def get_data_from_co2_signal(latitude, longitude, country_code_default):
if Ecomix.co2_signal_key is not None:
try:
now = datetime.utcnow().replace(tzinfo=UTC)
country_code = Ecomix.get_country(latitude, longitude,
country_code_default)
assert country_code is not None
if country_code not in Ecomix._cache:
Ecomix._cache[country_code] = []
elif len(Ecomix._cache[country_code]) > 0 and \
(now - Ecomix._cache[country_code][-1][0]).total_seconds() < CO2_SIGNAL_REQ_INTERVAL:
return False
res = requests.get(
CO2_SIGNAL_URL + "/v1/latest",
headers={"auth-token": Ecomix.co2_signal_key},
params={"countryCode": country_code})
data = res.json()
value = data["data"]["carbonIntensity"]
assert isinstance(value, numbers.Number)
Ecomix._cache[country_code].append([now, value])
return data["status"] == "ok"
except (AssertionError, NameError, KeyError):
logger.debug("ecomix:", exc_info=True)
return False
else:
return False
def doWork(self):
'''重写WorkRequest类的线程执行函数，此函数将在线程池中执行，
功能：从为自己分配的下载队列中取出url进行下载
'''
logger.debug('Start downloader`s doWork...')
# self.test()
while True:
if self.__dlQueue.qsize() > 0:
urlNode = self.__dlQueue.get()
self.__downloadingFlag += 1
page = self.__downloadPage(urlNode.url)
if len(page) == 0:
self.__downloadingFlag -= 1
continue
# logger.debug('download page success, url: %s', urlNode.url)
# 将下载的html页面封装为内部数据格式并添加到html队列供解析模块解析
htmlNode = HtmlModel(urlNode.url, page, timestamp(), urlNode.depth)
self.__htmlQueue.put(htmlNode)
self.__downloadingFlag -= 1
# 检测退出事件
if self.__exitEvent.is_set():
logger.info('Download model quit...')
return
# 下载时间间隔
time.sleep(FETCH_TIME_INTERVAL)
def parse(line):
match = pattern.match(line)
if match:
vpn_account = match.group(1)
logger.debug('find vpn account {}', vpn_account)
return vpn_account
return None
def refresh_remote_token(self, force=False):
if not force and self.remote_token_last_update is not None:
last_update: datetime = self.remote_token_last_update
if (datetime.now() - last_update).total_seconds() < MQTT_TOKEN_TTL:
return None
self.refresh_token()
try:
if self.remote_refresh_token is None:
logger.error("remote_refresh_token isn't defined")
self.load_otp(force_new=True)
res = self.manager.post(REMOTE_URL + self.client_id,
json={"grant_type": "refresh_token", "refresh_token": self.remote_refresh_token},
headers=self.headers)
data = res.json()
logger.debug("refresh_remote_token: %s", data)
if "access_token" in data:
self.remote_access_token = data["access_token"]
self.remote_refresh_token = data["refresh_token"]
self.remote_token_last_update = datetime.now()
else:
logger.error("can't refresh_remote_token: %s\n Create a new one", data)
self.remote_token_last_update = datetime.now()
otp_code = self.get_otp_code()
res = self.get_remote_access_token(otp_code)
self.mqtt_client.username_pw_set("IMA_OAUTH_ACCESS_TOKEN", self.remote_access_token)
self.save_config()
return res
except RequestException as e:
logger.error("Can't refresh remote token %s", e)
sleep(60)
return None
def createWorkers(self, threadNum, pollTimeout):
'''创建工作线程并将它们添加到线程池中'''
logger.debug('Start create work thread...')
