def slutrating(phrase):
phrase = cleanurl(phrase)
for i in range(5): # Try up to 5 times to get a good result
try:
data = geturl(searchURL, opts={u'q': phrase, u'safe': u'off'})
unsafe = int(match_re.search(data).group(1).replace(u',', u''))
except AttributeError:
unsafe = 0
try:
data = geturl(searchURL, opts={u'q': phrase, u'safe': u'active'})
try:
filtered = filter_re.search(data).group(1)
raise WordFiltered(filtered)
except AttributeError:
pass
safe = int(match_re.search(data).group(1).replace(u',', u''))
except AttributeError:
safe = 0
if not unsafe:
if safe > 0:
continue # shouldn't really be possible to have safe w/o unsafe
else:
return 0
value = float(unsafe - safe) / float(unsafe)
if value > 0:
return value
def rate_imdb(self, name):
"""Get user rating from IMDB"""
page = geturl(self.imdb_search, {'s': 'tt', 'q': name},
referer=self.imdb_url)
soup = BeautifulSoup(page)
if soup.title.renderContents() == 'IMDb Title Search':
main = soup.body.find('div', id='main')
name = self.normalize(name)
url = None
for p in main('p', style=None):
for row in p.table('tr'):
link = row('td')[2].a
if self.normalize(link.renderContents()) == name:
url = urljoin(self.imdb_url, link['href'])
break
if url:
break
else:
raise ValueError('no exact matches')
soup = BeautifulSoup(geturl(url, referer=self.imdb_search))
try:
rating = soup.body.find('div', 'meta').b.renderContents()
except AttributeError:
rating = 'Unrated'
return stripHTML(soup.title.renderContents()), rating
def get_song_for_artist(self, qsong, qartist):
opts = dict(self.search_opts)
opts['type'] = 'artist'
opts['q'] = qartist
page = geturl(self.search, opts=opts, referer=self.baseurl)
results = self.result.findall(page)
exact = None
for url, artist in results:
if normalize(artist) == normalize(qartist):
exact = url
break
if not exact:
exact = results[0][0]
url = urljoin(self.baseurl, exact)
url = urljoin(url, 'lyrics.html')
page = geturl(url, referer=self.search)
results = self.result.findall(page)
exact = None
for url, song in results:
song = song.replace(' lyrics', '')
if normalize(song) == normalize(qsong):
exact = url
break
if not exact:
exact = results[0][0]
url = urljoin(self.baseurl, exact)
return self.get_lyrics_from_url(url)
def response(self, nick, args, kwargs):
try:
group_page = geturl(self.group_url)
ids = {}
for id, name, status in self.member_re.findall(group_page):
ids[id] = dict(name=name, status=status)
for id, link in self.link_re.findall(group_page):
ids[id]['link'] = link
ingame = []
online = []
for data in ids.values():
if data['status'] == 'In-Game':
page = geturl(data['link'])
try:
game = self.game_re.search(page).group(1).strip()
except AttributeError:
game = 'Non-Steam Game'
ingame.append('%s: %s' % (data['name'], game))
elif data['status'] == 'Online' and self.online:
online.append('%s: Online' % data['name'])
output = ingame + online
if not output:
if self.online:
message = 'Online'
else:
message = 'In-Game'
output = ['No users ' + message]
return '\n'.join(output)
except Exception, error:
log.warn(u'error in module %s' % self.__module__)
log.exception(error)
return u'%s: %s' % (nick, error)
def lookup_item(self, item):
page = geturl(self._search_url, opts={u'search_text': item})
item = item.lower()
redirect = self._redirect_re.search(page)
if redirect:
url = urljoin(self._base_url, redirect.group(1))
page = geturl(url)
elif u'Search results for' in page:
items = self._results_re.findall(page)
if not items:
return
items = [(v.lower(), k) for k, v in items]
items = sorted(items)
map = dict(items)
if item in map:
url = map[item]
else:
url = items[0][1]
page = geturl(url)
bonus = u', '.join(self._bonus_re.findall(page))
bonus = self._stat_gap_re.sub(r'\1\2', bonus)
if not bonus:
bonus = u'No bonuses'
rarity, name = self._item_name_re.search(page).groups()
color = self._rarity_colors[rarity]
name = name.replace('\\', '')
name = name.strip()
name = self.colorlib.get_color(color, text=name)
return u'%s: %s' % (name, bonus)
def response(self, nick, args, kwargs):
