PYNLPIR_1

#coding = UTF-8
import pynlpir
pynlpir.open()
s = "长江市长江大桥参加了长江大桥的开通仪式。"
pynlpir.segment(s, pos_tagging = True)

pynlpir.segment(s, pos_tagging = False)

for word in pynlpir.segment(s, pos_tagging = False):
    print word

for word in pynlpir.segment(s, pos_tagging = True):
    print word[0],word[1]

for word in pynlpir.segment(s, pos_tagging = True, pos_names = "child"):
    print word[0],word[1]
    
for word in pynlpir.segment(s, pos_tagging = True, pos_names = "all"):
    print word[0], word[1]
    
pynlpir.nlpir.FileProcess("C:\\Users\\Luo Chen\\Desktop\\test.txt", "C:\\Users\\Luo Chen\\Desktop\\output.txt",True)

sou = open("C:\\Users\\Luo Chen\\Desktop\\source.txt")
source = sou.read()
print source
for word in pynlpir.segment(source, pos_tagging = False):
    print word
    
stop = open("C:\\Users\\Luo Chen\\Desktop\\stopword.txt")
stopword = stop.read()
print stopword

pynlpir.nlpir.AddUserWord("天安门城楼")
pynlpir.nlpir.AddUserWord(" 很久没有")
pynlpir.nlpir.AddUserWord("《漂洋过海来看你》")
for word in pynlpir.segment(source, pos_tagging = False):
    print word

stopWords = []
for word in open("C:\\Users\\Luo Chen\\Desktop\\stopword.txt","r"):
    stopWords.append(word.strip())
print stopWords

for line in open("C:\\Users\\Luo Chen\\Desktop\\source.txt", "r").readlines():
    segmented_line = pynlpir.segment(line.strip(), pos_tagging = False)
    origin_line = ""
    stayed_line = ""
    for word in segmented_line:
        origin_line = origin_line + word + " "
        if word.encode("utf-8") not in stopWords:
            stayed_line = stayed_line + word + " "
    print "原句：",origin_line
    print "过滤后：",stayed_line