for i in range(min(MAX_THREAD_NUM, threadNum)):
# 为工作线程传递任务队列
self.__workers.append(
WorkerThread(self.__requestsQueue, pollTimeout))
def read_file_trans(fn):
nlp = train_ner_cn.init_model_4_pred(
'../../../guiyang_real_population_address/trunk/models/ner')
result = {}
cont = ''
with open(fn, 'rb') as g:
cont = g.read().decode('utf-8')
lines = cont.split('\n')
np.random.shuffle(lines)
cnt = 0
for line in lines[:3000]:
try:
json_result = __pred(line, nlp)
#json_result = test(line)
#json_result = pred(line, nlp)
logger.debug(json_result)
k = tuple(json_result.items())[0][0]
v = tuple(json_result.items())[0][1]
result[k] = v
logger.debug('最终保存样本是')
logger.debug(k)
logger.debug(v)
cnt += 1
if cnt % 100 == 0:
logger.debug(cnt)
except BaseException:
traceback.print_exc()
continue
with open("./ner_train.json", 'w') as json_file:
json.dump(result, json_file)
return 0
def test_extractEntities(self):
file= u'/tmp/esx-w2-erqa230-2014-05-09--23.23/var/log/hostd.log'
patterns = ['\d\d\d\d-\d\d-\d\dT\d\d:\d\d:\d\d\.\d\d\dZ.*/(?P<entity>.*\.vmx).*Failed to load virtual machine: vim.fault.FileNotFound']
entities = set()
extractEntities(file, patterns, entities)
logger.debug(entities)
self.assertEqual(len(entities), 2)
def __on_mqtt_message(self, client, userdata, msg):
try:
logger.info("mqtt msg %s %s", msg.topic, msg.payload)
data = json.loads(msg.payload)
charge_info = None
if msg.topic.startswith(MQTT_RESP_TOPIC):
if "return_code" not in data:
logger.debug("mqtt msg hasn't return code")
elif data["return_code"] == "400":
self.refresh_remote_token(force=True)
logger.error("retry last request, token was expired")
elif data["return_code"] == "300":
logger.error('%s', data["return_code"])
elif data["return_code"] != "0":
logger.error('%s : %s', data["return_code"], data["reason"])
if msg.topic.endswith("/VehicleState"):
charge_info = data["resp_data"]["charging_state"]
self.precond_programs[data["vin"]] = data["resp_data"]["precond_state"]["programs"]
elif msg.topic.startswith(MQTT_EVENT_TOPIC):
charge_info = data["charging_state"]
if charge_info is not None and charge_info['remaining_time'] != 0 and charge_info['rate'] == 0:
# fix a psa server bug where charge beginning without status api being properly updated
logger.warning("charge begin but API isn't updated")
sleep(60)
self.wakeup(data["vin"])
except KeyError:
logger.exception("mqtt message:")
def record_info(self, car: Car):
mileage = car.status.timed_odometer.mileage
level = car.status.get_energy('Electric').level
level_fuel = car.status.get_energy('Fuel').level
charge_date = car.status.get_energy('Electric').updated_at
moving = car.status.kinetic.moving
longitude = car.status.last_position.geometry.coordinates[0]
latitude = car.status.last_position.geometry.coordinates[1]
altitude = car.status.last_position.geometry.coordinates[2]
date = car.status.last_position.properties.updated_at
if date is None:
date = charge_date
logger.debug("vin:%s longitude:%s latitude:%s date:%s mileage:%s level:%s charge_date:%s level_fuel:"
"%s moving:%s", car.vin, longitude, latitude, date, mileage, level, charge_date, level_fuel,
moving)
Database.record_position(self.weather_api, car.vin, mileage, latitude, longitude, altitude, date, level,
level_fuel, moving)
self.abrp.call(car, Database.get_last_temp(car.vin))
try:
charging_status = car.status.get_energy('Electric').charging.status
charging_mode = car.status.get_energy('Electric').charging.charging_mode
Charging.record_charging(car, charging_status, charge_date, level, latitude, longitude, self.country_code,
charging_mode)
logger.debug("charging_status:%s ", charging_status)
except AttributeError:
logger.error("charging status not available from api")
def doWork(self):
'''重写WorkRequest类的线程执行函数，此函数将在线程池中执行'''
logger.debug('Start storage`s doWork...')
if not self.__initDB():
logger.error('Storage thread is stop.')
return
conn = sqlite3.connect(self.__dbPath)
cur = conn.cursor()
while True:
try:
# 从data队列获取数据并插入数据库
if self.__dataQueue.qsize() > 0:
data = self.__dataQueue.get()
sqlInsert = '''INSERT INTO zspider(url, time, depth) VALUES ('%s', '%s', %d)''' % (data.url, data.time, data.depth)
cur.execute(sqlInsert)
conn.commit()
else:
time.sleep(1)
except Exception, e:
logger.error('Database operate exception: %s ', str(e))
continue
# 检测退出事件
if self.__exitEvent.is_set():
cur.close()
conn.close()
logger.info('Storage model quit...')
