Error handling, tests, lint, beat the patriarchy slightly

Author: HairyFotr

requirements.txt

@@ -1,10 +1,10 @@
-requests==2.4.3
-Pillow==2.6.1
-tweepy==3.1.0
+requests==2.9.1
+Pillow==3.1.1
+tweepy==3.5.0
 gdata==2.0.18
-pytest==2.6.4
-mock==1.0.1
-lxml==3.4.1
-coverage==3.7.1
-coveralls==0.5
-Pafy==0.3.74
+pytest==2.8.7
+mock==1.3.0
+lxml==3.5.0
+coverage==4.0.3
+coveralls==1.1
+Pafy==0.4.3

run_analysis

@@ -1,9 +1,9 @@
 #!/bin/sh
 export PYTHONPATH=src/:$PYTHONPATH
 . venv/bin/activate
-
 pip install -r requirements-analysis.txt -U
-pep8 --ignore=E501,W503 src tests
+
+pep8 --ignore=W503 src tests
 pyflakes src tests
 pep257 --ignore=D100,D101,D102,D103,D104,D200,D205,D211,D400 src tests
 bandit -r src

run_tests

@@ -1,4 +1,4 @@
 #!/bin/sh
 export PYTHONPATH=src/:$PYTHONPATH
 . venv/bin/activate
-coverage run --source src -m py.test -s tests
+coverage run --source src -m py.test -s tests && coverage report

setup_venv

@@ -1,4 +1,4 @@
 #!/bin/sh
 virtualenv venv
 . venv/bin/activate
-pip install -r requirements.txt
+pip install -r requirements.txt -U

src/handler.py

@@ -58,12 +58,20 @@ def handle_connect(self):
     def collect_incoming_data(self, data):
         self.buffer += data
 
-    def log_error(self, error):
+    def log_error(self, text):
         with open("error.log", "a") as f:
             f.write(str(datetime.now()) + '\n')
-            f.write('ERROR: ' + str(error) + '\n\n')
-        if self.debug:
-            print error
+            f.write('Error: ' + text + '\n')
+            if self.debug:
+                print text
+
+            from traceback import format_exception
+            from sys import exc_info
+            ex_type, ex_val, ex_tb = exc_info()
+            ex_text = ''.join(format_exception(ex_type, ex_val, ex_tb, 10))
+            f.write(ex_text + '\n')
+            if self.debug:
+                print ex_text
 
     def found_terminator(self):
         line = self.buffer

src/plugins/nsfw_image_detector.py

@@ -8,10 +8,10 @@
 * jpeg decoder for PIL (libjpeg-dev package on Ubuntu)
 """
 
-import re
 import os
 import uuid
 import tempfile
+import regex
 from os.path import join as pjoin
 
 import requests
@@ -33,11 +33,6 @@
 
 SKIN_PERCENTAGE_THRESHOLD = 30
 
-imgur_regex = re.compile(
-    "(?:https?://)(?:www[.])?(?:imgur.com/)"
-    + "(?:(?:gallery/)|(?:r/[a-z]+/))?([A-Za-z0-9]+)"
-)
-
 
 class NSFWImageDetectorPlugin(BotPlugin):
 
@@ -50,7 +45,7 @@ def __init__(self, bot):
         self._images_dir = tempfile.mkdtemp(suffix='nsfw-images')
 
     def handle_message(self, channel, nick, msg, line=None):
-        urls = re.findall(r'(https?://[^\s]+)', msg)
+        urls = regex.WEB_URL.findall(msg)
 
         if not urls:
             return
@@ -102,7 +97,8 @@ def _get_skin_ratio_percentage(self, file_path):
         try:
             im = Image.open(file_path)
         except:
-            self.bot.log_error('Could not open NSFW image: ' + file_path)
+            self.bot.log_error('Could not open NSFW image: "'
+                               + file_path + '"')
             return 0.0
 
         im = im.convert('RGB')
@@ -132,9 +128,10 @@ def _get_image_urls(self, urls):
 
