def get_imdb(self, e, urlposted=False):
#reads title, rating, and movie description of movie titles
searchterm = e.input
if urlposted:
url = searchterm
else:
url = tools.google_url("site:imdb.com/title " + searchterm,
"imdb.com/title/tt\\d{7}/")
title = ""
if not url:
pass
elif url.find("imdb.com/title/tt") != -1:
try:
movietitle = ""
rating = ""
summary = ""
imdbid = re.search("tt\\d{7}", url)
imdburl = ('http://www.imdb.com/title/' + imdbid.group(0) + '/')
opener = urllib2.build_opener()
opener.addheaders = [('User-Agent', "Opera/9.10 (YourMom 8.0)"),
('Range', "bytes=0-40960")]
pagetmp = opener.open(imdburl)
page = BeautifulSoup(pagetmp.read(40960))
opener.close()
movietitle = tools.decode_htmlentities(
tools.remove_html_tags(str(page.find('title'))).replace(
" - IMDb", ""))
movietitle = movietitle.replace("IMDb - ", "")
movietitle = "Title: " + movietitle
if page.find(id="overview-top") != None:
page = page.find(id="overview-top").extract()
if page.find("div", "star-box-giga-star") != None:
rating = tools.remove_html_tags(
str(page.find("div", "star-box-giga-star").text))
rating = " - Rating: " + rating
if len(page.findAll('p')) == 2:
summary = str(page.findAll('p')[1])
removelink = re.compile(r'\<a.*\/a\>')
summary = removelink.sub('', summary)
summary = tools.remove_html_tags(summary)
summary = summary.replace('»', "")
summary = tools.decode_htmlentities(
summary.decode("utf-8", 'ignore'))
summary = re.sub("\&.*?\;", " ", summary)
summary = summary.replace("\n", " ")
summary = " - " + summary
title = movietitle + rating + summary
if not urlposted:
title = title + " [ %s ]" % url
e.output = title.encode('utf-8', 'ignore')
return e
except Exception as inst:
print "!imdb " + searchterm + ": " + str(inst)
return None
def advocate_beer(self, e):
query = e.input
# get the name, rating and style of a beer from beeradvocate.com
url = tools.google_url("site:beeradvocate.com " + query, "/beer/profile/[0-9]*?/[0-9]+")
# url = "http://beeradvocate.com/beer/profile/306/1212/"
socket.setdefaulttimeout(30)
try:
beerpage = urllib.request.urlopen(url).read().decode("utf-8")
except:
return None
socket.setdefaulttimeout(10)
titlestart = beerpage.find("<title>") + 7
titleend = beerpage.find(" - ", titlestart)
beertitle = beerpage[titlestart:titleend]
score_start_tag = '<span class="BAscore_big">'
score_end_tag = "Reviews</td>"
start = beerpage.find(score_start_tag) + len(score_start_tag)
score_line = beerpage[start : start + 100]
find_start_tag = '</span>\n<br><a href="/help/index?topic=ratings"><b>'
find_end_tag = "</b></a>\n<br>-<br>"
# print score_line
grade = score_line[0 : score_line.find(find_start_tag)]
# print "\n" + grade
grade_wording = score_line[score_line.find(find_start_tag) + len(find_start_tag) : score_line.rfind(find_end_tag)]
# print grade_wording
if grade_wording == "":
grade_wording = "N/A"
find_start_tag = find_end_tag
find_end_tag = "</td>"
num_reviews = score_line[score_line.rfind(find_start_tag) + len(find_start_tag) : score_line.find(find_end_tag)]
# print num_reviews
find_start_tag = "Style | ABV"
style_line = beerpage[beerpage.find(find_start_tag) : beerpage.find(find_start_tag) + 120]
find_start_tag = "><b>"
find_end_tag = "</b></a> | "
style = style_line[style_line.find(find_start_tag) + len(find_start_tag) : style_line.find(find_end_tag)]
find_start_tag = find_end_tag
find_end_tag = "% <a href"
abv = style_line[style_line.find(find_start_tag) + len(find_start_tag) : style_line.find(find_end_tag) + 1]
response_string = "Beer: %s - Grade: %s [%s, %s] Style: %s ABV: %s [ %s ]" % (
beertitle,
grade,
grade_wording,
num_reviews,
style,
abv,
tools.shorten_url(url),
)
e.output = response_string
return e
def get_metacritic(self, e):
url = tools.google_url("site:metacritic.com " + e.input, "www.metacritic.com/")
opener = urllib2.build_opener()
opener.addheaders = [('User-Agent',"Opera/9.10 (YourMom 8.0)")]
pagetmp = opener.open(url)
page = pagetmp.read()
opener.close()
page = BeautifulSoup(page)
try:
titleDiv = page.findAll('div',attrs={"class" : "product_title"})[0]
except:
return
title = titleDiv.a.string.encode("utf-8", 'ignore')
titleUrl = titleDiv.a['href']
if titleUrl.find("game/") > 0:
category = 'Game - '
category += titleDiv.findAll('span',attrs={"class" : "platform"})[0].a.string
elif titleUrl.find("movie/") > 0:
category = "Movie"
elif titleUrl.find("tv/") > 0:
category = "TV"
elif titleUrl.find("music/") > 0:
print "got here!"
