def extract_compounds(candidates):
"""Iterative extraction of valid compounds from list of split compound candidates."""
spell = SpellChecker(language='de')
compounds_preliminary = []
compounds_final = []
compounds_final_translations = []
for compound in candidates:
if spell[compound[1]] and spell[compound[2]] or duden_search.search(
compound[1]) and duden_search.search(compound[2]):
print("Assessing '{compound1}' - '{compound2}'...".format(
compound1=compound[1], compound2=compound[2]))
compounds_preliminary.append([compound[1], compound[2]])
print('\n\n\nTranslating compound segments...')
for compound in compounds_preliminary:
print("Translating '{word}'...".format(word=''.join(compound).title()))
compound_translations = []
for word in compound:
compound_translations.append(google_search.search(word))
if compound_translations[0] and compound_translations[1]:
compounds_final.append(compound)
compounds_final_translations.append(compound_translations)
compounds_dictionary = dict(
zip([
''.join([segments[0], segments[1].lower()])
for segments in compounds_final
], compounds_final_translations))
print('\n\n\nExtracted compounds:')
for i in compounds_dictionary.items():
print(i)
return compounds_dictionary
def retrive_from_google(query, num_pages=5):
"""
Search Google for a keyword and retrieve urls of search results.
Keyword arguments:
query : Query to search on Google
num_pages : Number of urls to return
Return:
results : List of urls
"""
print('Searching google for "', query, '" ...')
import google_search as google
import os
response = google.search(query, stop=num_pages)
results = {}
cache = [
''.join(fname.split('.')[:-1])
for fname in os.listdir('google_retrieved')
]
pbar = ProgressBar()
for link in pbar(response):
fname = ''.join(link.split('/'))
if fname not in cache:
text = scrape_data(link)
cache.append(link)
open(os.path.join('google_retrieved', fname), 'w').write(text)
return results
def searchGoogle (productName, searchTerm, resultAmount):
now = datetime.now()
todayTime = '%02d %02d' % (datetime.time(now).hour,datetime.time(now).minute)
todayDate = '%04d %02d %02d' % (datetime.date(now).year,datetime.date(now).month,datetime.date(now).day)
#productName = 'archetype'
#searchTerm = 'archetype vfx pipeline nederhorst torrent'
urlList = []
for url in search (searchTerm,stop=resultAmount):
urlList.append(url)
accetableSites = [
'amazon.com',
'thegnomonworkshop.com',
'cgchannel.com',
'vray.info',
'thefoundry.co.uk',
'youtube.com',
'vimeo.com',
'pixologic.com',
'twitter.com',
'facebook.com',
'3dtotal.com',
'tutsplus.com',
'gnomonschool.com',
'chillingeffects.org',
'deviantart.com'
]
outData = {
'product':
{
'name':productName,
'searchterm':searchTerm,
'date':todayDate,
'time':todayTime
}
}
illegalURLs = []
for url in urlList:
foundIllegalSite = False
for goodSite in accetableSites:
if goodSite.lower() in url.lower():
break
else:
illegalURLs.append(url)
logger.info('Found : %s' % url)
#illegalURLs = [targ for targ in urlList if any(re.search(r'(?!\b{})'.format(goodSite), targ, re.I) for goodSite in accetableSites)]
#print matches
outData['product']['sites']= illegalURLs
return outData
def __init__(self, term):
url = ''
urls = g.search(term)
for i in urls:
if 'product-reviews' in i:
url = i
self.filt = []
self.d = {}
page = requests.get(url).text
lst = amazon_scraper.get_page_reviews(page)
self.calc_freq(lst[0])
self.filt = self.generate_list()
def __init__(self, term):
url = ''
urls = g.search(term)
for i in urls:
if 'product-reviews' in i:
url = i
self.filt = []
self.d = {}
page = requests.get(url).text
lst = amazon_scraper.get_page_reviews(page)
self.calc_freq(lst[0])
self.filt = self.generate_list()
async def on_message(message):
if message.author == client.user:
return
if message.content == 'hi':
return await message.channel.send("<@{0}> Hey".format(
message.author.id))
if message.content.startswith('!google'):
search_text = message.content.split("!google")
if len(search_text) > 1:
persistent_store.add_search(search_text[1], message.author.id)
search_response = google_search.search(search_text[1])
return await message.channel.send("<@{0}> {1}".format(
message.author.id, search_response))
if message.content.startswith('!recent'):
search_text = message.content.split("!recent")
if len(search_text) > 1:
recent_response = persistent_store.find_search_term(
search_text[1], message.author.id)
return await message.channel.send("<@{0}> {1}".format(
message.author.id, recent_response))
def get_message(bot, update):
update.message.reply_text("got text")
word = update.message.text
text = search(word)
update.message.reply_text(text)
def getResponse(msg, ints, intents_json):
tag = ints[0]['intent']
list_of_intents = intents_json['intents']
for i in list_of_intents:
if (tag == "lyrics"):
response = random.choice(i['responses'])
ChatLog.insert(END, "Chatty: " + response + '\n\n')
content = song_lyrics(msg)
if type(content) == str:
ChatLog.insert(END, "Chatty: " + content + '\n\n')
return "here are you results."