return
def call(self, car: Car, ext_temp: float = None):
try:
if self.token is None or len(self.token) == 0:
logger.debug("No abrp token provided")
elif car.vin in self.abrp_enable_vin:
energy = car.status.get_energy('Electric')
tlm = {"utc": int(datetime.timestamp(energy.updated_at)),
"soc": energy.level,
"speed": getattr(car.status.kinetic, "speed", None),
"car_model": car.get_abrp_name(),
"current": car.status.battery.current,
"is_charging": energy.charging.status == "InProgress",
"lat": car.status.last_position.geometry.coordinates[1],
"lon": car.status.last_position.geometry.coordinates[0],
"power": energy.consumption
}
if ext_temp is not None:
tlm["ext_temp"] = ext_temp
params = {"tlm": json.dumps(tlm), "token": self.token, "api_key": self.api_key}
response = requests.request("POST", self.url, params=params, proxies=self.proxies,
verify=self.proxies is None)
logger.debug(response.text)
return response.json()["status"] == "ok"
except (AttributeError, IndexError, ValueError):
logger.exception("abrp:")
return False
def getTgzFiles(folder_path):
page = BeautifulSoup(urlopen(folder_path).read())
urls = []
logger.debug(folder_path)
for link in page.findAll('a', href=re.compile(r'.*\.tgz')):
urls.append(folder_path + '/' + link['href'])
return urls
def doWork(self):
'''重写WorkRequest类的线程执行函数，此函数将在线程池中执行，
功能：从为自己分配的下载队列中取出url进行下载
'''
logger.debug('Start downloader`s doWork...')
# self.test()
while True:
if self.__dlQueue.qsize() > 0:
urlNode = self.__dlQueue.get()
self.__downloadingFlag += 1
page = self.__downloadPage(urlNode.url)
if len(page) == 0:
self.__downloadingFlag -= 1
continue
# logger.debug('download page success, url: %s', urlNode.url)
# 将下载的html页面封装为内部数据格式并添加到html队列供解析模块解析
htmlNode = HtmlModel(urlNode.url, page, timestamp(),
urlNode.depth)
self.__htmlQueue.put(htmlNode)
self.__downloadingFlag -= 1
# 检测退出事件
if self.__exitEvent.is_set():
logger.info('Download model quit...')
return
# 下载时间间隔
time.sleep(FETCH_TIME_INTERVAL)
def doWork(self):
'''重写WorkRequest类的线程执行函数，此函数将在线程池中执行'''
logger.debug('Start storage`s doWork...')
if not self.__initDB():
logger.error('Storage thread is stop.')
return
conn = sqlite3.connect(self.__dbPath)
cur = conn.cursor()
while True:
try:
# 从data队列获取数据并插入数据库
if self.__dataQueue.qsize() > 0:
data = self.__dataQueue.get()
sqlInsert = '''INSERT INTO zspider(url, time, depth) VALUES ('%s', '%s', %d)''' % (
data.url, data.time, data.depth)
cur.execute(sqlInsert)
conn.commit()
else:
time.sleep(1)
except Exception, e:
logger.error('Database operate exception: %s ', str(e))
continue
# 检测退出事件
if self.__exitEvent.is_set():
cur.close()
conn.close()
logger.info('Storage model quit...')