category = "Music"
# band name is here, append it to title
title += " " + titleDiv.findAll('span',attrs={"class" : "band_name"})[0].string
if category:
category = "(%s) " % category
# declare these to avoid null reference
metaScore = ""
userScore = ""
try:
metaScoreDiv = page.findAll('div',attrs={"class" : "metascore_wrap highlight_metascore"})[0]
metaScore = metaScoreDiv.findAll('span',attrs={"class" : "score_value"})[0].string
metaDesc = metaScoreDiv.findAll('span',attrs={"class" : "desc"})[0].string
metaNum = metaScoreDiv.findAll('span',attrs={"class" : "count"})[0].a.span.string
except:
pass
try:
userScoreDiv = page.findAll('div',attrs={"class" : "userscore_wrap feature_userscore"})[0]
userScore = userScoreDiv.findAll('span',attrs={"class" : "score_value"})[0].string
userDesc = userScoreDiv.findAll('span',attrs={"class" : "desc"})[0].string
userNum = userScoreDiv.find('span',attrs={"class" : "count"}).a.string
except:
pass
if metaScore:
metaScore = "Metascore: " + metaScore
metaScore += " out of 100 - %s (%s Reviews)" % (metaDesc.strip(), metaNum.strip())
metaScore = "%s | " % metaScore
if userScore:
userScore = "User Score: " + userScore
userScore += " out of 10 - %s (%s)" % (userDesc.strip(), userNum.strip())
if metaScore or userScore:
e.output = "%s %s| %s%s" % (title, category, metaScore, userScore)
return e
def get_wiki(self, e, urlposted=False):
#read the first paragraph of a wikipedia article
searchterm = e.input
if urlposted:
url = searchterm
else:
if searchterm == "":
url = "http://en.wikipedia.org/wiki/Special:Random"
else:
url = tools.google_url("site:wikipedia.org " + searchterm,"wikipedia.org/wiki")
title = ""
if url and url.find("wikipedia.org/wiki/File:") != -1:
file_title=get_wiki_file_description(url)
if file_title:
e.output = file_title
return e
if url and url.find("wikipedia.org/wiki/") != -1:
try:
opener = urllib2.build_opener()
opener.addheaders = [('User-Agent',"Opera/9.10 (YourMom 8.0)")]
pagetmp = opener.open(url)
page = pagetmp.read()
url = pagetmp.geturl()
opener.close()
if url.find('#') != -1:
anchor = url.split('#')[1]
page = page[page.find('id="' + anchor):]
page = BeautifulSoup(page)
tables = page.findAll('table')
for table in tables:
table.extract()
page = page.findAll('p')
if str(page[0])[0:9] == '<p><span ':
page = unicode(page[1].extract())
else:
page = unicode(page[0].extract())
title = tools.remove_html_tags(re.search('(?s)\<p\>(.*?)\<\/p\>',page).group(1))
title = title.encode("utf-8", 'ignore')
title = title.replace("<","");
rembracket = re.compile(r'\[.*?\]')
title = rembracket.sub('',title)
#title = re.sub("\&.*?\;", " ", title)
title = title.replace("\n", " ")
title = tools.decode_htmlentities(title.decode("utf-8", 'ignore')).encode("utf-8", 'ignore')
title = title[0:420]
if title.rfind(".")!=-1:
title = title[0:title.rfind(".")+1]
if not urlposted:
url = tools.shorten_url(url)
title = (title.decode('utf-8', 'ignore') + " [ %s ]" % url).encode('utf-8', 'ignore')
except Exception as inst:
print "!wiki " + searchterm + " : " + str(inst)
title = tools.remove_html_tags(re.search('\<p\>(.*?\.) ',str(page)).group(1))
e.output = title
return e
def get_wiki(self, e, urlposted=False):
# read the first paragraph of a wikipedia article
searchterm = e.input
if urlposted:
url = searchterm
else:
if searchterm == "":
url = "http://en.wikipedia.org/wiki/Special:Random"
else:
