def text_blob(doc):
"""
TextBlob Sentiment (by segment)
:param doc: zh doc
:return: (-1~1)
"""
try:
translator_en = Translator()
en_text = translator_en.translate(doc).text
blob = TextBlob(en_text)
except:
try:
blob = TextBlob(doc)
blob = blob.translate()
except:
try:
en_text = iciba(doc, dst='en')
blob = TextBlob(en_text)
except:
try:
gs = goslate.Goslate()
en_text = gs.translate(doc, 'en')
blob = TextBlob(en_text)
except:
translator = tT(to_lang="en")
en_text = translator.translate(doc)
blob = TextBlob(en_text)
score = []
for sentence in blob.sentences:
emotion = sentence.sentiment.polarity * sentence.sentiment.subjectivity
if 0.00001 > emotion > -0.00001:
continue
score.append(emotion)
return np.mean(score)
def get_html_text(url):
'''
通过URL获取页面内容
并提取其中的文本信息
:param url: 目标url
:return: 提取得到的文本信息
'''
#下载页面内容
try:
req=requests.get(url,headers=headers,timeout=3)
req.encoding = req.apparent_encoding
html=req.text
#print(html)
soup = BeautifulSoup(html, 'lxml')
#去除script与style
[s.extract() for s in soup(['script','style'])]
#提取文本 拼接为一串
text=soup.get_text()
lines = (line.strip() for line in text.splitlines())
chunks = (phrase.strip() for line in lines for phrase in line.split(" "))
text = ' '.join(chunk for chunk in chunks if chunk)
print(text)
# tansor=Translator()
#
# print(tansor.detect(text).lang)
# if tansor.detect(text).lang=='en':
# text=tansor.translate(text,dest="zh-cn").text
# print(text)
try:
print(detect(text))
if detect(text) != 'zh-cn':
text = iciba(text, dst='zh')
print(text)
except:
pass
return text
except:
return None
def run_inference_on_image(image):
"""Runs inference on an image.
Args:
image: Image file name.
Returns:
Nothing
"""
if not tf.gfile.Exists(image):
tf.logging.fatal('File does not exist %s', image)
image_data = tf.gfile.FastGFile(image, 'rb').read()
# Creates graph from saved GraphDef.
create_graph()
with tf.Session() as sess:
# Some useful tensors:
# 'softmax:0': A tensor containing the normalized prediction across
# 1000 labels.
# 'pool_3:0': A tensor containing the next-to-last layer containing 2048
# float description of the image.
# 'DecodeJpeg/contents:0': A tensor containing a string providing JPEG
# encoding of the image.
# Runs the softmax tensor by feeding the image_data as input to the graph.
softmax_tensor = sess.graph.get_tensor_by_name('softmax:0')
predictions = sess.run(softmax_tensor,
{'DecodeJpeg/contents:0': image_data})
predictions = np.squeeze(predictions)
# Creates node ID --> English string lookup.
node_lookup = NodeLookup()
top_k = predictions.argsort()[-FLAGS.num_top_predictions:][::-1]
for node_id in top_k:
human_string = node_lookup.id_to_string(node_id)
score = predictions[node_id]
try:
human_string_zh = iciba('Also known as ' + human_string, dst='zh')
if sys.version_info.major <= 2:
human_string_zh = human_string_zh.encode('utf-8')
print('%s(%s)---(Matching = %.5f)' % (human_string, human_string_zh, score))
except (TranslateError, ConnectError):
print('%s---(Matching = %.5f)' % (human_string, score))
def get_html_text_by_file(fileName):
'''
通过已经下载的html文件 提取其中的文本信息
:param fileName: html文件
:return: 提取的文件信息
'''
try:
with open(fileName, 'r', encoding='utf-8', errors='ignore') as f:
html = f.read()
soup = BeautifulSoup(html, 'lxml')
# 去除script与style
[s.extract() for s in soup(['script', 'style'])]
# 提取文本 拼接为一串
text = soup.get_text()
lines = (line.strip() for line in text.splitlines())
chunks = (phrase.strip() for line in lines for phrase in line.split(" "))
text = ' '.join(chunk for chunk in chunks if chunk)
print(text)
# tansor = Translator()
#
# print(tansor.detect(text).lang)
# if tansor.detect(text).lang == 'en':
# text = tansor.translate(text, dest="zh-cn").text
# print(text)
try:
print(detect(text))
if detect(text) != 'zh-cn':
text = iciba(text, dst='zh')
print(text)
except:
pass
return text
except IOError:
return None
# from googletrans import Translator
# translator = Translator()
# print(translator.translate('hola'))
# from translate import Translator
# translator= Translator(from_lang="tr",to_lang="en")
# print(translator.translate("Bu bir dolma kalemdir."))
from translation import baidu, google, youdao, iciba
#print(google('hello world!', dst = 'zh-CN'))
#print(google('hello world!', dst = 'ru'))
print(baidu('hello world!', dst='zh'))
print(baidu('hello world!', dst='ru'))
print(youdao('hello world!', dst='zh-CN'))
print(iciba('hello world!', dst='zh'))
print(bing('hello world!', dst='zh-CHS'))
from translation import Translation, baidu, google, youdao, iciba, bing
print(baidu('hello world!', dst = 'zh'))
print(youdao('hello world!', dst = 'zh-CN'))
print(iciba('hello world!', dst = 'zh'))
print(google('hello world!', dst = 'zh-CN'))
print(bing('hello world!', dst = 'zh-CHS'))
'''
try:
with open(fileName, 'r', encoding='utf-8', errors='ignore') as f:
html = f.read()
soup = BeautifulSoup(html, 'lxml')
input_cnt = len(soup.find_all("input"))
pwd_input_cnt = len(soup.find_all("input", attrs={"type": "password"}))
print((input_cnt, pwd_input_cnt))
return (input_cnt, pwd_input_cnt)
except:
return (-1, -1)
if __name__ == '__main__':
#print(get_psychology_features("http://www.iep.utm.edu/aestheti/"))
#print(get_psychology_features_by_url("https://en.wikipedia.org/wiki/How-to"))
#count_page_input_by_url("https://shop.dma.org/")
#count_page_input_by_file("test.html")
#print(get_psychology_features_by_file("test.html"))
text="English is good"
print(detect("你好呀"))
if detect(text) == 'en':
text=iciba(text, dst = 'zh')
print(text)