nlp_tool.py 文件源码

def word_seg_get(data):
    output = get_page(get_addres + urllib2.quote(data.encode("utf-8")))
    if not 'SegmentResult' in output:
        return {}
    result = {}
    output = output.decode("gbk").encode("utf-8")
    #print output
    #print data.encode("utf-8")
    #output = output.translate(string.maketrans('\n',' '))
    info_dict = json.loads(output)
    segment = []
    if 'SegmentResult' in info_dict:
        for i in range(0, len(info_dict['SegmentResult'])):
            if info_dict['SegmentResult'][i] and 'buffer' in info_dict['SegmentResult'][i]:
                segment.append(info_dict['SegmentResult'][i]['buffer'])
                #print info_dict['SegmentResult'][i]['buffer'].encode('utf-8')
    basic = []
    if 'BasicWordResult' in info_dict:
        for i in range(0, len(info_dict['BasicWordResult'])):
            if info_dict['BasicWordResult'][i] and 'buffer' in info_dict['BasicWordResult'][i]:
                basic.append(info_dict['BasicWordResult'][i]['buffer'])
                #print info_dict['SegmentResult'][i]['buffer'].encode('utf-8')
    result["segment"] = segment
    result["basic"] = basic
    return result