try:
geturl(self.baseurl)
doc = geturl(self.searchurl, opts={'number': args[0]})
city, state = self.city.search(doc).groups()
city = ' '.join([x.lower().capitalize() for x in city.split()])
return '%s: %s = %s, %s' % (nick, args[0], city, state)
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return "%s: I couldn't look that up for some reason. D:" % nick
def response(self, nick, args, kwargs):
try:
geturl(self.baseurl)
doc = geturl(self.searchurl, opts={'number': args[0]})
city, state = self.city.search(doc).groups()
city = ' '.join([x.lower().capitalize() for x in city.split()])
return '%s: %s = %s, %s' % (nick, args[0], city, state)
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return "%s: I couldn't look that up for some reason. D:" % nick
def response(self, nick, args, kwargs):
query = args[0]
try:
check = self.clean.sub('', query)
check = re.compile(check, re.I)
results = []
doc = geturl(self.url)
for i in self.incidents.findall(doc):
data = [stripHTML(c) for c in self.data.findall(i)][1:]
if len(data) != 4:
continue
if check.search(data[2]):
results.append('=> %s: %s - %s - %s' %
(data[0], data[1], data[2], data[3]))
if len(results) > 0:
return '\n'.join(results)
else:
return '%s: No incidents found' % nick
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return '%s: I failed to perform that lookup' % nick
def response(self, nick, args, kwargs):
try:
source = self.sources[args[0]]
try:
query = args[1]
except:
query = None
try:
num = int(query)
query = None
except:
num = None
if num:
url = source.bynum.replace(u'num', unicode(num))
opts = None
elif query:
url = source.search
opts = dict(source.opts)
opts[source.query] = query
else:
url = source.random
opts = None
doc = geturl(url, opts=opts)
entries = source.entries.findall(doc)
if query:
entries = filter(None, entries)
entry = random.choice(entries)
entry = stripHTML(entry).strip()
return entry
except Exception, error:
log.warn(u'error in module %s' % self.__module__)
log.exception(error)
return u'%s: %s' % (nick, self._error)
def response(self, nick, args, kwargs):
query = args[0]
try:
check = self.clean.sub('', query)
check = re.compile(check, re.I)
results = []
doc = geturl(self.url)
for i in self.incidents.findall(doc):
data = [stripHTML(c) for c in self.data.findall(i)][1:]
if len(data) != 4:
continue
if check.search(data[2]):
results.append('=> %s: %s - %s - %s' % (data[0], data[1],
data[2], data[3]))
if len(results) > 0:
return '\n'.join(results)
else:
return '%s: No incidents found' % nick
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return '%s: I failed to perform that lookup' % nick
def response(self, nick, args, kwargs):
try:
try:
user = args[0]
except:
user = None
if user is None or user == '':
doc = geturl(self.randomURL)
user = re.search('"currentJournal": "(.*?)"', doc).group(1)
url = urljoin(self.baseURL, '/users/%s/data/rss' % user)
feed = rssparser.parse(url)
# get latest entry and their homepage url
entry = feed['items'][0]['description']
page = feed['channel']['link']
# strip out html
entry = stripHTML(entry)
# detect unusual amounts of high ascii, probably russian journal
if isUTF8(entry):
return '%s: Russian LJ :(' % nick
# these can get absurdly long
entry = entry[:self.max]
return '%s: [%s] %s' % (nick, page, entry)
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return "%s: Couldn't load the page LJ returned D:" % nick
def get_lyrics_from_url(self, url):
page = geturl(url, referer=self.baseurl)
soup = BeautifulSoup(page)
content = soup.find('div', attrs={'id': 'content'})
[div.extract() for div in content.findAll('div')]
[link.extract() for link in content.findAll('a')]
[script.extract() for script in content.findAll('script')]
lines = [str(line) for line in content.contents]
data = ''.join(lines)
data = self._newline.sub('', data)
data = self._leadbreak.sub('', data)
data = self._endbreak.sub('', data)
lines = self._break.split(data)
verses = []
while True:
try:
i = lines.index('')
verse, lines = lines[:i], lines[i+1:]
