def __init__(self):
self.logger = Logger()
self.mongo = mongo.Mongo(self.logger)
self.rpc_connection = Proxy(
f"http://{os.environ['CRYPTO_USER']}:{os.environ['CRYPTO_PASS']}@"
f"127.0.0.1:{os.environ['CRYPTO_PORT']}")
self.tx_cache = TxCache()
def __init__(self):
log.debug("[Startup]: Initializing YouTube Module . . .")
self.mongo = mongo.Mongo()
self.queue = Queue()
self.cache = ExpiringDict(max_age_seconds=10800, max_len=1000)
self.search_cache = dict()
self.session = aiohttp.ClientSession()
def run(self):
for model in self.Models:
contents = model.run()
mongo.Mongo(model.target_save['ip'], model.target_save['port'],
model.target_save['db_name'],
model.target_save['db_table']).insert(contents)
print(str(len(contents)) + '件入りました')
def __init__(self, metier, localisation, email):
self.email = email
self.metier = metier
self.localisation = localisation
self.counter = 0
self.preprocess = pp.preprocessing()
self.db = mongo.Mongo()
def mongo(self):
m = mongo.Mongo(self.client_name, self.db_name)
m.upload_train_data(self.origin_data, self.feature_names,
'winequality-white_origin')
m.upload_train_data(self.train_data, self.feature_names,
'winequality-white_train')
m.upload_train_data(self.validation_data, self.feature_names,
'winequality-white_validation')
m.upload_choice_matrix(self.choice_matrix)
def submitPurchase(request):
connection = mongo.Mongo()
context = {}
# recieve = request.GET.get('send')
# print(recieve[u'typeId'])
connection.updateInstrument(1, 99)
print "PURCHASE"
# test()
# send_mail()
test.delay()
return JsonResponse(context)
def index_sub():
import mongo
email = request.form['mail']
mongo = mongo.Mongo()
cond = mongo.check_mail(email)
if cond:
mongo.add_email(email)
message = 'Votre email à été ajoutée à la liste !'
else:
message = 'Veuillez entrer un email valide'
return render_template("scripts.html",message = message)
def getCurrent(request):
connection = mongo.Mongo()
r_server = MyRedis.getServer(self=MyRedis)
r_server.incr('getCurrent_counter')
recieve = json.loads(request.GET.get('send'))
# items = Instrument.objects.filter(type="1", id=recieve[u'currentId'])\
# .values('id', 'manufacturer__name', 'model', 'type', 'coast')
# json_items = json.dumps(list(items), default=decimal_default)
json_items = json.dumps(connection.getInstrumentById(
recieve[u'currentId']),
default=decimal_default)
context = {'content': json_items, 'information': 'INFOOOO'}
print 'getCurrent total count ' + r_server.get('getCurrent_counter')
return JsonResponse(context)
def register():
if request.method == 'POST':
users = mongo.db.users
existing_user = users.find_one({'user_email' : request.form['email']})
if existing_user is None:
DB = mongo.Mongo()
hashpass = bcrypt.hashpw(request.form['pass'].encode('utf-8'), bcrypt.gensalt())
DB.add_user(request.form['email'])
users.insert_one({'name':request.form['username'], 'password': hashpass})
session['username'] = request.form['username']
return redirect(url_for('index'))
return 'That username already exists!'
return render_template('register.html')
def __init__(self, bot):
self.dictionary = {}
self.bot = bot
self.log = logging_manager.LoggingManager()
self.spotify = spotify.Spotify()
self.youtube = youtube.Youtube()
self.lastfm = lastfm.LastFM()
self.mongo = mongo.Mongo()
bot.remove_command("help")
self.log.debug("[Startup]: Initializing Music Module . . .")
