Python TextBlob.translate方法代码示例

# 需要导入模块: from textblob import TextBlob [as 别名]
# 或者: from textblob.TextBlob import translate [as 别名]
def matchRhyme(word1,word2):
    #str1 = "tekst"
    #word1+="टेक्स्ट"
    str1 = ""
    str2 = ""

    word1+= "टेक्स्ट"
    word2+= "टेक्स्ट"

    str1 += " " + word1
    str2 += " " + word2

    hindi_blob1 = TextBlob(str1)
    hindi_blob2 = TextBlob(str2)

    transliteratedtxt1 = hindi_blob1.translate(from_lang="hi", to='en')
    transliteratedtxt1=transliteratedtxt1.substring[:-5]
    transliteratedtxt2 = hindi_blob2.translate(from_lang="hi", to='en')
    transliteratedtxt2= transliteratedtxt2.substring[:-5]

    word1Index= len(transliteratedtxt1)
    word2Index= len(transliteratedtxt2)
    ##Matcing last charater if they are same!!
    if (transliteratedtxt1[word1Index-1] == transliteratedtxt2[word2Index-1]):

        #rhymeMeter=3;
        ##Matching if second Last character is any of the Matras!!
        if ( ((transliteratedtxt1[word1Index-2]=='a') and (transliteratedtxt2[word2Index-2]=='a')) or ((transliteratedtxt1[word1Index-2]=='e') and (transliteratedtxt2[word2Index-2]=='e'))or ((transliteratedtxt1[word1Index-2]=='o') and (transliteratedtxt2[word2Index-2]=='o')) or ((transliteratedtxt1[word1Index-2]=='i') and (transliteratedtxt2[word2Index-2]=='i')) or ((transliteratedtxt1[word1Index-2]=='u') and (transliteratedtxt2[word2Index-2]=='u')) ):
            rhymeMeter=5
        else:
            if(transliteratedtxt1[word1Index-2]!=transliteratedtxt1[word1Index-2]):
                rhymeMeter=4
    return rhymeMeter

# 需要导入模块: from textblob import TextBlob [as 别名]
# 或者: from textblob.TextBlob import translate [as 别名]
    def scrape(self,links=[],ads=True,translator=False):
        responses = []
        values = {}
        data = []
        
        if ads:
            for link in links:
                r = requests.get(link)
                responses.append(r)
        else:
            for link in links:
                r = requests.get(link)
                text = unidecode(r.text)
                html = lxml.html.fromstring(text)

                links = html.xpath("//div[@class='cat']/a/@href")
                for link in links:
                    if len(self.base_urls) > 1 or len(self.base_urls[0]) > 3:
                        time.sleep(random.randint(5,27))
                    try:
                        responses.append(requests.get(link))
                        print link
                    except requests.exceptions.ConnectionError:
                        print "hitting connection error"
                        continue

        for r in responses:
            text = r.text
            html = lxml.html.fromstring(text)
            values["title"] = html.xpath("//div[@id='postingTitle']/a/h1")[0].text_content()
            values["link"] = unidecode(r.url)
            values["new_keywords"] = []
            try:
                values["images"] = html.xpath("//img/@src")
            except IndexError:
                values["images"] = "weird index error"
            pre_decode_text = html.xpath("//div[@class='postingBody']")[0].text_content().replace("\n","").replace("\r","")  
            values["text_body"] = pre_decode_text 
            try:
                values["posted_at"] = html.xpath("//div[class='adInfo']")[0].text_content().replace("\n"," ").replace("\r","")
            except IndexError:
                values["posted_at"] = "not given"
            values["scraped_at"] = str(datetime.datetime.now())
            body_blob = TextBlob(values["text_body"])
            title_blob = TextBlob(values["title"])
            values["language"] = body_blob.detect_language() #requires the internet - makes use of google translate api
            values["polarity"] = body_blob.polarity
            values["subjectivity"] = body_blob.sentiment[1]
            if values["language"] != "en" and not translator:
                values["translated_body"] = body_blob.translate(from_lang="es")
                values["translated_title"] = title_blob.translate(from_lang="es")
            else:
                values["translated_body"] = "none"
                values["translated_title"] = "none"
            text_body = values["text_body"]
            title = values["title"]
            values["phone_numbers"] = self.phone_number_parse(values)
            data.append(values)
        
        return data

# 需要导入模块: from textblob import TextBlob [as 别名]
# 或者: from textblob.TextBlob import translate [as 别名]
def sentiment():
    doob = "Great Movie!"    
    blob = TextBlob(doob)

    for sentence in blob.sentences:
        print(sentence.sentiment)
        
    print blob.translate(to="cn") 

# 需要导入模块: from textblob import TextBlob [as 别名]
# 或者: from textblob.TextBlob import translate [as 别名]
def to_english(message, original_language=None):

	blob = TextBlob(text)

	if original_language is not None:
		return blob.translate(from_lang=original_language, to="en")
	else:
		return blob.translate(to="en")