         image_urls = []
         for url in urls:
-            imgur_id = imgur_regex.search(url)
-            if imgur_id:
-                url = "https://i.imgur.com/" + imgur_id.group(1) + ".jpg"
+            # Rewrite imgur urls
+            imgur_res = regex.IMGUR.search(url)
+            if imgur_res:
+                url = "https://i.imgur.com/" + imgur_res.group('id') + ".jpg"
 
             if self._is_image_url(url=url):
                 image_urls.append(url)
@@ -154,6 +151,8 @@ def _download_image(self, url):
             extension = os.path.splitext(url)[1]
             response = requests.get(url, stream=True)
         except:
+            self.bot.log_error('Failed to download NSFW image: "'
+                               + url + '"')
             return
 
         if not response.status_code == 200:
@@ -168,8 +167,8 @@ def _download_image(self, url):
                 if first_chunk:
                     first_chunk = False
                     if not self._is_image(chunk):
-                        self.bot.log_error('NSFW image was not an image: '
-                                           + url)
+                        self.bot.log_error('NSFW image was not an image: "'
+                                           + url + '"')
                         return
 
                 fp.write(chunk)

src/plugins/psywerx_history.py

@@ -12,21 +12,21 @@ def handle_message(self, channel, nick, msg, line=None):
         if r.startswith('REPOST'):
             self._handle_repost(r, channel)
         elif r != 'OK':
-            self.bot.log_error("Response: " + r)
+            self.bot.log_error("Response not OK: " + r)
 
     def handle_say(self, channel, msg, line):
         msg = ":" + self.bot.nick + "!~" + self.bot.nick + "@6.6.6.6 " + line
         self.request(channel, 'irc/add', {'raw': msg})
 
     def _handle_repost(self, r, channel):
-        _, nick, repostNick, messageType, num = r.split(' ')
-        if messageType != 'M':
+        _, nick, repost_nick, message_type, num = r.split(' ')
+        if message_type != 'M':
             return
 
-        response = self._pick_response(nick == repostNick, int(num) > 1)
+        response = self._pick_response(nick == repost_nick, int(num) > 1)
         self.bot.say(response % {
             'nick': nick,
-            'repostNick': repostNick,
+            'repost_nick': repost_nick,
             'num': num
         }, channel)
 

src/plugins/psywerx_karma.py

@@ -33,14 +33,17 @@ def pf(number):
                 self.bot.say(str("** CONGRATS " + p['nick'] + " **"), channel)
 
         except:
-            from traceback import format_exc
-            self.bot.log_error('Could not get upboats: ' + str(format_exc()))
+            self.bot.log_error('Could not get upboats.')
 
     def _karma(self, tokens, channel):
         if len(tokens) != 1:
-            r = json.loads(self.request(channel, 'irc/karma_nick', {}))
+            response = self.request(channel, 'irc/karma_nick', {})
+            if not response:
+                msg = "Sorry, could not get karmas."
+                self.bot.say(msg, channel)
+                return
             s = ""
-            for p in r:
+            for p in json.loads(response):
                 s += str(p['nick']) + " (" + str(p['karma']) + "), "
             self.bot.say(s[:-2], channel)
         else:
@@ -49,6 +52,8 @@ def _karma(self, tokens, channel):
             params = {'nick': nick}
             response = self.request(channel, 'irc/karma_nick', params)
             if not response:
+                msg = "Sorry, could not get karma for " + nick + "."
+                self.bot.say(msg, channel)
                 return
             nick = tokens[0] if tokens[0] not in users else users[tokens[0]]
             self.bot.say(nick + " has " + response + " karma.", channel)

src/plugins/read_links.py

@@ -1,20 +1,20 @@
 from base import BotPlugin
-from tweepy import OAuthHandler, API
+from tweepy import OAuthHandler, API as TWITTER_API
 from settings import TWITTER as T
 from response import random_response
-from regex import twt_regex, yt_regex, vimeo_regex, web_regex
 from urllib2 import urlopen
-import json
 import re
+import json
 import requests
 import lxml.html
+import regex
 
