def response(self, nick, args, kwargs):
try:
feed = rssparser.parse(self.rssurl)
# get latest entry and their homepage url
title = feed['items'][0]['title'].split()
offer = ' '.join(title[:-2])
try:
price = "$%.2f" % title[-1]
except:
price = ''
longdescription = feed['items'][0]['description']
page = feed['items'][0]['link']
# strip out html
longdescription = stripHTML(longdescription).strip()
# these can get absurdly long
if longdescription > self.max:
longdescription = longdescription[:self.max-4] + ' ...'
return '%s: %s\n[%s]\n%s' % (offer, price, page, longdescription)
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return "%s: Couldn't load the page woot returned D:" % nick
def response(self, nick, args, kwargs):
try:
feed = rssparser.parse(self.rssurl)
# get latest entry and their homepage url
title = feed['items'][0]['title'].split()
offer = ' '.join(title[:-2])
try:
price = "$%.2f" % title[-1]
except:
price = ''
longdescription = feed['items'][0]['description']
page = feed['items'][0]['link']
# strip out html
longdescription = stripHTML(longdescription).strip()
# these can get absurdly long
if longdescription > self.max:
longdescription = longdescription[:self.max - 4] + ' ...'
return '%s: %s\n[%s]\n%s' % (offer, price, page, longdescription)
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return "%s: Couldn't load the page woot returned 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 parse_email(self, payload):
try:
message = email.message_from_string(payload)
for part in message.walk():
if part.get_content_maintype() == 'multipart':
continue
mime_type = part.get_content_type()
body = part.get_payload(decode=True)
if mime_type == 'text/plain':
break
elif mime_type == 'text/html':
body = stripHTML(body)
break
for spam in self._spams:
if spam in body:
body = body.replace(spam, '')
body = body.strip()
cleaned = []
for line in body.splitlines():
line = line.strip()
if not len(line) or line.startswith('>'):
continue
elif self._quoted.search(line) or line == self._sig:
break
else:
cleaned.append(line)
body = ' '.join(cleaned)
except Exception, e:
raise ParsingError, "couldn't parse payload: %s" % e
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):
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 normalize(name):
name = stripHTML(name)
name = badchars.sub('', name)
name = name.lower()
name = name.strip()
name = whitespace.sub(' ', name)
return name
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 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):
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:
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 parse_email(self, payload):
try:
message = email.message_from_string(payload)
for part in message.walk():
if part.get_content_maintype() == 'multipart':
continue
mime_type = part.get_content_type()
body = part.get_payload(decode=True)
if mime_type == 'text/plain':
break
elif mime_type == 'text/html':
body = stripHTML(body)
break
for spam in self._spams:
if spam in body:
body = body.replace(spam, '')
body = body.strip()
cleaned = []
for line in body.splitlines():
line = line.strip()
if not len(line) or line.startswith('>'):
continue
elif self._quoted.search(line) or line == self._sig:
break
else:
cleaned.append(line)
body = ' '.join(cleaned)
except Exception, e:
raise ParsingError, "couldn't parse payload: %s" % e
def response(self, nick, args, kwargs):
try:
item = feedparser.parse(self.url).entries[0]
body = stripHTML(item.description).strip()
return u' | '.join([item.link, body, item.updated])
except Exception, error:
log.warn(u'error in module %s' % self.__module__)
log.exception(error)
return u'%s: %s' % (nick, error)
def lookup(self, term, idx=1):
"""Lookup term in dictionary"""
url = urljoin(self.define_url, quote(term.lower()))
soup = getsoup(url, referer=self.base_url)
for br in soup('br'):
br.extract()
val = stripHTML(soup.renderContents().decode('utf-8'))
val = val.replace(u'\xa0', ' ').replace('\n', ' ')
return self.whitespace_re.sub(' ', val).strip()
def normalize(name):
"""Normalize a movie title for easy comparison"""
name = stripHTML(name)
name = year.sub('', name)
name = badchars.sub(' ', name)
name = name.lower()
name = name.strip()
name = whitespace.sub(' ', name)
return name
def normalize(name):
"""Normalize a movie title for easy comparison"""
name = stripHTML(name)
name = year.sub('', name)
name = badchars.sub(' ', name)
name = name.lower()
name = name.strip()
name = whitespace.sub(' ', name)
return name
class Main(Base):
def __init__(self, madcow):
self.madcow = madcow
self.enabled = madcow.config.twitter.enabled
self.frequency = madcow.config.twitter.updatefreq
self.output = madcow.config.twitter.channel
self.api = twitter.Api()
self.api.SetCache(None) # this fills up /tmp :(
self.api.SetUserAgent(
'Mozilla/4.0 (compatible; MSIE 7.0; Windows NT 6.0)')
self.api.SetCredentials(self.madcow.config.twitter.username,
self.madcow.config.twitter.password)
self.__updatelast()
def __updatelast(self):
"""Updates timestamp of last update."""