elif type(content) == tuple:
for data in content:
ChatLog.insert(END, "Chatty: " + data + '\n\n')
return "here are you results."
elif (tag == "music"):
content = music(msg)
if type(content) == str:
ChatLog.insert(END, "Chatty: " + content + '\n\n')
elif type(content) == tuple:
title, flink, vlink = content
def audio_link():
# import vlc
# p = vlc.MediaPlayer(flink)
# p.play()
webbrowser.open_new(flink)
def video_link():
webbrowser.open_new(vlink)
ChatLog.insert(END, "Chatty: " + title + '\n\n')
ChatLog.insert(END, "Audio link: " + flink + '\n\n',
hyperlink.add(audio_link))
ChatLog.insert(END, "Video link: " + vlink + '\n\n',
hyperlink.add(video_link))
return "here are you results."
elif (tag == 'news'):
title, description, short_link = get_news()
for i in range(5):
def news_link():
webbrowser.open_new(short_link[i])
ChatLog.insert(END,
"News: " + title[i] + ' - \n' + description[i])
ChatLog.insert(END, "\nclick here for brief.\n\n",
hyperlink.add(news_link))
return "here are your result."
elif (tag == 'weather'):
weather_report = get_weather_data(msg)
ChatLog.insert(END, "Chatty: " + weather_report + '\n\n')
return "here are your results"
elif (tag == 'quotations'):
quoto = get_quotations()
ChatLog.insert(END, "Chatty: " + quoto + '\n\n')
return "here are your result"
elif (tag == 'search'):
search(msg)
return "open your browser if it's not opened automatically"
elif (i['tag'] == tag):
result = random.choice(i['responses'])
return result
if (choice == 1):
request = input('you: ') # user requesting here with a message
else:
request = listencommand()
response = bot.get_response(request) #bot responding to their request
# action based on response of bot
if (response == "bye"):
#
strrespo = str(response) + " Happy to help you"
print('Bot: ', strrespo) # printing the response of Bot
speak(strrespo)
break
elif (request == google + request[6:]):
speak("here we go")
google_search.search(request[6:])
elif (response == "google on" or response == "google about"
or response == "google it" or response == "google this"
or response == "search on google"):
#
print(response)
strres = str(response)
strlen = len(strres)
finalstr = request[strlen:]
speak("here we go")
google_search.search(finalstr[0:])
elif (response == "wiki about" or response == "wikipedia about"
or response == "tell me about" or response == "tell me"
or response == "who is" or response == "what is a"
or response == "what is an" or response == "wikipedia"
or response == "wiki on" or response == "what is"):
def start(cmd):
if "find meaning" in cmd or ("tell" in cmd and "meaning" in cmd) or ("find" in cmd and "meaning" in cmd):
the_voice.say_and_print("Say the word to get meaning")
a = the_voice.listening()
if a is None:
print("Sorry, didn't get you!")
print("Please say the name of file to search, or \"CANCEL\" to cancel")
while a is not None:
a = the_voice.listening()
a = a.lower()
if a == "cancel":
return 1
a = a.lower()
the_voice.say_and_print("Finding meaning...")
tell_meaning.meaning(a)
return 1
elif "search google" in cmd or "find on google" in cmd or ("search" in cmd and "net" in cmd) or (
"search" in cmd and "google" in cmd):
the_voice.say_and_print("What do you want to search?")
a = the_voice.listening()
if a is None:
print("Sorry, didn't get you!")
print("Please say the name of file to search, or \"CANCEL\" to cancel")
while a is not None:
a = the_voice.listening()
a = a.lower()
if a == "cancel":
return 1
a = a.lower()
the_voice.say_and_print("Searching...")
google_search.search(a)
return 1
elif "open site" in cmd or ("open" in cmd and "site" in cmd):
the_voice.say_and_print("which site do you want to open?")
a = the_voice.listening()
if a is None:
print("Sorry, didn't get you!")
print("Please say the name of file to search, or \"CANCEL\" to cancel")
while a is not None:
a = the_voice.listening()
a = a.lower()
if a == "cancel":
return 1
a = a.lower()
the_voice.say_and_print("Opening Site...")
frequent_site.site(a)
return 1
elif "set reminder" in cmd or ("set" in cmd and "reminder" in cmd):
the_voice.say_and_print("What shall I remind you about?")
a = the_voice.listening()
if a is None:
print("Sorry, didn't get you!")
print("Please say the name of file to search, or \"CANCEL\" to cancel")
while a is not None:
a = the_voice.listening()
a = a.lower()
if a == "cancel":
return 1
a = a.lower()
the_voice.say_and_print("Setting reminder...")