verses.append(verse)
except ValueError:
verses.append(lines)
break
for i, verse in enumerate(verses):
verse = ' / '.join(verse)
verse = whitespace.sub(' ', verse)
verses[i] = verse
if self._spam in verses:
del verses[verses.index(self._spam)]
return verses
def response(self, nick, args, kwargs):
try:
page = geturl(self._baseurl)
try:
score = self._score_re.search(page).group(1)
dem = self._dem_re.search(score).groups()
gop = self._gop_re.search(score).groups()
# XXX diebold patch :D
#dem, gop = (dem[0], gop[1]), (gop[0], dem[1])
tie = None
try:
tie = self._tie_re.search(score).groups()
except AttributeError:
pass
except AttributeError:
raise Exception(u"couldn't parse page")
output = [self.colorize(u'blue', *dem), self.colorize(u'red', *gop)]
if tie:
output.append(self.colorize(u'white', *tie))
return u'%s: Projected Senate Seats 2010: %s' % (
nick, u', '.join(output))
except Exception, error:
log.warn(u'error in module %s' % self.__module__)
log.exception(error)
return u'%s: %s' % (nick, error)
def response(self, nick, args, kwargs):
word = args[0].lower()
try:
try:
num = int(args[1])
except:
num = 1
url = urljoin(self.base_url, word)
doc = geturl(url)
defs = self.re_defs.search(doc).group(1)
defs = self.re_newline.sub('', defs)
defs = self.re_def_break.split(defs)
if len(defs) > 1:
defs.pop(0)
if num > len(defs):
num = 1
definition = defs[num - 1]
definition = stripHTML(definition)
definition = self.header.sub('', definition)
return '%s: [%s/%s] %s' % (nick, num, len(defs), definition)
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return "%s: I couldn't look that up for some reason. D:" % nick
def response(self, nick, args, kwargs):
try:
try:
user = args[0]
except:
user = None
if user is None or user == '':
doc = geturl(self.randomURL)
user = re.search('"currentJournal": "(.*?)"', doc).group(1)
url = urljoin(self.baseURL, '/users/%s/data/rss' % user)
feed = rssparser.parse(url)
# get latest entry and their homepage url
entry = feed['items'][0]['description']
page = feed['channel']['link']
# strip out html
entry = stripHTML(entry)
# detect unusual amounts of high ascii, probably russian journal
if isUTF8(entry):
return '%s: Russian LJ :(' % nick
# these can get absurdly long
entry = entry[:self.max]
return '%s: [%s] %s' % (nick, page, entry)
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return "%s: Couldn't load the page LJ returned D:" % nick
def response(self, nick, args, kwargs):
word = args[0].lower()
try:
try:
num = int(args[1])
except:
num = 1
url = urljoin(self.base_url, word)
doc = geturl(url)
defs = self.re_defs.search(doc).group(1)
defs = self.re_newline.sub('', defs)
defs = self.re_def_break.split(defs)
if len(defs) > 1:
defs.pop(0)
if num > len(defs):
num = 1
definition = defs[num - 1]
definition = stripHTML(definition)
definition = self.header.sub('', definition)
return '%s: [%s/%s] %s' % (nick, num, len(defs), definition)
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return "%s: I couldn't look that up for some reason. D:" % nick
def time(self):
try:
doc = geturl(DoomsDay._url)
time = DoomsDay._re_time.search(doc).group(1)
return time
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return 'UNKNOWN'
def time(self):
try:
doc = geturl(DoomsDay._url)
time = DoomsDay._re_time.search(doc).group(1)
return time
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return 'UNKNOWN'
def time(self):
try:
doc = geturl(DoomsDay._url)
time = self._re_time.search(doc).group(1)
return time
except Exception, error:
log.warn(u'error in module %s' % self.__module__)
log.exception(error)
return u'UNKNOWN'
def response(self, nick, args, kwargs):
query = args[0]
try:
doc = geturl(self.search, opts={u'verbose': u'on', u'name': query})
drink = self.drink.search(doc).group(1)
url = urljoin(self.baseurl, drink)
doc = geturl(url)
title = self.title.search(doc).group(1)
ingredients = self.ingredients.findall(doc)
instructions = self.instructions.search(doc).group(1)
response = u'%s: %s - %s - %s' % (
