def get_dbinfo(slot1,slot2, choose):
client = db.MongoClient(DB_IP, DB_PORT)
collection_division = client[DB_NAME]["division"]
collection_disease = client[DB_NAME]["disease"]
doctor_list = []
#use disease to find division
if slot2 == "department":
for data in collection_disease.find({"disease_c": {"$regex": slot1}}):
return data['department']
#use disease to find doctors
elif slot2 == "doctor" and choose == 0:
for data in collection_division.find({"$and": [{"disease": {"$regex": slot1}},
{"department": {"$regex": ""}}]}):
for name in data['doctor']:
if name not in doctor_list:
doctor_list.append(name)
return doctor_list
#use division to find doctors
elif slot2 == "doctor" and choose == 1:
for data in collection_division.find({"$and": [{"disease": {"$regex": ''}},
{"department": {"$regex": slot1}}]}):
for name in data['doctor']:
if name not in doctor_list:
doctor_list.append(name)
return doctor_list
def __init__(self):
client = db.MongoClient(DB_IP, DB_PORT)
collection_division = client[DB_NAME]["division"]
collection_disease = client[DB_NAME]["disease"]
disease_list = [line.rstrip('\n') for line in open("../data_resource/disease_dict.txt", "r")]
#print(disease_list)
notfind = True
while notfind :
notfind = False
disease = disease_list[random.randint(0, len(disease_list)-1)]
#print(disease)
while collection_division.find({"disease": disease}).count() < 1:
disease = disease_list[random.randint(0, len(disease_list) - 1)]
#print(disease)
for collection in collection_disease.find({"disease_c": disease}):
division = collection['department'][0]
doctor_list = []
for collection in collection_division.find({"disease": disease}):
doctor_list.extend(collection['doctor'])
#print(doctor_list)
if len(doctor_list) is 0:
notfind = True
elif len(doctor_list) > 1:
name = doctor_list[random.randint(0, len(doctor_list)-1)]
else:
name = doctor_list[0]
if not notfind:
time_list = CrawlerTimeTable.Timetable(name).get_time()
#print(time_list)
if len(time_list) is 0:
notfind = True
elif len(time_list) > 1:
time = time_list[random.randint(0, len(time_list)-1)]
else:
time = time_list[0]
self.goal = {'intent': random.randint(1, 5),
'slot': {'disease': disease, 'division': division, 'doctor': name, 'time': time}}
#sys.path.append('../../../doctorbot')
#from doctorbot import settings
#from fb_doctor_chatbot import models
#setup_environ(settings)
#os.environ['DJANGO_SETTINGS_MODULE'] = 'doctorbot.settings'
DIR_NAME = '../../../../DoctorBot/doctorbot/'
import sqlite3
conn = sqlite3.connect(DIR_NAME + 'db.sqlite3')
#fb = conn.cursor()
DB_IP = "104.199.131.158" # doctorbot GCP ip
DB_PORT = 27017 # default MongoDB port
DB_NAME = "doctorbot" # use the collection
client = db.MongoClient(DB_IP, DB_PORT)
collection_division = client[DB_NAME]["division"]
collection_disease = client[DB_NAME]["disease"]
def initialize():
state = {"intent": None, "disease": None, "division": None, "doctor": None, "time": None}
DM = {"Request": None, "Intent": None, "Slot": None, "State": state}
#if os.path.exists("DM.json"):
#os.remove("DM.json")
with open("DM.json", 'w') as f:
json.dump(DM,f)
return DM
#################################################################################################
# search for division or doctor from database #
#################################################################################################
def get_dbinfo(slot1,slot2, choose):
'//div[@id="link-report"]//div[@class="intro"]/p/text()')
jianjie = ''.join(jianjie_list)
author_jianjie_list = html.xpath(