url = tools.google_url("site:wikipedia.org " + searchterm, "wikipedia.org/wiki")
title = ""
if url and url.find("wikipedia.org/wiki/File:") != -1:
file_title = get_wiki_file_description(url)
if file_title:
e.output = file_title
return e
if url and url.find("wikipedia.org/wiki/") != -1:
try:
opener = urllib2.build_opener()
opener.addheaders = [("User-Agent", "Opera/9.10 (YourMom 8.0)")]
pagetmp = opener.open(url)
page = pagetmp.read()
url = pagetmp.geturl()
opener.close()
if url.find("#") != -1:
anchor = url.split("#")[1]
page = page[page.find('id="' + anchor) :]
page = BeautifulSoup(page)
tables = page.findAll("table")
for table in tables:
table.extract()
page = page.findAll("p")
if str(page[0])[0:9] == "<p><span ":
page = unicode(page[1].extract())
else:
page = unicode(page[0].extract())
title = tools.remove_html_tags(re.search("(?s)\<p\>(.*?)\<\/p\>", page).group(1))
title = title.encode("utf-8", "ignore")
title = title.replace("<", "")
rembracket = re.compile(r"\[.*?\]")
title = rembracket.sub("", title)
# title = re.sub("\&.*?\;", " ", title)
title = title.replace("\n", " ")
title = tools.decode_htmlentities(title.decode("utf-8", "ignore")).encode("utf-8", "ignore")
title = title[0:420]
if title.rfind(".") != -1:
title = title[0 : title.rfind(".") + 1]
if not urlposted:
url = tools.shorten_url(url)
title = (title.decode("utf-8", "ignore") + " [ %s ]" % url).encode("utf-8", "ignore")
except Exception as inst:
print "!wiki " + searchterm + " : " + str(inst)
title = tools.remove_html_tags(re.search("\<p\>(.*?\.) ", str(page)).group(1))
e.output = title
return e
def advocate_beer(self, e):
query = e.input
#get the name, rating and style of a beer from beeradvocate.com
url = tools.google_url("site:beeradvocate.com " + query,
"/beer/profile/[0-9]*/")
#url = "http://beeradvocate.com/beer/profile/306/1212/"
socket.setdefaulttimeout(30)
try:
beerpage = urllib2.urlopen(url).read() #.decode("ISO-8859-1")
except:
return None
socket.setdefaulttimeout(10)
titlestart = beerpage.find("<title>") + 7
titleend = beerpage.find(" - ", titlestart)
beertitle = beerpage[titlestart:titleend]
score_start_tag = '<span class="BAscore_big">'
score_end_tag = 'Reviews</td>'
start = beerpage.find(score_start_tag) + len(score_start_tag)
score_line = beerpage[start:start + 50]
find_start_tag = "</span>\n<br>"
find_end_tag = "<br>"
#print score_line
grade = score_line[0:score_line.find(find_start_tag)]
#print "\n" + grade
grade_wording = score_line[score_line.find(find_start_tag) +
len(find_start_tag):score_line.
rfind(find_end_tag)]
#print grade_wording
find_start_tag = find_end_tag
find_end_tag = "</td>"
num_reviews = score_line[score_line.rfind(find_start_tag) +
len(find_start_tag):score_line.find(find_end_tag)]
#print num_reviews
find_start_tag = "Style | ABV"
style_line = beerpage[beerpage.find(find_start_tag
):beerpage.find(find_start_tag) + 120]
find_start_tag = "><b>"
find_end_tag = "</b></a> | "
style = style_line[style_line.find(find_start_tag) +
len(find_start_tag):style_line.find(find_end_tag)]
find_start_tag = find_end_tag
find_end_tag = "% <a href"
abv = style_line[style_line.find(find_start_tag) +
len(find_start_tag):style_line.find(find_end_tag) + 1]
response_string = "Beer: %s - Grade: %s [%s, %s] Style: %s ABV: %s [ %s ]" % (
beertitle, grade, grade_wording, num_reviews, style, abv,
tools.shorten_url(url))
e.output = response_string
return e