nick, title, u', '.join(ingredients), instructions)
response = stripHTML(response)
return response
except Exception, error:
log.warn(u'error in module %s' % self.__module__)
log.exception(error)
return u"%s: Something ungood happened looking that up, sry" % nick
def response(self, nick, args, kwargs):
query = args[0]
try:
doc = geturl(self.search, opts={'verbose': 'on', 'name': query})
drink = self.drink.search(doc).group(1)
url = urljoin(self.baseurl, drink)
doc = geturl(url)
title = self.title.search(doc).group(1)
ingredients = self.ingredients.findall(doc)
instructions = self.instructions.search(doc).group(1)
response = '%s: %s - %s - %s' % (
nick, title, ', '.join(ingredients), instructions)
response = stripHTML(response)
return response
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return "%s: Something ungood happened looking that up, sry" % nick
def level(self):
try:
doc = geturl(Terror._url)
level = self._re_level.search(doc).group(1)
color = self._color_map[level.lower()]
return self.colorlib.get_color(color, text=level)
except Exception, error:
log.warn(u'error in module %s' % self.__module__)
log.exception(error)
return u'UNKNOWN'
def level(self):
try:
doc = geturl(Terror._url)
level = Terror._re_level.search(doc).group(1)
color = Terror._color_map[level.lower()]
return '\x03%s,1\x16\x16%s\x0f' % (color, level)
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return 'UNKNOWN'
def level(self):
try:
doc = geturl(Terror._url)
level = Terror._re_level.search(doc).group(1)
color = Terror._color_map[level.lower()]
return '\x03%s,1\x16\x16%s\x0f' % (color, level)
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return 'UNKNOWN'
def rate(self, movie):
try:
opts = dict(self.movie_opts)
opts['ts'] = movie
page = geturl(self.search, opts=opts)
movie = normalize(movie)
movies = self.result.findall(page)
movies = [(path, normalize(title)) for path, title in movies]
url = None
for path, title in movies:
if title == movie:
url = urljoin(self.baseurl, path)
break
if not url:
url = urljoin(self.baseurl, movies[0][0])
page = geturl(url, referer=self.search)
try:
critic_rating = self.critic_rating.search(page).group(1)
critic_rating = 'Critics: ' + critic_rating + '/100'
except:
critic_rating = None
try:
user_rating = self.user_rating.search(page).group(1)
user_rating = 'Users: ' + user_rating + '/10'
except:
user_rating = None
title = html_title.search(page).group(1)
title = title.replace(': Reviews', '')
response = 'Meta'
if normalize(title) != movie:
response += ' [%s]' % stripHTML(title)
ratings = [
i for i in (critic_rating, user_rating) if i is not None
]
ratings = ', '.join(ratings)
if ratings:
response += ' - %s' % ratings
return response
except:
return
def rate_rt(self, name):
"""Rating from rotten tomatoes"""
page = geturl(self.rt_search, {'search': name}, referer=self.rt_url)
soup = BeautifulSoup(page)
for table in soup.body('table'):
if table.caption.renderContents() == 'Movies':
break
else:
raise ValueError('no movies found in search results')
name = self.normalize(name)
for row in table.tbody('tr'):
link = row.a
if self.normalize(link.renderContents()) == name:
url = urljoin(self.rt_url, link['href'])
break
else:
raise ValueError('no exact matches')
soup = BeautifulSoup(geturl(url, referer=self.rt_search))
info = soup.body.find('div', 'movie_info_area')
return stripHTML(info.h1.renderContents()), info.a['title']
def get_text():
page = geturl(url)
soup = BeautifulSoup(page)
texts = soup.body.findAll('div', 'post_content')
text = random.choice(texts)
text = text.renderContents()
text = stripHTML(text)
text = text.splitlines()
text = [line.strip() for line in text]
text = [line for line in text if line]
text = u'\n'.join(text)
return text
def response(self, nick, args, kwargs):
try:
from_loc = self.get_location_data(args[0])
to_loc = self.get_location_data(args[1])
opts = {
'city': from_loc[0],
'main': from_loc[1],
'cross': from_loc[2],
}
page = geturl(self.second_url, opts=opts, referer=self.start_url)
origin = self.re_origin.search(page).group(1)