def generate_key(length):
letters = string.ascii_letters
response = ""
for a in range(0, length):
response += random.choice(letters)
return response
restart_key = generate_key(64)
asyncio.run_coroutine_threadsafe(self.mongo.set_restart_key(restart_key), self.bot.loop)
if not discord.opus.is_loaded():
discord.opus.load_opus("/usr/lib/libopus.so")
def itemList(request):
connection = mongo.Mongo()
r_server = MyRedis.getServer(self=MyRedis)
r_server.incr('itemList_counter')
recieve = json.loads(request.GET.get('send'))
print("Recieve: ")
print(recieve)
if (recieve[u'searchParams'] == {}):
# items = Instrument.objects.filter(type=str(recieve[u'typeId'])) \
# .values('id', 'manufacturer__name', 'model', 'type', 'coast')
json_items = json.dumps(
connection.getInstrumentsByType(str(recieve[u'typeId']))) # mongo
# items = connection.getInstrumentsByType(str(recieve[u'typeId'])) # mongo
else:
search = recieve[u'searchParams']
searchType = search[u'searchType']
searchValue = search[u'searchValue']
if (searchType == u'By manufacturer'):
# items = Instrument.objects.filter(type=str(recieve[u'typeId']), manufacturer__name=str(searchValue))\
# .values('id', 'manufacturer__name', 'model', 'type', 'coast')
json_items = json.dumps(
connection.getInstrumentByManufacturer(str(searchValue)))
if (searchType == u'By model'):
# items = Instrument.objects.filter(type=str(recieve[u'typeId']), model__search=str(searchValue))\
# .values('id', 'manufacturer__name', 'model', 'type', 'coast')
json_items = json.dumps(
connection.getInstrumentByModel(str(searchValue)))
if (searchType == u'By cost'):
# items = Instrument.objects.filter(type=str(recieve[u'typeId']), coast=searchValue)\
# .values('id', 'manufacturer__name', 'model', 'type', 'coast')
json_items = json.dumps(
connection.getInstrumentByCost(str(searchValue)))
# itemsLength = len(items)
# print("SPLIT")
# print(splitQuery(items))
# print(len(splitQuery(items)))
# splitted = splitQuery(items)
# items = searchCase[searchType]
# print("Items: ")
# print(items)
# json_items = json.dumps(list(splitted[int(recieve[u'pageId']) - 1]), default=decimal_default)
# print("JSON Items: ")
# print(json_items)
# print "HERE I AM"
# for document in items:
# print document
# context = {'content': items,
# 'pageCount': 1}
# connection.insertInstrument()
# print "HERE I AM"
# print json_items
# for document in json_items:
# print document
context = {'content': json_items, 'pageCount': 1}
print 'itemList total count ' + r_server.get('itemList_counter')
return JsonResponse(context)
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Tue Apr 9 10:12:53 2019
@author: zanea
"""
import mongo
import preProcessing
import re
mongo = mongo.Mongo()
df = mongo.get_df()
def process_location(location):
""" Extrait le code postal (pour l'IDF) ou la ville (pour les autres villes),
puis le classe dans la catégorie 'Bassin_emploi' correspondante. """
import villes_csv
location = location.lower()
# Extraction de la ville et du le code postal
localisation = re.findall(r'(.*) \(?', location)[0]
cp = int(re.findall(r'.* \(([0-9]*).*', location)[0])
