• 借助ltp语义分析提取特征,之后,文本生成


    """
    地点-哪里有做-业务-的(正规|靠谱)-公司?
    地点-做-业务-的(正规|靠谱)-公司(有哪些?|的联系方式是什么?|哪家口碑好值得信赖?)
    地点-做-业务-(怎么能省钱?|费用是多少?|需要注意什么?|有哪些流程?)
    地点-业务-(靠谱吗?到底怎样?)
    地点-(最好的|靠谱的)业务-是哪家?
    """
    p, b = '深圳市', ['广告设计', '网络推广']

    ltp_model = ['地点-哪里有做-业务-的(正规|靠谱)-公司?', '地点-做-业务-的(正规|靠谱)-公司(有哪些|的联系方式是什么|哪家口碑好值得信赖)?',
    '地点-做-业务-(怎么能省钱|费用是多少|需要注意什么|有哪些流程|靠谱吗|到底怎样)?', '地点-(最好的|靠谱的)业务-是哪家?']
    r_l = []
    for s in ltp_model:
    s = s.replace('地点', p).replace('-', '')
    for i in b:
    r_l.append(s.replace('业务', i))

    def deal_first_splittag_str(i):
    s_l_1 = []
    psl, psr = i.find('(', 0), i.find(')', 0)
    sl, sm, sr = i[0:psl], i[psl + 1:psr], i[psr + 1:]
    l = sm.split('|')
    for ii in l:
    s_l_1.append('%s%s%s' % (sl, ii, sr))
    return s_l_1


    def deal_first_splittag(s_l_0):
    s_l_1 = []
    for i in s_l_0:
    psl, psr = i.find('(', 0), i.find(')', 0)
    if psl == -1:
    s_l_1.append(i)
    else:
    sl, sm, sr = i[0:psl], i[psl + 1:psr], i[psr + 1:]
    l = sm.split('|')
    for ii in l:
    s_l_1.append('%s%s%s' % (sl, ii, sr))
    return s_l_1


    while True:
    f = 0
    for i in r_l:
    if '(' in i:
    f = 1
    del r_l[r_l.index(i)]
    l = deal_first_splittag_str(i)
    r_l += l
    if f == 0:
    break

    d = 9






    def gen_r(uid):
    from pymongo import MongoClient

    def select_to_dic(k, collection_name,
    database=MongoClient("mongodb://192.168.2.50:27017/", username='admin', password='admin')[
    "personas_test"], where={}, fields={}):
    collection, r = database[collection_name], {}
    if fields == {}:
    cursor = collection.find(where)
    else:
    cursor = collection.find(where, fields)
    try:
    for doc in cursor:
    r[doc[k]] = doc
    finally:
    cursor.close()
    return r

    uid = int(uid)
    user_info = select_to_dic('_id', 'Analyse_user',
    fields={'city': 1, 'city': 1, 'province': 1, 'core_keyword': 1, 'extract_keyword': 1,
    'biz': 1},
    where={'uid': uid})
    if user_info == {}:
    return ['uid not in db']
    for k in user_info:
    d = user_info[k]
    p = '%s%s' % (d['province'], d['city'])
    b = d['core_keyword'] + d['extract_keyword'] + d['biz']
    b = [i for i in set(b)]

    """
    地点-哪里有做-业务-的(正规|靠谱)-公司?
    地点-做-业务-的(正规|靠谱)-公司(有哪些?|的联系方式是什么?|哪家口碑好值得信赖?)
    地点-做-业务-(怎么能省钱?|费用是多少?|需要注意什么?|有哪些流程?)
    地点-业务-(靠谱吗?到底怎样?)
    地点-(最好的|靠谱的)业务-是哪家?
    """
    # p, b = '深圳市', ['广告设计', '网络推广']

    ltp_model = ['地点-哪里有做-业务-的(正规|靠谱)-公司?', '地点-做-业务-的(正规|靠谱)-公司(有哪些|的联系方式是什么|哪家口碑好值得信赖)?',
    '地点-做-业务-(怎么能省钱|费用是多少|需要注意什么|有哪些流程|靠谱吗|到底怎样)?', '地点-(最好的|靠谱的)业务-是哪家?']
    r_l = []
    for s in ltp_model:
    s = s.replace('地点', p).replace('-', '')
    for i in b:
    r_l.append(s.replace('业务', i))

    def deal_first_splittag_str(i):
    s_l_1 = []
    psl, psr = i.find('(', 0), i.find(')', 0)
    sl, sm, sr = i[0:psl], i[psl + 1:psr], i[psr + 1:]
    l = sm.split('|')
    for ii in l:
    s_l_1.append('%s%s%s' % (sl, ii, sr))
    return s_l_1

    def deal_first_splittag(s_l_0):
    s_l_1 = []
    for i in s_l_0:
    psl, psr = i.find('(', 0), i.find(')', 0)
    if psl == -1:
    s_l_1.append(i)
    else:
    sl, sm, sr = i[0:psl], i[psl + 1:psr], i[psr + 1:]
    l = sm.split('|')
    for ii in l:
    s_l_1.append('%s%s%s' % (sl, ii, sr))
    return s_l_1

    while True:
    f = 0
    for i in r_l:
    if '(' in i:
    f = 1
    del r_l[r_l.index(i)]
    l = deal_first_splittag_str(i)
    r_l += l
    if f == 0:
    break

    return r_l


    from wsgiref.util import setup_testing_defaults, request_uri
    from wsgiref.simple_server import make_server


    # A relatively simple WSGI application. It's going to print out the
    # environment dictionary after being updated by setup_testing_defaults
    def simple_app(environ, start_response):
    setup_testing_defaults(environ)

    status = '200 OK'
    headers = [('Content-type', 'text/plain; charset=utf-8')]

    start_response(status, headers)
    r_uri = request_uri(environ, include_query=True)
    if 'test_dump' in r_uri:
    return [("%s: %s " % (key, value)).encode('utf-8') for key, value in environ.items()]
    elif 'uid' in r_uri:

    try:
    uid = int(r_uri.split('/')[-1])
    if uid > 0:
    r_l = gen_r(uid)
    return [("%s: %s " % (i, r_l[i])).encode('utf-8') for i in range(len(r_l))]
    else:
    return [('%s%s' % ('BAD-REQUEST ', r_uri)).encode('utf-8')]
    except Exception as e:
    return [('%s%s%s' % (e, ' retry...,please.... ', r_uri)).encode('utf-8')]
    else:
    return [('%s%s' % ('dev-ING- ', r_uri)).encode('utf-8')]


    with make_server('', 8000, simple_app) as httpd:
    print("Serving on port 8000...")
    httpd.serve_forever()



  • 相关阅读:
    android数据恢复
    UVA 690 Pipeline Scheduling
    2017 国庆湖南 Day4
    2017 国庆湖南 Day5
    2017 国庆湖南 Day6
    2017国庆 清北学堂 北京综合强化班 Day1
    2017 国庆湖南Day2
    bzoj 2962 序列操作
    UVA 818 Cutting Chains
    UVA 211 The Domino Effect
  • 原文地址:https://www.cnblogs.com/rsapaper/p/8043008.html
Copyright © 2020-2023  润新知