def CkipReturn(in_text): #in_text is string
segmenter = CKIPSegmenter('changcheng.tu', 'a10206606')
try:
segmented_in_text_result = segmenter.process(unicode(in_text))
except:
segmented_in_text_result = segmenter.process(unicode('got an error'))
return segmented_in_text_result
def to_ckip(inp):
segmenter = CKIPSegmenter('Bolin', 'Bolin') #ckip連線帳戶
try:
result = segmenter.process(inp) #斷詞結果
if result['status_code'] != '0': #若斷詞失敗
print('Process Failure: ' + result['status'])
SaveList = []
SaveSeg = []
sen_all = []
for sentence in result['result']:
for term in sentence:
SaveList.append(term['term']) #詞陣列
SaveSeg.append(term['pos']) #詞性陣列
for word, pos in zip(SaveList, SaveSeg):
wp = word + '(' + pos + ')'
sen_all.append(wp)
combine = ' '.join(sen_all)
return [SaveList, SaveSeg, combine]
except:
print('error :', inp)
return False
noun_terms_arr = []
verb_terms_arr = []
words_use = pseg.cut(test_sent)
for word_use in words_use:
if re.match("n", word_use.flag) != None and word_use.word not in noun_terms_arr:
noun_terms_arr.append(word_use.word)
if re.match("v", word_use.flag) != None and word_use.word not in verb_terms_arr:
verb_terms_arr.append(word_use.word)
result_arr.extend(noun_terms_arr)
result_arr.extend(verb_terms_arr)
print("no ckip")
print(result_arr)
return (result_arr, noun_terms_arr, verb_terms_arr)
segmenter = CKIPSegmenter('gcsn', 'rb303147258')
parser = CKIPParser('gcsn', 'rb303147258')
client = MongoClient('mongodb://localhost:27017/')
db = client['councilor']
collection = db['ntp_bills']
# collection_save = db['test']
bills = list(collection.find())
for bill in bills:
description_verb = []
description_nonu = []
description_term = []
try:
result = segmenter.process(bill["description"])
if result['status_code'] != '0':
sentence = sentence[pos + 1:]
pos = sentence.find(u"。")
if pos == -1:
pos = sentence.find(u"？")
if len(part_sentence) == 0:
part_sentence.append(u"".join(sentence))
num_part_sentence += 1
content.append(part_sentence)
f_account = codecs.open("ckip_account.txt", 'r')
account_info = f_account.readlines()
segmenter = CKIPSegmenter(account_info[0][:-1], account_info[1][:-1])
j = 0
words = []
for sentence in content:
for line in sentence:
j += 1
if line == u"\n":
continue
print(str(j) + "/" + str(num_part_sentence))
print(line)
result = segmenter.process(line)
if result['status_code'] != '0':
def log_in(self):
f_account = codecs.open("ckip_account.txt", 'r')
account_info = f_account.readlines()
self.segmenter = CKIPSegmenter(account_info[0][:-1],
account_info[1][:-1])
from ckip import CKIPSegmenter, CKIPParser
def traverse(root):
"""Helper function to traverse all leaf nodes of the given tree root."""
if 'child' in root:
for child in root['child']:
for leaf in traverse(child):
yield leaf
else:
yield root
# Usage example of the CKIPSegmenter class
segmenter = CKIPSegmenter('YOUR USERNAME', 'YOUR PASSWORD')
result = segmenter.process('這是一隻可愛的小花貓')
if result['status_code'] != '0':
print('Process Failure: ' + result['status'])
for sentence in result['result']:
for term in sentence:
print(term['term'], term['pos'])
# Usage example of the CKIPParser class
parser = CKIPParser('YOUR USERNAME', 'YOUR PASSWORD')
result = parser.process('這是一隻可愛的小花貓')
if result['status_code'] != '0':
print('Process Failure: ' + result['status'])