bassin_emploi = villes_csv.get_circo(cp)
return bassin_emploi, localisation
def run(self):
for model in self.Models:
model = model.run()
mongo.Mongo('erobloadPortal', 'contents').insert(model)
print(len(model))
print('件入りました')
def run_models(self):
import mongo
# Importation de la base de données en dataframe
mongo = mongo.Mongo()
df = mongo.get_df()
cols = ['Bassin_emploi', 'Compagny', 'Contrat', 'Date', 'Date_scrap', 'Location', 'Poste', 'Resume', 'Salary', '_id','Forest','RBF']
df = pd.DataFrame(df,columns=cols)
# Sélection des données qui comportent un salaire
data = df[['Bassin_emploi', 'Contrat', 'Poste', 'Salary']][df['Salary'] != '']
# Encodage des données en numérique
data = pd.get_dummies(data=data, columns={'Poste', 'Bassin_emploi', 'Contrat'}, drop_first=True)
# Séparation des données indépendantes/target
x = data.iloc[:, 1:]
y = data['Salary'].astype('int64')
x_train, x_test, y_train, y_test = train_test_split(x, y)
# Implantation du Kernel RBF
rbf = SVC()
parameters = {'kernel': ['rbf'],
'gamma': [1e-3, 1e-4],
'C': [1, 10, 100, 1000],
'shrinking' : [True, False]}
clf_rbf = GridSearchCV(rbf, parameters, cv=5)
clf_rbf.fit(x_train, y_train)
clf_rbf.best_params_
y_pred_rbf = clf_rbf.predict(x_test)
# # Comparaison données test/entraînement > seulement pour les tests
# plt.scatter(range(len(y_test)), y_test, color = 'blue')
# plt.scatter(range(len(y_pred_rbf)), y_pred_rbf, color = 'red')
# plt.legend(('Training set', 'Test set'))
# plt.title('Comparaison des résultats avec le modèle Kernel RBF')
# Implantation du Random Forest
rf = RandomForestClassifier()
parameters = grid_param = {'n_estimators': [100, 300, 500, 800, 1000],
'criterion': ['gini', 'entropy'],
'bootstrap': [True, False]}
clf_rf = GridSearchCV(rf, parameters, cv=5)
clf_rf.fit(x_train, y_train)
clf_rf.best_params_
y_pred_rf = clf_rf.predict(x_test)
# # Score du modèle
# accuracy_score(y_test, y_pred_rf)
# f1_score(y_test, y_pred_rf, average='micro')
# all_accuracies = cross_val_score(estimator=clf_rf, X=x_train, y=y_train, cv=5)
# # Comparaison données test/entraînement > seulement pour les tests
# plt.scatter(range(len(y_test)), y_test, color = 'blue')
# plt.scatter(range(len(y_pred_rf)), y_pred_rf, color = 'red')
# plt.legend(('Training set', 'Test set'))
# plt.title('Comparaison des résultats avec le modèle Random Forest')
# Prédiction : ajout dans la DB Mongo
data_to_pred = df[['Bassin_emploi', 'Contrat', 'Poste', '_id']][df['Salary'] == '']
data_to_pred = pd.get_dummies(data=data_to_pred, columns={'Poste', 'Bassin_emploi', 'Contrat'}, drop_first=True)
data_to_pred['Salaires_RBF'] = clf_rbf.predict(data_to_pred.iloc[:, 1:])
data_to_pred['Salaires_Random_Forest'] = clf_rf.predict(data_to_pred.iloc[:, 1:-1])
final_data = data_to_pred[['_id', 'Salaires_RBF', 'Salaires_Random_Forest']]
indexes = final_data.index
for i in indexes:
forest = final_data.loc[i,'Salaires_Random_Forest']
rbf = final_data.loc[i,'Salaires_RBF']
df.loc[i,'Forest'] = forest
df.loc[i,'RBF'] = rbf
if mongo.final_df(df):
print('DB updated')
return True
# -*- coding: utf-8 -*-
"""
Éditeur de Spyder
Ceci est un script temporaire.
