python自动化测试

测试API`http://192.168.100.75XXXXXXXXXXXXXXXXXXXXX

解析json:

{'result': True,
     'MetaList': [{
	                'ID': '-1769765650_2108236046', 
					'Data': 
					     {'Extra': {'来源链接': '', '答案': '您好，九龙湖校区馆长室在李文正图书馆A506，电话025-52090321。\r\n四牌楼校区馆长室在四牌楼图书馆205，电话025-83793481。', '来源': '', '完整答案': '', '问题': '馆长室在哪？'}, 
						  'Domain': '图书馆_业务数据', 
						  'Question': '馆长室在哪？', 
						  'Answer': '您好，九龙湖校区馆长室在李文正图书馆A506，电话025-52090321。\r\n四牌楼校区馆长室在四牌楼图书馆205，电话025-83793481。'}, 
				    'DataType': 0
				}]
}

# -*- coding: utf-8 -*-
"""
Created on Mon Apr 15 15:00:50 2019

@author: xiaocui
"""

import json

import pandas as pd
import urllib
import urllib.request as urllib2
import random

import socket 
socket.setdefaulttimeout(30) 

user_agents = ['Mozilla/5.0 (Windows NT 6.1; WOW64; rv:23.0) Gecko/20130406 Firefox/23.0', \
    'Mozilla/5.0 (Windows NT 6.1; WOW64; rv:18.0) Gecko/20100101 Firefox/18.0', \
    'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US) AppleWebKit/533+ \
    (KHTML, like Gecko) Element Browser 5.0', \
    'IBM WebExplorer /v0.94', 'Galaxy/1.0 [en] (Mac OS X 10.5.6; U; en)', \
    'Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0)', \
    'Opera/9.80 (Windows NT 6.0) Presto/2.12.388 Version/12.14', \
    'Mozilla/5.0 (iPad; CPU OS 6_0 like Mac OS X) AppleWebKit/536.26 (KHTML, like Gecko) \
    Version/6.0 Mobile/10A5355d Safari/8536.25', \
    'Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.36 (KHTML, like Gecko) \
    Chrome/28.0.1468.0 Safari/537.36', \
    'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.0; Trident/5.0; TheWorld)']



def ExtractInfo(question):
    link = 'http://XXXXXXXXXX/dn.qa.api/GetAnswer?appid=lib_neu&aid=ee831eebc9f01c3f18d6c2198ff879b2&q={0}'.format(urllib.parse.quote(question))
    urlDomain = urllib2.Request(link)
    r = random.randint(0,len(user_agents)-1)
    urlDomain.add_header('User-agent', user_agents[r])
    urlDomain.add_header('connection','keep-alive')

    #解析出来的ID
    ID = []
    #解析出来的领域
    domain = []
    #解析出来的匹配问题
    matchQustion = []
    #解析出来的答案
    answer = []
    is_match = []
    try:
        req = urllib2.urlopen(urlDomain)

        html = req.read()
        
        js = json.loads(html.decode('utf-8'))

        print(js)

        # if(js['result'] == True):
        #     for item in js['MetaList']:
        #         tmp = item['DataType']
        #         if(tmp == 1):
        #             child = item['MetaList'][0]
        #             ID.append(child['ID'])
        #             domain.append(child['DOMAIN'])
        #             matchQustion.append(child['QUESTION'])
        #             answer.append(child['Answer'].replace("\n",'')[:30])
        #         # 能匹配
        #         elif(tmp == 0):
        #             d_tmp = item['Domain']
        #             for child in item['MetaList']:
        #                 domain.append(d_tmp)
        #                 matchQustion.append(child[d_tmp+'名'])
        #                 ID.append(child[d_tmp+'ID'])
        #                 answer.append("")
        if (js['result'] == True):
            for list in js['MetaList']:
                #ID = list['DataType']
                # if (len(list['ID']) == 0):
                #     is_match.append('不能匹配')
                #     ID.append(list['ID'])
                # else:
                #     is_match.append('可以匹配')
                ID.append(list['ID'])
                domain.append(list['Data']['Domain'])
                matchQustion.append(list['Data']['Question'])
                answer.append(list['Data']['Answer'])
        else:
            ID
            domain.append('无答案')
            matchQustion.append('无答案')
            answer.append('无答案')
        return ID,domain,matchQustion,answer

    except urllib.error.HTTPError:
        return [],[],[],[]
 
file_path = r"E:\工作\东南大学图书馆\0527测试不通过问题.txt"
questions = open("{0}".format(file_path),encoding="gb18030").read().strip().split('\n')

######################################################################################
match_ids = []
match_domain = []
match_questions = []
match_answers = []
match_dataType = []
# 原问题
valid_q = []
# 是否匹配
is_match = []
for q in questions:
    print(q)
    ID,domain,matchQustion,answer = ExtractInfo(q)
    if(len(ID) == 0):
        is_match.append('无答案')
        valid_q.append(q)
        match_ids.append('')
        match_domain.append('')
        match_questions.append('')
        match_answers.append('')
        continue
    else:
        is_match.append('可以匹配')
    
    valid_q.append(q)
    match_ids.append(ID[0])
    match_domain.append(domain[0])
    match_questions.append(matchQustion[0])
    match_answers.append(answer[0])
    for idx,d,q,a in zip(ID[1:],domain[1:],matchQustion[1:],answer[1:]):
        valid_q.append('')
        is_match.append('Y')
        match_ids.append(idx)
        match_domain.append(d)
        match_questions.append(q)
        match_answers.append(a)
###################################################################################### 


df = pd.DataFrame()


df['原问题'] = valid_q
df['是否匹配'] = is_match
df['匹配的ID'] = match_ids
df['匹配的问题'] = match_questions
df['匹配的领域'] = match_domain
df['匹配的答案'] = match_answers
df.to_excel('test_result_0418-1.xlsx')