opts = {
'city': to_loc[0],
'main': to_loc[1],
'cross': to_loc[2],
'origin': origin,
'originCity': from_loc[0],
'originMain': from_loc[1],
'originCross': from_loc[2],
}
page = geturl(self.report_url, opts=opts, referer=self.second_url)
time, miles, table = self.re_trip.search(page).groups()
rows = self.re_rows.findall(table)[2:]
speeds = []
for row in rows:
try:
road, speed = self.re_cells.findall(row)[:2]
road = self.re_tags.sub('', road)
road = road.replace(' ', '')
speed = self.re_tags.sub('', speed)
speed = speed.replace(' or higher', '')
speeds.append('%s=%s' % (road, speed))
except:
continue
speeds = ', '.join(speeds)
return '%s: %s mins. (%s miles) [%s]' % (nick, time, miles, speeds)
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return '%s: %s' % (nick, self.error)
def rate(self, movie):
try:
opts = dict(self.movie_opts)
opts['ts'] = movie
page = geturl(self.search, opts=opts)
movie = normalize(movie)
movies = self.result.findall(page)
movies = [(path, normalize(title)) for path, title in movies]
url = None
for path, title in movies:
if title == movie:
url = urljoin(self.baseurl, path)
break
if not url:
url = urljoin(self.baseurl, movies[0][0])
page = geturl(url, referer=self.search)
try:
critic_rating = self.critic_rating.search(page).group(1)
critic_rating = 'Critics: ' + critic_rating + '/100'
except:
critic_rating = None
try:
user_rating = self.user_rating.search(page).group(1)
user_rating = 'Users: ' + user_rating + '/10'
except:
user_rating = None
title = html_title.search(page).group(1)
title = title.replace(': Reviews', '')
response = 'Meta'
if normalize(title) != movie:
response += ' [%s]' % stripHTML(title)
ratings = [i for i in (critic_rating, user_rating) if i is not None]
ratings = ', '.join(ratings)
if ratings:
response += ' - %s' % ratings
return response
except:
return
def response(self, nick, args, kwargs):
try:
from_loc = self.get_location_data(args[0])
to_loc = self.get_location_data(args[1])
opts = {
'city': from_loc[0],
'main': from_loc[1],
'cross': from_loc[2],
}
page = geturl(self.second_url, opts=opts, referer=self.start_url)
origin = self.re_origin.search(page).group(1)
opts = {
'city': to_loc[0],
'main': to_loc[1],
'cross': to_loc[2],
'origin': origin,
'originCity': from_loc[0],
'originMain': from_loc[1],
'originCross': from_loc[2],
}
page = geturl(self.report_url, opts=opts, referer=self.second_url)
time, miles, table = self.re_trip.search(page).groups()
rows = self.re_rows.findall(table)[2:]
speeds = []
for row in rows:
try:
road, speed = self.re_cells.findall(row)[:2]
road = self.re_tags.sub('', road)
road = road.replace(' ', '')
speed = self.re_tags.sub('', speed)
speed = speed.replace(' or higher', '')
speeds.append('%s=%s' % (road, speed))
except:
continue
speeds = ', '.join(speeds)
return '%s: %s mins. (%s miles) [%s]' % (nick, time, miles, speeds)
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return '%s: %s' % (nick, self.error)
def rate(self, movie):
"""Get the freshness rating of a movie"""
try:
opts = {'sitesearch': 'rt', 'search': movie}
page = geturl(self.search, opts=opts, referer=self.baseurl)
movie = normalize(movie)
title = html_title.search(page).group(1)
if title == self.search_title:
# normalize search results
movies = self.movies.findall(page)
movies = [(path, normalize(title)) for path, title in movies]
# look for exact match
url = None
for path, title in movies:
if title == movie:
url = urljoin(self.baseurl, path)
break
# no exact match, take first one
if not url:
url = urljoin(self.baseurl, movies[0][0])
# load page
page = geturl(url, referer=self.search)
# find rating
title = self.movie_title.search(page).group(1)
rating = self.rating.search(page).group(1)
# construct response
response = 'Freshness'
if normalize(title) != movie:
response += ' [%s]' % stripHTML(title)
response += ': %s' % rating
return response
except:
return
def rate(self, movie):
"""Get the freshness rating of a movie"""
try:
opts={'sitesearch': 'rt', 'search': movie}