"""
import dash
import dash_core_components as dcc
import dash_html_components as html
import dash_table
import pandas as pd
import mongo
db = mongo.Mongo()
df = db.get_df()
external_stylesheets = ['https://codepen.io/chriddyp/pen/bWLwgP.css']
app = dash.Dash(__name__, external_stylesheets=external_stylesheets)
app.layout = html.Div(children=[
html.H1(children="DB"),
dash_table.DataTable(
id='table',
columns=[{"name": i, "id": i} for i in df.columns],
data=df.to_dict("rows"),
style_table={
'maxHeight': '300',
'overflowY': 'scroll'
},
class Spider(object):
base_url = "http://weixin.sogou.com/weixin" #基本url
key_word = 'AI' #搜搜关键词
#list_url = [] #存储url和其callback 函数
#list_item = [] #临时存储url和callback函数， 只存储两个数据，添加到list_url 后，应该立即清空
#session = requests.Session() #开始设置
"""
headers = {
'Accept':'text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8',
'Accept-Encoding':'gzip, deflate, sdch',
'Accept-Language':'zh-CN,zh;q=0.8',
'Cache-Control':'max-age=0',
'Connection':'keep-alive',
'Cookie':'sw_uuid=3334394017; sg_uuid=2065896719; dt_ssuid=853760490; pex=C864C03270DED3DD8A06887A372DA219231FFAC25A9D64AE09E82AED12E416AC; ssuid=8258541632; CXID=33A866F87888D6C8D1A553B76F2BADCA; SUV=00C02729B46B344C5B72F4ADF43D0798; ad=Vyllllllll2bt0CzlllllVHCuHYlllllWWn@vlllll9lllll9Vxlw@@@@@@@@@@@; SUID=53DA31773765860A5B11413D000B34E8; pgv_pvi=431889408; ABTEST=0|1534575838|v1; weixinIndexVisited=1; SUIR=CBA7F587B6B0C605F48511D2B6DE9810; ld=cyllllllll2bNDvxlllllVHThntlllllGUlvKyllllGlllll9klll5@@@@@@@@@@; LSTMV=385%2C26; LCLKINT=3828; ppinf=5|1534577030|1535786630|dHJ1c3Q6MToxfGNsaWVudGlkOjQ6MjAxN3x1bmlxbmFtZToyOkJDfGNydDoxMDoxNTM0NTc3MDMwfHJlZm5pY2s6MjpCQ3x1c2VyaWQ6NDQ6bzl0Mmx1RkZDdlpaY1dsTmdsalgwYzd4dE1iY0B3ZWl4aW4uc29odS5jb218; pprdig=R6R352FfiGDW1H3tvcqyhorgCkT3odPRYTPZ6thnUHaWCcL8UwwFEC0W9gzyUhzku8ScAL6CKkabRXXTfE-0dh1--l0JtsESkg17NAfPWozGHDP-9Cvpu2Ptq3VSXL_WM0U0R_tAFMHYEKwu3nrfiziia6XaFgqf5RrLXJuDUa0; sgid=16-36640129-AVt3yYYDq8t3XJ2MTXx5PMc; SNUID=9A8F42F88286F68589E463E1837385F0; IPLOC=CN2200; JSESSIONID=aaafIZVUumv_l7fFtEBvw; pgv_si=s8715192320; ppmdig=1535095739000000e7ea71c241fae9486d10ed0a4333c9a9; sct=14',
'DNT':'1',
'Host':'weixin.sogou.com',
'Upgrade-Insecure-Requests':'1',
'User-Agent':'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/55.0.2883.87 Safari/537.36',
}
"""
cookies = {
'sw_uuid': '3334394017',
'sg_uuid': '2065896719',
'dt_ssuid': '853760490',
'pex':
'C864C03270DED3DD8A06887A372DA219231FFAC25A9D64AE09E82AED12E416AC',
'ssuid': '8258541632',
'CXID': '33A866F87888D6C8D1A553B76F2BADCA',
'SUV': '00C02729B46B344C5B72F4ADF43D0798',
'ad':
'Vyllllllll2bt0CzlllllVHCuHYlllllWWn@vlllll9lllll9Vxlw@@@@@@@@@@@',
'SUID': '53DA31773765860A5B11413D000B34E8',
'pgv_pvi': '431889408',
'ABTEST': '0|1534575838|v1',
'weixinIndexVisited': '1',
'ld':
'cyllllllll2bNDvxlllllVHThntlllllGUlvKyllllGlllll9klll5@@@@@@@@@@',
