From 28ef6bd23d0e83e9123db9175c8a5c6090cbd80d Mon Sep 17 00:00:00 2001
From: Thorsten <mail@aero2k.de>
Date: Wed, 6 Sep 2017 21:37:49 +0200
Subject: [PATCH] add search, fix TLS, do not import plugins in idlebot

---
 idlebot.py          | 12 ++++--
 plugins/commands.py | 23 ++++++++++-
 plugins/searx.py    | 98 +++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 127 insertions(+), 6 deletions(-)
 create mode 100644 plugins/searx.py

diff --git a/idlebot.py b/idlebot.py
index 840ae56..7b647c1 100755
--- a/idlebot.py
+++ b/idlebot.py
@@ -1,19 +1,23 @@
 #!/usr/bin/python3
 # -*- coding: utf-8 -*-
 import logging
-import time
 import sys
+import time
+import _ssl
+
+from sleekxmpp import ClientXMPP
+
 import config
 import events
 from common import VERSION
 
-from sleekxmpp import ClientXMPP
-
 
 class IdleBot(ClientXMPP):
     def __init__(self, jid, password, rooms, nick):
         ClientXMPP.__init__(self, jid, password)
 
+        self.ssl_version = _ssl.PROTOCOL_TLSv1_2
+
         self.rooms = rooms
         self.nick = nick
 
@@ -114,7 +118,7 @@ def start(botclass, active=False):
     config.runtimeconf_set('start_time', -time.time())
 
     if active:
-        import plugins
+        pass
 
     events.event_loop.start()
 
diff --git a/plugins/commands.py b/plugins/commands.py
index 4a4e9b1..f22065e 100644
--- a/plugins/commands.py
+++ b/plugins/commands.py
@@ -14,6 +14,7 @@ from lxml import etree
 
 import config
 from common import VERSION
+from plugins.searx import searx
 from rate_limit import RATE_FUN, RATE_GLOBAL, RATE_INTERACTIVE, RATE_NO_SILENCE, RATE_NO_LIMIT
 from plugin_system import pluginfunction, ptypes, plugin_storage, plugin_enabled_get, plugin_enabled_set
 
@@ -881,8 +882,8 @@ def reload_runtimeconfig(argv, **args):
         return {'msg': 'done'}
 
 
-@pluginfunction('search', 'search the web (using duckduckgo)', ptypes.COMMAND)
-def search_the_web(argv, **args):
+@pluginfunction('ducksearch', 'search the web (using duckduckgo)', ptypes.COMMAND)
+def search_the_duck(argv, **args):
     url = 'http://api.duckduckgo.com/'
     params = dict(
         q=' '.join(argv),
@@ -913,6 +914,24 @@ def search_the_web(argv, **args):
         return {'msg': 'Sorry, no results.'}
 
 
+@pluginfunction('search', 'search the web (using searx)', ptypes.COMMAND)
+def search_the_web(argv, **args):
+    result = searx(' '.join(argv))
+    if not result:
+        return {'msg': 'Sorry, no results.'}
+    else:
+        abstract, url = result
+
+    if len(abstract) > 150:
+        suffix = '…'
+    else:
+        suffix = ''
+    return {
+        'msg': '{}{} ({})'.format(abstract[:150], suffix, url)
+    }
+    pass
+
+
 @pluginfunction('raise', 'only for debugging', ptypes.COMMAND)
 def raise_an_error(argv, **args):
     if args['reply_user'] == config.conf_get("bot_owner"):
diff --git a/plugins/searx.py b/plugins/searx.py
new file mode 100644
index 0000000..058e318
--- /dev/null
+++ b/plugins/searx.py
@@ -0,0 +1,98 @@
+import logging
+import time
+from functools import wraps
+from json import JSONDecodeError
+
+import requests
+from lxml import etree, html
+from requests import HTTPError
+
+search_list = []
+
+
+class RateLimitingError(HTTPError):
+    pass
+
+
+def retry(ExceptionToCheck, tries=4, delay=3, backoff=2, logger=None):
+    """Retry calling the decorated function using an exponential backoff.
+
+    http://www.saltycrane.com/blog/2009/11/trying-out-retry-decorator-python/
+    original from: http://wiki.python.org/moin/PythonDecoratorLibrary#Retry
+
+    :param ExceptionToCheck: the exception to check. may be a tuple of
+        exceptions to check
+    :type ExceptionToCheck: Exception or tuple
+    :param tries: number of times to try (not retry) before giving up
+    :type tries: int
+    :param delay: initial delay between retries in seconds
+    :type delay: int
+    :param backoff: backoff multiplier e.g. value of 2 will double the delay
+        each retry
+    :type backoff: int
+    :param logger: logger to use. If None, print
+    :type logger: logging.Logger instance
+    """
+
+    def deco_retry(f):
+
+        @wraps(f)
+        def f_retry(*args, **kwargs):
+            mtries, mdelay = tries, delay
+            while mtries > 1:
+                try:
+                    return f(*args, **kwargs)
+                except ExceptionToCheck as e:
+                    msg = "%s, Retrying in %d seconds..." % (str(e), mdelay)
+                    if logger:
+                        logger.warning(msg)
+                    else:
+                        print(msg)
+                    time.sleep(mdelay)
+                    mtries -= 1
+                    mdelay *= backoff
+            return f(*args, **kwargs)
+
+        return f_retry  # true decorator
+
+    return deco_retry
+
+
+def fetch_all_searx_engines():
+    # error handling is for pussies
+    tree = etree.XML(
+        requests.get("http://stats.searx.oe5tpo.com").content,
+        parser=html.HTMLParser()
+    )
+    searxes = [str(x) for x in tree.xpath('//span[text()[contains(.,"200 - OK")]]/../..//a/text()')]
+
+    return searxes
+
+
+@retry(ExceptionToCheck=(RateLimitingError, JSONDecodeError))
+def searx(text):
+    global search_list
+    if not search_list:
+        search_list = fetch_all_searx_engines()
+    logger = logging.getLogger(__name__)
+
+    url = search_list[-1]
+    logger.info('Currently feeding from {} (of {} in stock)'.format(url, len(search_list)))
+    response = requests.get(url, params={
+        'q': text,
+        'format': 'json',
+        'lang': 'de'
+    })
+    if response.status_code == 429:
+        search_list.pop()
+        raise RateLimitingError(response=response, request=response.request)
+    try:
+        response = response.json()
+    except JSONDecodeError as e:
+        # "maintenance" they say...
+        search_list.pop()
+        raise
+
+    if not response['results']:
+        return
+    return [(r['content'], r['url']) for r in response['results']][0]