page = geturl(self.search, opts=opts, referer=self.baseurl)
movie = normalize(movie)
title = html_title.search(page).group(1)
if title == self.search_title:
# normalize search results
movies = self.movies.findall(page)
movies = [(path, normalize(title)) for path, title in movies]
# look for exact match
url = None
for path, title in movies:
if title == movie:
url = urljoin(self.baseurl, path)
break
# no exact match, take first one
if not url:
url = urljoin(self.baseurl, movies[0][0])
# load page
page = geturl(url, referer=self.search)
# find rating
title = self.movie_title.search(page).group(1)
rating = self.rating.search(page).group(1)
# construct response
response = 'Freshness'
if normalize(title) != movie:
response += ' [%s]' % stripHTML(title)
response += ': %s' % rating
return response
except:
return
def rate(self, movie):
"""Get the rating for a movie"""
try:
page = geturl(self.search, opts={'s': 'all', 'q': movie})
movie = normalize(movie)
title = html_title.search(page).group(1)
if title == self.search_title:
# normalize search results
movies = self.movies.findall(page)
movies = [(y, z) for x, y, z in movies]
movies = [(path, normalize(title)) for path, title in movies]
movies = [(path, title) for path, title in movies if title]
# see if we can find an exact match
url = None
for path, title in movies:
if title == movie:
url = urljoin(self.baseurl, path)
break
# no exact match, take first option returned
if not url:
url = urljoin(self.baseurl, movies[0][0])
# load actual page & title
page = geturl(url, referer=self.search)
title = html_title.search(page).group(1)
# get rating and generate response
rating = self.rating.search(page).group(1)
response = 'IMDB'
if normalize(title) != movie:
response += ' [%s]' % stripHTML(title)
response += ': %s/10' % rating
return response
except:
return
def rate(self, movie):
"""Get the rating for a movie"""
try:
page = geturl(self.search, opts={'s': 'all', 'q': movie})
movie = normalize(movie)
title = html_title.search(page).group(1)
if title == self.search_title:
# normalize search results
movies = self.movies.findall(page)
movies = [(y, z) for x, y, z in movies]
movies = [(path, normalize(title)) for path, title in movies]
movies = [(path, title) for path, title in movies if title]
# see if we can find an exact match
url = None
for path, title in movies:
if title == movie:
url = urljoin(self.baseurl, path)
break
# no exact match, take first option returned
if not url:
url = urljoin(self.baseurl, movies[0][0])
# load actual page & title
page = geturl(url, referer=self.search)
title = html_title.search(page).group(1)
# get rating and generate response
rating = self.rating.search(page).group(1)
response = 'IMDB'
if normalize(title) != movie:
response += ' [%s]' % stripHTML(title)
response += ': %s/10' % rating
return response
except:
return
def bodycount(self):
try:
doc = geturl(self._bodycount_url)
data = self._bodycount_re.search(doc).group(1)
data = data.decode('ascii', 'replace')
data = stripHTML(data)
data = self._re_whitespace.sub(u' ', data)
data = data.strip()
return data
except Exception, error:
log.warn(u'error in module %s' % self.__module__)
log.exception(error)
return u'UNKNOWN'
def response(self, nick, args, kwargs):
query = args[0]
try:
doc = geturl(self.passage, opts={'search': query, 'version': 31})
response = self.verse.search(doc).group(1)
response = self.footnotes.sub('', response)
response = self.junk_html.sub('', response)
response = stripHTML(response)
response = response.strip()
return response[:self.max]
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return "%s: God didn't like that." % nick
def get_locations(self, reload=False):
if not self.locs or reload:
page = geturl(self.start_url)
self.locs = {}
c = m = None
for loc_type, loc in self.re_loc.findall(page):
if loc_type == u'c':
c = loc
self.locs.setdefault(c, {})
elif loc_type == u'm':
m = loc
self.locs[c].setdefault(m, [])
elif loc_type == u'x':
self.locs[c][m].append(loc)
return self.locs
def bodycount(self):
try:
doc = geturl(IraqWar._bodycount_url)
soup = BeautifulSoup(doc)
data = soup.find('td', attrs={'class': 'main-num'})
data = data.find('a')
data = str(data.contents[0])
data = stripHTML(data)
data = IraqWar._re_whitespace.sub(' ', data)
data = data.strip()
return data
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return 'UNKNOWN'
def get_locations(self, reload=False):
if not self.locs or reload:
page = geturl(self.start_url)
self.locs = {}
c = m = None
for loc_type, loc in self.re_loc.findall(page):
if loc_type == 'c':
c = loc
self.locs.setdefault(c, {})
elif loc_type == 'm':
m = loc
self.locs[c].setdefault(m, [])
elif loc_type == 'x':
self.locs[c][m].append(loc)
return self.locs
def bodycount(self):
try:
doc = geturl(IraqWar._bodycount_url)
soup = BeautifulSoup(doc)
data = soup.find('td', attrs={'class': 'main-num'})
data = data.find('a')
data = str(data.contents[0])
data = stripHTML(data)
data = IraqWar._re_whitespace.sub(' ', data)
data = data.strip()
return data
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return 'UNKNOWN'
def response(self, nick, args, kwargs):
try:
doc = geturl(self.random)
soup = BeautifulSoup(doc)
confs = soup.findAll('div', attrs={'class': 'content'})[3:]
conf = random.choice(confs)
conf = [str(p) for p in conf.findAll('p')]
conf = ' '.join(conf)
conf = stripHTML(conf)
conf = conf.strip()
return conf
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return '%s: I had some issues with that..' % nick
def response(self, nick, args, kwargs):
query = args[0]
try:
doc = geturl(self.passage, opts={'search': query, 'version': 31})
response = self.verse.search(doc).group(1)
response = self.footnotes.sub('', response)
response = self.junk_html.sub('', response)
response = stripHTML(response)
response = response.strip()
return response[:self.max]
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return "%s: God didn't like that." % nick
def response(self, nick, args, kwargs):
try:
doc = geturl(self.random)
soup = BeautifulSoup(doc)
confs = soup.findAll('div', attrs={'class': 'content'})[3:]
conf = random.choice(confs)
conf = [str(p) for p in conf.findAll('p')]
conf = ' '.join(conf)
conf = stripHTML(conf)
conf = conf.strip()
return conf
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return '%s: I had some issues with that..' % nick
def get_comment(self):
page = geturl(self.url)
# remove high ascii since this is going to IRC
page = self.utf8.sub('', page)
# create BeautifulSoup document tree
soup = BeautifulSoup(page)
table = soup.find('table')
rows = table.findAll('tr')
row = rows[1]
cells = row.findAll('td')
source = cells[1].string
comment = cells[2].string
author = cells[3].string
return '<%s@%s> %s' % (author, source, comment)
def get_comment(self):
page = geturl(self.url)
# remove high ascii since this is going to IRC
page = self.utf8.sub('', page)
# create BeautifulSoup document tree
soup = BeautifulSoup(page)
table = soup.find('table')
rows = table.findAll('tr')
row = rows[1]
cells = row.findAll('td')
source = cells[1].string
comment = cells[2].string
author = cells[3].string
return '<%s@%s> %s' % (author, source, comment)
def response(self, nick, args, kwargs):
try:
doc = geturl(self.random, add_headers={'Accept': '*/*'})
soup = BeautifulSoup(doc)
main = soup.find(u'div', attrs={u'id': u'main'})
confs = main.findAll(u'div', attrs={u'class': u'content'})
conf = random.choice(confs)
conf = [unicode(p) for p in conf.findAll(u'p')]
conf = u' '.join(conf)
conf = stripHTML(conf)
conf = conf.strip()
return conf
except Exception, error:
log.warn(u'error in module %s' % self.__module__)
log.exception(error)
return u'%s: I had some issues with that..' % nick
def response(self, nick, args, kwargs):
query = args[0]
if query is None or query == '':
url = self.random_url
else:
query = ' '.join(query.split())
query = query.replace(' ', '_')
query = urllib.quote(query) + '.html'
url = urljoin(self.baseurl, query)
try:
doc = geturl(url)
results = self.artfart.findall(doc)
result = random.choice(results)
title, art = result