-oauth = OAuthHandler(T['consumer_key'], T['consumer_secret'])
-oauth.set_access_token(T['access_token_key'], T['access_token_secret'])
-twt = API(oauth)
+TWITTER_OAUTH = OAuthHandler(T['consumer_key'], T['consumer_secret'])
+TWITTER_OAUTH.set_access_token(T['access_token_key'], T['access_token_secret'])
+TWITTER = TWITTER_API(TWITTER_OAUTH)
 
 # These will be filtered out in _read_webistes
-__all_non_web__ = [twt_regex, yt_regex, vimeo_regex]
+__all_non_web__ = [regex.TWITTER, regex.YOUTUBE, regex.VIMEO]
 
 VIDEO_RESPONSES = [
     "That video is titled '%(title)s'. "
@@ -41,25 +41,23 @@
 
 class ReadLinks(BotPlugin):
 
-    def _get_name_text(self, status_id):
-        status = twt.get_status(status_id)
+    def _get_tweet_info(self, status_id):
+        status = TWITTER.get_status(status_id)
         name = status.user.screen_name
         text = status.text.replace('\n', ' ')
         return name, text
 
     def _read_twitter(self, channel, msg):
-        res = twt_regex.search(msg)
-        if not res:
+        twt_res = regex.TWITTER.search(msg)
+        if not twt_res:
             return
         try:
-            (name, text) = self._get_name_text(str(res.groups()[0]))
+            (name, text) = self._get_tweet_info(twt_res.group('id'))
             response = unicode("@" + name + " on Twitter says: " + text)
             response = response.encode('utf8')
             self.bot.say(response, channel)
-        except Exception as e:
-            print e
-            self.bot.log_error('Could not get tweet from: "'
-                               + msg + '" the exception was: ' + str(e))
+        except:
+            self.bot.log_error('Could not get tweet from: "' + msg + '"')
             self.bot.say('Sorry, I wasn\'t able to read the last tweet :(',
                          channel)
 
@@ -80,17 +78,16 @@ def _get_vimeo_info(self, video_id):
         }
 
     def _read_vimeo(self, channel, msg):
-        res = vimeo_regex.search(msg)
-        if not res:
+        vimeo_res = regex.VIMEO.search(msg)
+        if not vimeo_res:
             return
         try:
-            video_id = str(res.groups()[0])
-            video_info = self._get_vimeo_info(video_id)
+            video_info = self._get_vimeo_info(vimeo_res.group('id'))
             self.bot.say(random_response(VIDEO_RESPONSES) % video_info,
                          channel)
-        except Exception as e:
+        except:
             self.bot.log_error('Could not get title of vimeo link from: "'
-                               + msg + '" the exception was: ' + str(e))
+                               + msg + '"')
             self.bot.say('For some reason I couldn\'t read the title of that '
                          + 'vimeo link.', channel)
 
@@ -113,36 +110,34 @@ def _get_youtube_info(self, video_id):
         }
 
     def _read_youtube(self, channel, msg):
-        res = yt_regex.search(msg)
-        if not res:
+        yt_res = regex.YOUTUBE.search(msg)
+        if not yt_res:
             return
         try:
-            video_id = str(res.groups()[0])
-            video_info = self._get_youtube_info(video_id)
+            video_info = self._get_youtube_info(yt_res.group('id'))
             self.bot.say(random_response(VIDEO_RESPONSES) % video_info,
                          channel)
-        except Exception as e:
+        except:
             self.bot.log_error('Could not get title of youtube link from: "'
-                               + msg + '" the exception was: ' + str(e))
+                               + msg + '"')
             self.bot.say('For some reason I couldn\'t read the title of that '
                          + 'youtube link.', channel)
 
