汽车消费者典型意见¶

# -*- encoding: utf-8 -*-
from __future__ import print_function, unicode_literals
import sys
import time
import json

import requests

COMMENTS_ANALYSIS_URL = 'http://api.bosonnlp.com/comments/analysis/'
COMMENTS_PUSH_URL = 'http://api.bosonnlp.com/comments/push/'
COMMENTS_RESULT_URL = 'http://api.bosonnlp.com/comments/result/'
COMMENTS_STATUS_URL = 'http://api.bosonnlp.com/comments/status/'
COMMENTS_CLEAR_URL = 'http://api.bosonnlp.com/comments/clear/'
TASK_ID = 'task_%d' % int(time.time())

# 注意：在测试时请更换为您的API Token
session = requests.Session()
session.headers['X-Token'] = 'YOUR_API_TOKEN'


def comments_status():
    resp = session.get(COMMENTS_STATUS_URL + TASK_ID)
    resp.raise_for_status()
    return resp.json()["status"]


def detail_results(idx, comments):
    print('=' * 50)
    print('第%d组典型意见是:' % (idx + 1))
    print(comments['opinion'])
    print('-' * 20)
    print('共包含%s份文档，意见内容和原文ID如下:' % comments['num'])
    for comment, doc_id in comments['list']:
        print(comment, doc_id)


def main():
    print('任务ID:', TASK_ID)
    print('读入数据...')
    with open('text_comments.txt', 'rb') as f:
        docs = [line.decode('utf-8') for line in f if line]

    print('正在上传数据...')
    for i in xrange(0, len(docs), 100):
        data = json.dumps([{'_id': i + idx, 'text': text} for idx, text in enumerate(docs[i:i+100])])
        resp = session.post(COMMENTS_PUSH_URL + TASK_ID, data=data.encode('utf-8'))
        resp.raise_for_status()

    print('开始分析...')
    resp = session.get(COMMENTS_ANALYSIS_URL + TASK_ID)
    resp.raise_for_status()

    while True:
        status = comments_status()
        if status == 'DONE':
            resp = session.get(COMMENTS_RESULT_URL + TASK_ID)
            resp.raise_for_status()
            all_comments = resp.json()

            print('一共生成了%d组典型意见' % len(all_comments))
            sort_all_comments = sorted(all_comments, key=lambda comments: len(comments['list']), reverse=True)
            for idx, comments in enumerate(sort_all_comments):
                detail_results(idx, comments)

            resp = session.get(COMMENTS_CLEAR_URL + TASK_ID)
            resp.raise_for_status()
            break
        elif status == 'NOT FOUND':
            print('找不到典型意见任务。')
            break
        elif status == 'ERROR':
            print('任务失败，请稍后重试。')
        else:
            print('.', end='')
            sys.stdout.flush()
            time.sleep(0.5)


if __name__ == '__main__':
    main()

# -*- encoding: utf-8 -*-
from __future__ import print_function, unicode_literals
from bosonnlp import BosonNLP

# 注意：在测试时请更换为您的API Token
nlp = BosonNLP('YOUR_API_TOKEN')


def print_comments(idx, comments):
    print('=' * 50)
    print('第%d组典型意见是:' % (idx + 1))
    print(comments['opinion'])
    print('-' * 20)
    print('共包含%s份文档，意见内容和原文ID如下:' % comments['num'])
    for comment, doc_id in comments['list']:
        print(comment, doc_id)


def main():
    with open('text_comments.txt', 'rb') as f:
        docs = [line.decode('utf-8') for line in f if line]
    all_comments = nlp.comments(docs)
    sort_all_comments = sorted(all_comments, key=lambda comments: comments['num'], reverse=True)
    for idx, comments in enumerate(sort_all_comments):
        print_comments(idx, comments)


if __name__ == '__main__':
    main()