art = stripHTML(art)
return '>>> %s <<<\n%s' % (title, art)
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return "%s: I had a problem with that, sorry." % nick
def response(self, nick, args, kwargs):
try:
source = self.sources[args[0]]
try:
query = args[1]
except:
query = None
try:
num = int(query)
query = None
except:
num = None
if num:
url = source.bynum.replace('num', str(num))
elif query:
url = source.search.replace('query', query)
else:
url = source.random
doc = geturl(url)
entries = source.entries.findall(doc)
if query:
entries = [entry for entry in entries if query in entry]
if len(entries) > 1:
entry = random.choice(entries)
else:
entry = entries[0]
return stripHTML(entry)
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return '%s: %s' % (nick, self._error)
def get_quote(self, symbol):
url = Yahoo._quote_url.replace('SYMBOL', symbol)
page = geturl(url)
soup = BeautifulSoup(page)
company = ' '.join([str(item) for item in soup.find('h1').contents])
company = stripHTML(company)
tables = soup.findAll('table')
table = tables[0]
rows = table.findAll('tr')
data = {}
current_value = 0.0
open_value = 0.0
for row in rows:
key, val = row.findAll('td')
key = str(key.contents[0])
if key == 'Change:':
try:
img = val.find('img')
alt = str(img['alt'])
val = alt + stripHTML(str(val.contents[0]))
except:
val = '0.00%'
elif key == 'Ask:':
continue
else:
val = stripHTML(str(val.contents[0]))
val = val.replace(',', '')
if Yahoo._isfloat.search(val):
val = float(val)
data[key] = val
if key == 'Last Trade:' or key == 'Index Value:':
current_value = val
elif key == 'Prev Close:':
open_value = val
# see if we can calculate percentage
try:
change = 100 * (current_value - open_value) / open_value
data['Change:'] += ' (%.2f%%)' % change
except:
pass
# try and colorize the change field
try:
if 'Up' in data['Change:']:
data['Change:'] = self._green + data['Change:'] + self._reset
elif 'Down' in data['Change:']:
data['Change:'] = self._red + data['Change:'] + self._reset
except:
pass
# build friendly output
output = []
for key, val in data.items():
if isinstance(val, float):
val = '%.2f' % val
output.append('%s %s' % (key, val))
return '%s - ' % company + ' | '.join(output)
def forecast(self, location):
page = geturl(url=self.search, opts={'query': location},
referer=self.baseurl)
soup = BeautifulSoup(page)
# disambiguation page
if 'Search Results' in str(soup):
table = soup.find('table', attrs={'class': 'boxB full'})
rows = table.findAll('tr')
results = []
match = None
for row in rows:
cells = row.findAll('td', attrs={'class': 'sortC'})
for cell in cells:
link = cell.find('a')
if link is None or 'addfav' in str(link['href']):
continue
city = str(link.contents[0])
href = urljoin(self.baseurl, str(link['href']))
results.append(city)
if city.lower() == location.lower():
match = urljoin(self.baseurl, href)
break
if match:
break
if match:
page = geturl(url=match)
soup = BeautifulSoup(page)
else:
return 'Multiple results found: %s' % ', '.join(results)
rss_url = soup.find('link', attrs=self._rss_link)['href']
rss = rssparser.parse(rss_url)
title = str(soup.find('h1').string).strip()
conditions = stripHTML(rss['items'][0]['description'])
fields = self._bar.split(conditions)
data = {}
for field in fields:
try:
key, val = self._keyval.search(field).groups()
data[key] = val
except:
pass
try:
temp = float(self._tempF.search(data['Temperature']).group(1))
blink = False
if temp < 0:
color = 6
elif temp >=0 and temp < 40:
color = 2
elif temp >= 40 and temp < 60:
color = 10
elif temp >= 60 and temp < 80:
color = 3
elif temp >= 80 and temp < 90:
color = 7
elif temp >= 90 and temp < 100:
color = 5
elif temp >= 100:
color = 5
blink = True
data['Temperature'] = '\x03%s\x16\x16%s\x0F' % (color,
data['Temperature'])
if blink:
data['Temperature'] = '\x1b[5m' + data['Temperature'] + \
'\x1b[0m'
except:
pass
output = []
for key, val in data.items():
line = '%s: %s' % (key, val)
output.append(line)
output = ' | '.join(output)
return '%s: %s' % (title, output)