self.lastupdate = time.gmtime()
def __get_update_str(self):
return time.strftime("%a, %d %b %Y %X GMT", self.lastupdate)
def response(self, *args):
"""This is called by madcow, should return a string or None"""
try:
log.debug('getting tweets...')
tweets = self.api.GetFriendsTimeline(since=self.__get_update_str())
except Exception, e:
try:
if e.code == 304:
log.debug('no new tweets')
return
except:
pass
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return
log.debug('found %s tweets, parsing')
lines = []
for t in reversed(tweets):
if time.localtime(
t.GetCreatedAtInSeconds()
) < self.lastupdate: # twitter fails sometimes, so we do our own filter..
print "ignoring old tweet with timestamp %s (TWITTER SUCKS)" % t.created_at
continue
line = ">> tweet from %s: %s <<" % (t.user.screen_name,
stripHTML(t.text))
lines.append(line)
self.__updatelast()
if lines:
return "\n".join(lines)
else:
return None
def receiveMessage(self, user, multiparts, flags):
req = Request(message=stripHTML(multiparts[0][0]))
req.nick = user.name
req.channel = 'AIM'
req.private = True
req.addressed = True
req.aim = self
log.info('[AIM] <%s> %s' % (req.nick, req.message))
self.bot.checkAddressing(req)
self.bot.process_message(req)
def extract_quote(self, obj):
li = obj.find(u'li')
contents = li.contents
contents = [unicode(part) for part in contents]
quote = u' '.join(contents)
quote = stripHTML(quote)
quote = _linebreak.sub(u' ', quote)
quote = _whitespace.sub(u' ', quote)
quote = quote.strip()
return quote
def receiveMessage(self, user, multiparts, flags):
req = Request(message=stripHTML(multiparts[0][0]))
req.nick = user.name
req.channel = 'AIM'
req.private = True
req.addressed = True
req.aim = self
log.info('[AIM] <%s> %s' % (req.nick, req.message))
self.bot.checkAddressing(req)
self.bot.process_message(req)
def response(self, nick, args, kwargs):
query = args[0]
try:
if not query or query == 'headline':
url = self._world_url
else:
url = self._search_url + urllib.quote(query)
feed = rssparser.parse(url)
item = feed['items'][0]
url = item['link']
title = stripHTML(item['title'])
sum = stripHTML(item['description'])
return '\n'.join((url, title, sum))
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return '%s: %s' % (nick, self._error)
def response(self, nick, args, kwargs):
query = args[0]
try:
if not query or query == 'headline':
url = self._world_url
else:
url = self._search_url + urllib.quote(query)
feed = rssparser.parse(url)
item = feed['items'][0]
url = item['link']
title = stripHTML(item['title'])
sum = stripHTML(item['description'])
return '\n'.join((url, title, sum))
except Exception, e:
log.warn('error in %s: %s' % (self.__module__, e))
log.exception(e)
return '%s: %s' % (nick, self._error)
def normalize(self, name):
"""Normalize a movie title for easy comparison"""
name = stripHTML(name)
name = self.year_re.sub('', name) # strip trailing year
name = self.rev_article_re.sub(r'\2 \1', name) # Movie, The = The Movie
name = self.articles_re.sub('', name) # strip leading the/an
name = self.badchars_re.sub(' ', name) # only allow alnum
name = name.lower() # lowercase only
name = name.strip() # strip whitespace
name = self.whitespace_re.sub(' ', name) # compress whitespace
return name
def post(self, url, tags):
try:
html = self.ua.open(url, size=2048)
title = stripHTML(self.title.search(html).group(1))
except AttributeError:
title = url
opts = {u'url': url,
u'description': title,
u'tags': u' '.join(tags),
u'replace': u'no',
u'shared': u'yes'}
self.ua.open(self.posturl, opts=opts)
def response(self, nick, args, kwargs):
try:
soup = getsoup(self.spec_url % int(args[0]) if args[0] else self.rand_url)
soup.find('div', id='submit').extract()
post = soup.body.find('div', 'post')
return u'%s: (%d) %s' % (nick, int(post.find('a', 'fmllink')['href'].split('/')[-1]),
stripHTML(' '.join(link.renderContents()
for link in post('a', 'fmllink')).decode('utf-8', 'ignore')))
except Exception, error:
log.warn(u'error in module %s' % self.__module__)
log.exception(error)
return u'%s: Today I couldn\'t seem to access fmylife.com.. FML' % nick