the_voice.say_and_print("In how many seconds you want to be reminded?")
while True:
temp = the_voice.listening()
try:
b = int(temp)
break
except:
if temp.lower() == "cancel":
return 1
the_voice.say_and_print("Please tell after how many seconds you want to be reminded, or say \"CANCEL\" to cancel")
set_reminder.task(a, b)
return 1
elif "movies nearby" in cmd or "search movies" in cmd or ("movies" in cmd and "nearby" in cmd) or (
"search" in cmd and "movies" in cmd):
the_voice.say_and_print("Showing Movies Near by...")
movies_nearby.movies("movies nearby")
return 1
elif "plan travel" in cmd or ("plan" in cmd and "travel" in cmd) or ("book" in cmd and "hotel" in cmd) or (
"book" in cmd and "flight" in cmd) or ("book" in cmd and "train" in cmd) or (
"book" in cmd and "bus" in cmd):
the_voice.say_and_print("Plan Your Travel")
plan_travel.travel()
return 1
elif "latest updates" in cmd or ("latest" in cmd and "updates" in cmd) or ("tell" in cmd and "news" in cmd):
the_voice.say_and_print("Showing Latest Feeds...")
news_update.news()
return 1
elif "cricket score" in cmd or ("cricket" in cmd and "score" in cmd) or ("live" in cmd and "cricket" in cmd):
the_voice.say_and_print("Showing Cricket Score...")
cricket_score.score()
return 1
return 0
bot.get_response(request)) #bot responding to their request
strrespo = response + ", Happy to help you"
print('Bot:', strrespo) # printing the response of Bot
speak(strrespo)
break
elif ("#wiki" in request):
speak("sure")
reqind = request.find("#wiki")
response = wiki_search.wiki(request[reqind + 5:])
print("Bot:", response)
speak(response)
elif ("#google" in request):
speak("sure")
speak("here we go")
reqind = request.find("#google ")
response = google_search.search(request[reqind + 7:])
print("check it out please")
speak("check it out please")
elif ("#humidity" in request):
reqind = request.find("#humidity ")
fun_humidity(reqind + 10)
elif ("#temp " in request):
reqind = request.find("#temp ")
fun_temp(reqind + 5)
elif ("#weather " in request):
reqind = request.find("#weather ")
fun_complete_weather(reqind + 9)
elif ("#weather_status " in request):
reqind = request.find("#weather_status ")
fun_weather(reqind + 16)
elif ("#wind_speed " in request):
def main(self):
if self.incoming_data_file:
queries = IO.read_list_of_lists_from_file_usung_csv_v1(self.incoming_data_file)
IO.save_text_to_file('[', self.output_data_file)
elif self.search_domain:
print self.search_domain
print "Opps!!! Stopped ... Not implemented for domain search yet"
return
elif self.search_hotel_name:
#print self.search_hotel_name
search_query = [ 1, self.search_hotel_name , '']
if self.search_hotel_location:
search_query[2] = self.search_hotel_location
queries = []
queries.append(search_query)
else:
logging.error('Something went Wrong, Cant Proceed Further.Stop')
return
for query_list in queries:
try:
try:
sr_no = query_list[0]
except:
sr_no = None
try:
hotel_name = query_list[1]
except:
hotel_name = None
try:
hotel_location = query_list[2]
except:
hotel_location = None
if not hotel_name:
continue
#self.input_search_hotel_name = query_list[0]
query_dict = {'Hotel_Name': hotel_name, 'Hotel_Location': hotel_location, 'Sr_No': sr_no}
logging.info('To Find : {}'.format(query_dict))
domain = 'http://www.tripadvisor.com/Hotel_Review-'
params = {'lang': 'en', 'tld': 'com'}
params['pause'] = 2.0
params['stop']= 1
params['only_standard']= True
params['start']= 0
params['num']= 1
query = 'Site : {} {} {}'.format(str(self.base_url),hotel_name,hotel_location)
#print query
#do bing search for hotel
links_to_hotels = self.get_links_bing_search(query_dict)
if not links_to_hotels:
# if return No Url Then go For google Search
links_to_hotels = self.get_links_google_search(query_dict)
if not links_to_hotels:
#last try, if return No Url Then go For google Search With Proxy
logging.info("IN Google SEARCH With Proxy")
links_to_hotels = [url for url in search(query, **params)]
logging.info('Parse Link To Soup : {} '.format(links_to_hotels))
hotel_data =self.extract_trip_advisor_details(query_dict,links_to_hotels)
self.results = hotel_data
if self.incoming_data_file:
self.save_item_to_file(hotel_data,self.output_data_file)
except Exception as e:
logging.error('IN MAIN :: {} '.format(str(e)))
continue
time.sleep(3)
if self.incoming_data_file:
IO.save_text_to_file(']', self.output_data_file) # close json list