# 需要导入模块: from textblob import TextBlob [as 别名]
# 或者: from textblob.TextBlob import translate [as 别名]
def getSentimentScore (text):
    blob = TextBlob(text)
    blob.tags           
    blob.noun_phrases
    try:
        blob.translate(to="en")
        print blob
    except:
        print"No translation needed for English text"
    sentimentScore = blob.sentiment.polarity
    return sentimentScore

# 需要导入模块: from textblob import TextBlob [as 别名]
# 或者: from textblob.TextBlob import translate [as 别名]
    def keywordResultsCount(self, inputs):
        self.inputs = inputs['general']
        params = self.mapParameters(inputs)

        print 'ushmm'
        print params

        try:

         if 'German'in params:
            g = params['Solr__Query']
            z1 = str(g)
            blob = TextBlob(z1)
            params['Solr__Query']=str(blob.translate(to="de"))
            print params
            self.result_search_term = params['Solr__Query']
            print self.result_search_term




         if 'French' in params:
            g = params['Solr__Query']
            z1 = str(g)
            blob = TextBlob(z1)
            params['Solr__Query']=str(blob.translate(to="fr"))
            print params
            self.result_search_term = params['Solr__Query']
            print self.result_search_term
        except:
            pass
        '''
        query = inputs['general'].split(' ')
        x=len(query)
        '''
        url = "http://www.errproject.org/jeudepaume/card_advanced_search.php"
        r = requests.get(url, params=params)
        html = r.text
        soup = BeautifulSoup(html, "lxml")

        results = soup.find_all("tr", class_="results")
        count = results.__len__()
        '''
        if (x>1):
            self.result_search_term = query[1]
        else:
            self.result_search_term = query[0]
        '''
        #self.result_search_term = 'none'
        self.results_url = r.url
        self.results_count = count

        return self

# 需要导入模块: from textblob import TextBlob [as 别名]
# 或者: from textblob.TextBlob import translate [as 别名]
def split_sentence_based_on_verbs(reviewText):
    review_spacy = nlp(reviewText)
    review_textblob = TextBlob(reviewText)
    if not review_textblob.detect_language() == 'en':
        review_textblob = review_textblob.translate(to='en')
        review_spacy = nlp(review_textblob.string)
    else:
        contains_romanian_words = 0

        for word in review_textblob.words:
            word_textblob = TextBlob(word)
            if len(word_textblob.string) >= 3 and word_textblob.detect_language() == 'ro':
                contains_romanian_words = 1
                break

        if contains_romanian_words == 1:
            new_reviewText = ''
            for word in review_spacy:
                word_textblob = TextBlob(word.orth_)
                if not word.is_title and len(word_textblob.string) >= 3:
                    if word_textblob.detect_language() != 'ro':
                        new_reviewText = new_reviewText + ' ' + word_textblob.string
                    else:
                        new_word = word_textblob.translate(to='en')
                        new_reviewText = new_reviewText + ' ' + new_word.string
                else :
                    new_reviewText = new_reviewText + ' ' + word_textblob.string
                    # only_english_words = 0
                    # break
            review_textblob = TextBlob(new_reviewText)
            review_spacy = nlp(review_textblob.string)

    new_sentences = []
    verbs_positions = []
    for k in range(0, len(review_spacy)):
        if review_spacy[k].pos == VERB and review_spacy[k].dep_ == 'ROOT':
            verbs_positions.append(k)
    start = 0
    if len(verbs_positions) > 0:
        for p in range(0, len(verbs_positions)):
            if p == len(verbs_positions) - 1:
                new_sentences.append(review_spacy[start:len(review_spacy)].text)
            else:
                q = verbs_positions[p] + 1
                while q < len(review_spacy):
                    if review_spacy[q].is_stop and ((review_spacy[q].pos == CONJ and (q < len(review_spacy)-1 and review_spacy[q-1].pos != review_spacy[q+1].pos)) or (review_spacy[q].pos == DET and review_spacy[q].lower_ in ['the', 'this', 'those', 'which', 'other', 'another']) or (review_spacy[q].pos == PUNCT and review_spacy[q] in [',', ';'])):
                        new_sentences.append(review_spacy[start:q].text)
                        start = q
                        break
                    q += 1
    else:
        new_sentences.append(reviewText)
    return new_sentences

# 需要导入模块: from textblob import TextBlob [as 别名]
# 或者: from textblob.TextBlob import translate [as 别名]
 def parse_text_meta_data(self,html,values):
     if self.debug: print "Processing textual information - language, polarity, subjectivity.."
     body_blob = TextBlob(values["text_body"])
     title_blob = TextBlob(values["title"])
     values["language"] = body_blob.detect_language() #requires the internet - makes use of google translate api
     values["polarity"] = body_blob.polarity
     values["subjectivity"] = body_blob.sentiment[1]
     if values["language"] != "en" and not translator:
         values["translated_body"] = body_blob.translate(from_lang="es")
         values["translated_title"] = title_blob.translate(from_lang="es")
     else:
         values["translated_body"] = "none"
         values["translated_title"] = "none"
     return values

