 else:
+       stringbase = str
        import urllib.request as urllib2
        import urllib.parse as urlparse
-       import html.parser as HTMLParser
+       import html
        from bs4 import BeautifulSoup
 
 import re, json, datetime
 
-html_parser = HTMLParser.HTMLParser()
-
 hostmask_regex = re.compile(r'^(.*)!(.*)@(.*)$')
 
 def parser_hostmask(hostmask):
@@ -87,9 +88,12 @@ def process_line(line):
                                        num_found += 1
                                        if num_found > limit:
                                                return responses
-                                       resp = action(match)
+                                       if isinstance(match, stringbase):
+                                               resp = action(match)
+                                       else:
+                                               resp = action(*match)
                                        if resp is not None:
-                                               responses.append("%s: %s" % (prefix, action(match)))
+                                               responses.append("%s: %s" % (prefix, resp))
        return responses
 
 @lib.hooknum("PRIVMSG")
@@ -111,7 +115,7 @@ def privmsg_hook(bot, textline):
                        bot.msg(chan, ' | '.join(responses), True)
 
 def unescape(line):
-       return re.sub('\s+', ' ', html_parser.unescape(line))
+       return re.sub('\s+', ' ', html.unescape(line))
 
 def gotspotify(type, track):
        url = 'http://ws.spotify.com/lookup/1/?uri=spotify:%s:%s' % (type, track)
@@ -207,36 +211,27 @@ def goturl(url):
                for regex in group:
                        if regex.match(url):
                                return None
-       request = urllib2.Request(url)
+       request = urllib2.Request(url, headers={'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/115.0.0.0 Safari/537.36'})
        opener = urllib2.build_opener(SmartRedirectHandler())
        try:
-               soup = BeautifulSoup(opener.open(request, timeout=0.5))
+               soup = BeautifulSoup(opener.open(request, timeout=2))
                if soup.title:
                        return unescape('%s' % (soup.title.string))
                else:
                        return None
        except urllib2.HTTPError as e:
                return 'Error: %s %s' % (e.code, e.reason)
+       except urllib2.URLError as e:
+               return 'Error: %s' % (e.reason)
+       except TimeoutError as e:
+               return 'Error: request timed out'
        except Exception as e:
-               return 'Error: %r' % (e.message)
+               return 'Error: %s %r' % (type(e).__name__, e.args)
 
 url_regex = (
        re.compile(r'https?://[^/\s]+\.[^/\s]+(?:/\S+)?'),
 )
-spotify_regex = (
-       re.compile(r'spotify:(?P<type>\w+):(?P<track_id>\w{22})'),
-       re.compile(r'https?://open\.spotify\.com/(?P<type>\w+)/(?P<track_id>\w+)')
-)
-youtube_regex = (
-       re.compile(r'https?://(?:www\.)?youtube\.com/watch\?[a-zA-Z0-9=&_\-]+'),
-)
-twitch_regex = (
-       re.compile(r'https?:\/\/(?:www\.)?twitch.tv\/([A-Za-z0-9]*)'),
-)
 other_regexes = (
-       (gotspotify, spotify_regex, 'Spotify'),
-       (gotyoutube, youtube_regex, 'YouTube'),
-       (gottwitch, twitch_regex, 'Twitch'),
 )
 regexes = other_regexes + (
        (goturl, url_regex, 'Title'),