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:
opts = {'hl': 'en', 'aq': 'f', 'safe': 'off', 'q': args[0]}
soup = getsoup(self.google_search, opts, referer=self.google_url)
a = soup.body.find('a', 'spell')
if a:
res = stripHTML(a.renderContents().decode('utf-8', 'ignore'))
else:
res = u'spelled correctly'
except Exception, error:
log.warn('error in module %s' % self.__module__)
log.exception(error)
res = u'I had trouble with that'
def post(self, url, tags):
try:
html = self.ua.openurl(url, size=2048)
title = stripHTML(self.title.search(html).group(1))
except:
title = url
opts = {
'url': url,
'description': title,
'tags': ' '.join(tags),
'replace': 'no',
'shared': 'yes',
}
self.ua.openurl(self.posturl, opts=opts)
def post(self, url, tags):
try:
html = self.ua.openurl(url, size=2048)
title = stripHTML(self.title.search(html).group(1))
except:
title = url
opts = {
'url': url,
'description': title,
'tags': ' '.join(tags),
'replace': 'no',
'shared': 'yes',
}
self.ua.openurl(self.posturl, opts=opts)
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 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):
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 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, 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 get_summary(self, query):
soup, title = self.get_soup(query)
# check if this is a disambiguation page, if so construct special page
# there isn't a consistent style guide, so we just try to do the
# most common format (ordered list of links). if this fails, return
# a friendly failure for now
if soup.find(u'div', attrs={u'id': u'disambig'}):
try:
summary = u'%s (Disambiguation) - ' % title
for link in soup.find(u'ul').findAll(u'a'):
title = unicode(link[u'title']).strip()
if len(summary) + len(title) + 2 > self.summary_size:
break
if not summary.endswith(u' '):
summary += u', '
summary += title
except:
summary = u'Fancy, unsupported disambiguation page!'
return summary
# massage into plain text by concatenating paragraphs
content = []
for para in soup.findAll(u'p'):
content.append(unicode(para))
content = u' '.join(content)
# clean up rendered text
content = stripHTML(content) # strip markup
content = Wiki._citations.sub(u'', content) # remove citations
content = Wiki._parens.sub(u'', content) # remove parentheticals
content = Wiki._whitespace.sub(u' ', content) # compress whitespace
content = Wiki._fix_punc.sub(r'\1', content) # fix punctuation
content = content.strip() # strip whitespace
# search error
if title == self.error:
return u'No results found for "%s"' % query
# generate summary by adding as many sentences as possible before limit
summary = u'%s -' % title
for sentence in Wiki._sentence.findall(content):
if len(summary) + 1 + len(sentence) > self.summary_size:
break
summary += u' %s' % sentence
return summary
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 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):
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:
fail = BeautifulSoup(geturl(self.url)).h1
return self.spaces_re.sub(
" ",
stripHTML(
u"%s: %s: %s %s: %s"
% (
nick,
self.col("red", text="FAIL"),
self.fail_re.search(fail.renderContents()).group(1),
self.col("green", text="FIX"),
self.fail_re.search(fail.findNext("h1").renderContents()).group(1),
)
),
)
except Exception, error:
log.warn("error in module %s" % self.__module__)
log.exception(error)
return u"%s: Too much fail for technobabble" % (nick, error)
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 response(self, nick, args, kwargs):
query = args[0]
if query is None or query == u'':
url = self.random_url
else:
query = u' '.join(query.split())
query = query.replace(u' ', u'_')
query = urllib.quote(query) + u'.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 u'>>> %s <<<\n%s' % (title, art)
except Exception, error:
log.warn(u'error in module %s' % self.__module__)
log.exception(error)
return u"%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 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 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)