'//div[@class="indent "]//div[@class="intro"]/p/text()')
author_jianjie = ''.join(author_jianjie_list)
nianduBandan = 'https://book.douban.com/annual/2018?source=navigation#1'
save_res = bookName + ',' + url + ',' + authors + ',' + isbn + ',' + tags + ',' + publishDate + ',' + chubanshe + ',' + jianjie + ',' + author_jianjie + ',' + nianduBandan + '\n'
print(save_res)
results = {
'bookName': bookName,
'url': url,
'authors': authors,
'isbn': isbn,
'tags': tags,
'publishDate': publishDate,
'chubanshe': chubanshe,
'jianjie': jianjie,
'author_jianjie': author_jianjie,
'nianduBandan': nianduBandan,
}
dbCli.save(results)
if __name__ == '__main__':
dbCli = db.MongoClient()
start()
def main():
client = db.MongoClient(DB_IP, DB_PORT)
collection_division = client[DB_NAME]["division"]
collection_disease = client[DB_NAME]["disease"]
sys.stdout.flush()
print("您好，我是Seek Doctor Bot，如果您想要\n" + "1.查詢某疾病相關症狀，您可以問我：請問青光眼會怎樣\n" +
"2.知道某疾病屬於什麼科別，您可以問我：青光眼是哪科\n" + "3.查詢某疾病或科別主治醫師，您可以問我：青光眼要看哪些醫生\n" +
"4.查詢某疾病,科別或醫生的門診時間，您可以說：給我青光眼門診時刻表\n" +
"5.預約掛號某疾病,科別或醫生的門診，您可以說：我要掛號眼科")
while True:
sentence = input('\n\n請輸入: ')
slot_dictionary = LU.SlotFilling().decode(sentence)
print("[ Slot ]")
for slot, value in slot_dictionary.items():
print(slot, ": ", value)
intent = LU.IntentPredict().get_intent(sentence)
intent_index = intent.index(max(intent))
intents = [
'greeting', 'search_symptom', 'search_division', 'search_doctor',
'search_timetable', 'register'
]
print('[ Intent ] ' + intents[intent_index])
print('\n\n')
if intent_index == 1: # search_symptom
print("好的，您想查詢" + slot_dictionary['disease'] + "會有什麼症狀，以下為相關可能症狀：")
for data in collection_disease.find(
{"disease_c": {
"$regex": slot_dictionary['disease']
}}):
print(", ".join(data['symptom']))
elif intent_index == 2: # search_division
print("好的，您想查詢" + slot_dictionary['disease'] + "是屬於哪一科，以下為相關科別：")
for data in collection_disease.find(
{"disease_c": {
"$regex": slot_dictionary['disease']
}}):
print(", ".join(data['department']))
elif intent_index == 3: # search_doctor
print("好的，您想查詢" + slot_dictionary['division'] +
slot_dictionary['disease'] + "有哪些醫生可以掛號，以下為醫生表列：")
for data in collection_division.find({
"$and": [{
"disease": {
"$regex": slot_dictionary['disease']
}
}, {
"department": {
"$regex": slot_dictionary['division']
}
}]
}):
print(data['department'] + " 醫師: " + ", ".join(data['doctor']))
elif intent_index == 4: # search_timetable
print("好的，您想查詢" + slot_dictionary['division'] +
slot_dictionary['disease'] + slot_dictionary['doctor'] +
slot_dictionary['time'] + "的門診時間")
elif intent_index == 5: # register
print("好的，幫您預約掛號" + " " + slot_dictionary['division'] + " " +
slot_dictionary['disease'] + " " +
slot_dictionary['doctor'] + " " + slot_dictionary['time'] +
"的門診")
else:
print("不好意思,我不確定您的意思")
start_url = URL.format(keyword=keyword,pageToken=i,startDate=startDate,endDate=endDate)
print(start_url)
response = down.get_html(start_url)
if response:
# print(response.text):
parse(item,response)
else:
print('网络请求失败')
continue
#获取文章
wenzhang_url = 'https://s.weibo.com/article?q={keyword}&Refer=weibo_article&page={pageToken}'
for i in range(1,wenzhangPageNum+1):
start_url = wenzhang_url.format(keyword=keyword,pageToken=i)
print(start_url)
response = down.get_html(start_url)
if response:
# print(response.text)
parse_wenzhang(item,response)
else:
print('网络请求失败')
continue
if __name__ == '__main__':
down = download.Download()
mongoClient = db.MongoClient()
item_list = read()
for obj in item_list:
print('当前关键词：'+obj['keyword'])
main(obj)