# 需要导入模块: from textblob import TextBlob [as 别名]
# 或者: from textblob.TextBlob import translate [as 别名]
def translate_msg(message):
    try:
        if (len(message.text) > 3):
            b = TextBlob(unicode(message.text))
            if (b.detect_language() == "ru"):
                tr_text = unicode(b.translate(to="en"))
                bot.send_message(message.chat.id, tr_text)
            if (b.detect_language() == "en"):
                tr_text = unicode(b.translate(to="ru"))
                bot.send_message(message.chat.id, tr_text)
    except Exception as e:
        print (e.message)
        bot.send_message(message.chat.id, "Sorry Boss,can't translate :("
                                          " Try another message, please " +
                                          telegram.Emoji.KISSING_FACE)

# 需要导入模块: from textblob import TextBlob [as 别名]
# 或者: from textblob.TextBlob import translate [as 别名]
    def _german(self, text):
        blob = TextBlob(text)

        try:
            return str(blob.translate(to="en"))
        except:
            return text

# 需要导入模块: from textblob import TextBlob [as 别名]
# 或者: from textblob.TextBlob import translate [as 别名]
def hi(bot, trigger):
    lang_codes = ['af', 'ga', 'sq', 'it', 'ar',	'ja', 'az', 'kn', 'eu', 'ko', 'bn', 'la', 'en']
    trans = TextBlob('Greetings dear '+trigger.nick+'on the road of life ')
    ind = randint(0, 12)
    trans = trans.translate(to=lang_codes[ind])
    saying = str(trans)
    bot.say(saying)

# 需要导入模块: from textblob import TextBlob [as 别名]
# 或者: from textblob.TextBlob import translate [as 别名]
    def on_command(self, msg, stdin, stdout, reply):
        # pre-process args
        # this might mess up if "from" or "to" is left out and
        # the message contains "from" or "to"
        self._push_character(msg["args"], "from", "-", 1)
        self._push_character(msg["args"], "to",   "-", 1)

        try:
            args = self.parser.parse_args(msg["args"][1:])
        except (argparse.ArgumentError, SystemExit):
            return

        # get message from the appropriate place
        if args.message:
            message = " ".join(args.message)
        else:
            message = stdin.read().strip()

        # translate
        from_lang = args.from_language
        to_lang   = args.to_language
        message   = TextBlob(message)
        try:
            translated = message.translate(from_lang=from_lang, to=to_lang)
        except:
            pass
        else:
            print(translated, file=stdout)

# 需要导入模块: from textblob import TextBlob [as 别名]
# 或者: from textblob.TextBlob import translate [as 别名]
def _translate_message(bot, broadcast_list, context):
    if context and "autotranslate" in context:
        _autotranslate = context["autotranslate"]
        origin_language = _get_room_language(bot, _autotranslate["conv_id"])
        for send in broadcast_list:
            target_conversation_id = send[0]
            response = send[1]
            target_language = _get_room_language(bot, target_conversation_id)
            if origin_language != target_language:
                logger.debug("translating {} to {}".format(origin_language, target_language))
                translated = _autotranslate["event_text"]
                try:
                    en_blob = TextBlob(_autotranslate["event_text"])
                    translated = "{0}".format(en_blob.translate(to=target_language))
                    #translated = gs.translate(_autotranslate["event_text"], target_language
                except Exception:
                    logger.debug("Translation Api returned string unchanged")
                else:
                    pass
                finally:
                    if _autotranslate["event_text"] != translated:
                    # mutate the original response by reference
                        response.extend([
                            hangups.ChatMessageSegment('\n', hangups.SegmentType.LINE_BREAK),
                            hangups.ChatMessageSegment('(' + translated + ')')])

# 需要导入模块: from textblob import TextBlob [as 别名]
# 或者: from textblob.TextBlob import translate [as 别名]
def gen_translate(msg, fromlang=None, outputlang='en'):
    try:
        blob = TextBlob(msg)
        blob = blob.translate(from_lang=fromlang, to=outputlang)
        return str(blob)
    except NotTranslated:
        return msg

# 需要导入模块: from textblob import TextBlob [as 别名]
# 或者: from textblob.TextBlob import translate [as 别名]
def process_status(status, lang):
    text = ""

    # translate
    if lang == 'en':
        text = status['text']
    else:
        blob = TextBlob(status['text'])
        try:
            text = str(blob.translate())
        except textblob.exceptions.NotTranslated:
            text = status['text']

    # sentiment analysis
    sentiment = TextBlob(text).sentiment

    return {
          "created_at": 1000 * int(time.mktime((status['created_at']).timetuple()))
        , "id_str": status['id_str']
        , "text": text
        , "sentiment": {"polarity": sentiment[0], "subjectivity": sentiment[1]}
        , "retweet_count": status['retweet_count']
        , "in_reply_to_status_id_str": status['in_reply_to_status_id_str']
        , "geo": status['geo']
        , "retweeted": status['retweeted']
        , "in_reply_to_user_id_str": status['in_reply_to_user_id_str']
            }