'LSTMV': '385%2C26',
'LCLKINT': '3828',
'SNUID': '9A8F42F88286F68589E463E1837385F0',
'IPLOC': 'CN2200',
'pgv_si': 's3126373376',
'sct': '17',
'JSESSIONID': 'aaaYnzdJQDdUUguOHzBvw',
'ppinf':
'5|1535195192|1536404792|dHJ1c3Q6MToxfGNsaWVudGlkOjQ6MjAxN3x1bmlxbmFtZToyOkJDfGNydDoxMDoxNTM1MTk1MTkyfHJlZm5pY2s6MjpCQ3x1c2VyaWQ6NDQ6bzl0Mmx1RkZDdlpaY1dsTmdsalgwYzd4dE1iY0B3ZWl4aW4uc29odS5jb218',
'pprdig':
'eUprT1c-kM2bGGGiLWMW1FXo7TtbFMefITQzQeMOrxkE4dDJgEM15cuAXV1rcjDAXQR4-eqOc7Ycf8F7GwrWUylY1QiEjvrz-cMiEyjtWWMWAf8fkG4G5ZHbMpk0HR14pjbMQZGjZlrS57ZDsIiv3l_uGA5SpI7dIflpnoMu-ok',
'sgid': '16-36640129-AVuBODg3a8UkW2FdLzwf2W4',
'ppmdig': '1535195193000000ecfc6e6a5c33bb04d8a46936b64d2333'
}
csvfile = open("url.csv", "a", encoding="utf-8", newline='')
writer = csv.writer(csvfile)
browser = webdriver.Firefox() #声明浏览器
browser.get(base_url)
#添加cookie
for key, value in cookies.items():
name = key
value = value
cookie = {
'name': name,
'value': value,
}
browser.add_cookie(cookie)
mongo = mongo.Mongo() #类的实例化
redis = db.Redis() #redis 的实例化
def start(self):
"""
初始化，用来初始list_item 和 list_url
"""
#self.session.headers.update(self.headers)
url = self.base_url + "?" + parse.urlencode({
'type': '2',
"query": self.key_word,
})
url_item = [url, self.parse_index]
self.redis.push(url_item)
#self.list_url.append(url_item)
def parse_index(self, html):
"""
用于解析每个页面的链接，返回的值为url 和 调度函数组成的列表
"""
print("链接页")
try:
doc = pq(html)
items = doc('.news-list h3 a').items()
for item in items:
url = item.attr['href'].replace("amp:", "")
self.writer.writerow([url]) #写入csv
url_item = [url, self.parse_detail]
yield url_item
except:
print("url提取错误")
doc = pq(html)
next_page = doc("#sogou_next").attr['href']
url = self.base_url + str(next_page)
url_item = [url, self.parse_index]
yield url_item
def parse_detail(self, html):
"""
用于解析每页的文章的详细信息， 返回的信息为dic
"""
print("详情页")
try:
doc = pq(html)
data = {
'title': doc('#activity-name').text(),
'content': doc(".rich_media_content").text()
}
except:
print("文章内容提取出错")
else:
yield data
def request(self, url):
try:
time.sleep(3)
self.browser.get(url)
time.sleep(5)
sroll_cnt = 0
while True:
if sroll_cnt < 5:
self.browser.execute_script('window.scrollBy(0, 1000)')
time.sleep(1)
sroll_cnt += 1
else:
break
html = self.browser.page_source #获取网页源代码
except:
print("获取源代码错误")
else:
if len(html) != 0:
return html
else:
print("获取源代码错误")
return html
def scheduler(self):
"""
用于调度程序
"""
self.redis.delete() #决定是否重新开始
if self.redis.llen(): #列表长度为空，则完成初始化
self.start()
while True:
if not self.redis.llen():
url_item = self.redis.pop()
url = url_item[0]
callback = url_item[1]
print("schedulering url:", url)
html = self.request(url)
for item in callback(html):
if isinstance(item, dict):
self.mongo.save(item)
elif isinstance(item, list):
self.redis.push(item) #存储到redis
else:
print("url队列已经空了！")
break
def run(self):
self.scheduler()