     def _read_websites(self, channel, msg):
-        links = web_regex.findall(msg)
+        links = regex.WEB_URL.findall(msg)
         for link in links:
-            link = link[0]
             if [r for r in __all_non_web__ if r.search(link)]:
                 continue
             try:
-                t = lxml.html.parse(urlopen(str(link)))  # nopep8 # nosec: web_regex only allows http(s)
+                t = lxml.html.parse(urlopen(link))  # nopep8 # nosec: regex.WEB_URL only allows http(s)
                 t = t.find(".//title").text
                 t = t.strip().replace('\n', ' ')
                 if len(re.sub("[^a-zA-Z0-9]", "", t)) >= 5:
                     self.bot.say(random_response(WEB_RESPONSES) % {'title': t},
                                  channel)
-            except Exception as e:
+            except:
                 self.bot.log_error('Could not get title of webpage: "'
-                                   + msg + '" the exception was: ' + str(e))
+                                   + msg + '"')
 
     def handle_message(self, channel, nick, msg, line=None):
         if "PRIVMSG" in line:

src/plugins/uptime.py

@@ -11,6 +11,7 @@ def _uptime(self, tokens, channel):
                 server_uptime_seconds = int(float(f.readline().split()[0]))
                 server_uptime = str(timedelta(seconds=server_uptime_seconds))
         except:
+            self.bot.log_error('Could not get server uptime.')
             server_uptime = "unknown"
 
         bot_uptime_seconds = int(time() - self.bot.uptime)

src/regex.py

@@ -1,13 +1,14 @@
 import re
 
-twt_regex = re.compile(
-    "https?://(?:www\\.)?twitter\\.com/.*/status(?:es)?/([0-9]+)")
-yt_regex = re.compile(
-    "https?://(?:www\\.)?(?:youtu[.]be|youtube[.]com)/"
-    + "(?:embed/)?(?:[^/ ]*?[?&]v=)?([A-Za-z0-9_-]{11})(?:[^A-Za-z0-9_-]|$)")
-vimeo_regex = re.compile(
-    "https?://(?:www\\.)?vimeo.com/(?:videos?/)?([0-9]+)")
-url_regex = re.compile(
-    r"(?i)\b((?:[a-z][\w-]+:(?:/{1,3}|[a-z0-9%])|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s'!()\[\]{};:'\".,<>?']))")  # nopep8
-web_regex = re.compile(
-    r"(?i)\b((?:https?:(?:/{1,3}|[a-z0-9%])|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+|\(([^\s()<>]+|(\([^\s()<>]+\)))*\))+(?:\(([^\s()<>]+|(\([^\s()<>]+\)))*\)|[^\s'!()\[\]{};:'\".,<>?']))")  # nopep8
+TWITTER = re.compile(
+    "https?://(?:www[.])?twitter[.]com/.*/status(?:es)?/(?P<id>[0-9]+)")
+YOUTUBE = re.compile(
+    "https?://(?:www[.])?(?:youtu[.]be|youtube[.]com)/(?:embed/)?(?:[^/ ]*?[?&]v=)?(?P<id>[A-Za-z0-9_-]{11})(?:[^A-Za-z0-9_-]|$)")  # nopep8
+VIMEO = re.compile(
+    "https?://(?:www[.])?vimeo.com/(?:videos?/)?(?P<id>[0-9]+)")
+IMGUR = re.compile(
+    "https?://(?:www[.])?imgur.com/(?:(?:gallery/)|(?:r/[a-z]+/))?(?P<id>[A-Za-z0-9]+)")  # nopep8
+ANY_URL = re.compile(
+    r"(?i)\b((?:[a-z][\w-]+:(?:/{1,3}|[a-z0-9%])|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+|\((?:[^\s()<>]+|(?:\([^\s()<>]+\)))*\))+(?:\((?:[^\s()<>]+|(?:\([^\s()<>]+\)))*\)|[^\s'!()\[\]{};:'\".,<>?']))")  # nopep8
+WEB_URL = re.compile(
+    r"(?i)\b((?:https?:(?:/{1,3}|[a-z0-9%])|www\d{0,3}[.]|[a-z0-9.\-]+[.][a-z]{2,4}/)(?:[^\s()<>]+|\((?:[^\s()<>]+|(?:\([^\s()<>]+\)))*\))+(?:\((?:[^\s()<>]+|(?:\([^\s()<>]+\)))*\)|[^\s'!()\[\]{};:'\".,<>?']))")  # nopep8