return
def publish(self, mqtt_request: MQTTRequest, store=True):
self._refresh_remote_token()
message = mqtt_request.get_message_to_json(
self.remoteCredentials.access_token)
logger.debug("%s %s", mqtt_request.topic, message)
self.mqtt_client.publish(mqtt_request.topic, message)
if store:
self.last_request = [mqtt_request]
def _clean_text(text, cleaner_names, verbose):
for name in cleaner_names:
cleaner = getattr(cleaners, name)
if not cleaner:
raise Exception('Unknown cleaner: %s' % name)
text = cleaner(text)
if verbose:
logger.debug(f"cleaned text: {text}")
return text
def refresh_vehicle_info(self):
if self.info_refresh_rate is not None:
while True:
sleep(self.info_refresh_rate)
logger.debug("refresh_vehicle_info")
for car in self.vehicles_list:
self.get_vehicle_info(car.vin)
for callback in self.info_callback:
callback()
def add_table(self, src, figure):
try:
table = Table(figure.id, src, figure)
table.date_columns = [
col["id"][:-4] for col in figure.columns
if col["type"] == "datetime" and col["id"].endswith("_str")
]
self.tables.append(table)
except AttributeError:
logger.debug("figure isn't a table")
def load_otp(filename="otp.bin"):
try:
with open(filename, 'rb') as input_file:
try:
return pickle.load(input_file)
except ModuleNotFoundError:
return RenameUnpickler(input_file).load()
except FileNotFoundError:
logger.debug("", exc_info=True)
return None
def get_value_or_default(self, key):
val = getattr(self, key, None)
if val is None:
field = self.__mappings__[key]
if field.default is not None:
val = field.default() if callable(
field.default) else field.default
logger.debug('using default value for {}:{}'.format(
key, str(val)))
setattr(self, key, val)
return val
def clean_position(conn):
res = conn.execute(
"SELECT Timestamp,mileage,level from position ORDER BY Timestamp DESC LIMIT 3;"
).fetchall()
# Clean DB
if len(res) == 3 and res[0]["mileage"] == res[1]["mileage"] == res[2]["mileage"] and \
res[0]["level"] == res[1]["level"] == res[2]["level"]:
logger.debug("Delete duplicate line")
conn.execute("DELETE FROM position where Timestamp=?;",
(res[1]["Timestamp"], ))
conn.commit()
def parse_log_file(log_file):
with open(log_file, encoding='gb18030') as file:
for line in file:
vpn_account = parse(line)
if vpn_account:
if not vpn_account in summary_data:
summary_data[vpn_account] = 1
else:
summary_data[vpn_account] += 1
else:
logger.debug('not find vpn account in {}', line)
def extractFiles(paths):
dirs = []
for path in paths:
directory = path[0:path.rfind('.')]
if os.path.exists(directory):
logger.debug("%s already exists, won't extract again" % directory)
dirs.append(directory)
continue
logger.debug("extracting file %s" % path)
extractFile(path)
dirs.append(directory)
return dirs
def gen_qrcode(self):
url = 'https://login.weixin.qq.com/l/' + self.uuid
logger.debug("qrcode url:%s", url)
qr = qrcode.QRCode()
qr.border = 1
qr.add_data(url)
qr.make()
# img = qr.make_image()
# img.save("qrcode.png")
# mat = qr.get_matrix()
# self._printQR(mat) # qr.print_tty() or qr.print_ascii()
qr.print_ascii(invert=True)
def doWork(self):
'''重写WorkRequest类的线程执行函数，此函数将在线程池中执行'''
logger.debug('Start parser`s doWork...')
while True:
if self.__htmlQueue.qsize() > 0:
self.__parsePage()
else:
time.sleep(1)
#检测退出事件
if self.__exitEvent.is_set():
logger.info('Parser model quit...')
return
def __refresh_vehicle_info(self):
if self.info_refresh_rate is not None:
while True:
try:
logger.debug("refresh_vehicle_info")
for car in self.vehicles_list:
self.get_vehicle_info(car.vin)
for callback in self.info_callback:
callback()
except: # pylint: disable=bare-except
logger.exception("refresh_vehicle_info: ")
sleep(self.info_refresh_rate)
def doWork(self):
'''重写WorkRequest类的线程执行函数，此函数将在线程池中执行'''
logger.debug('Start parser`s doWork...')
while True:
if self.__htmlQueue.qsize() > 0:
self.__parsePage()
else:
time.sleep(1)
#检测退出事件
if self.__exitEvent.is_set():
logger.info('Parser model quit...')
return
def load_cars(name=None):
if name is None:
name = Cars().config_filename
try:
with open(name, "r", encoding="utf-8") as file:
json_str = file.read()
cars = Cars.from_json(json.loads(json_str))
cars.config_filename = name
cars.save_cars()
return cars
except (FileNotFoundError, TypeError) as ex:
logger.debug(ex)
return Cars()
def downloadSupportBundles(url):
urls = processUrl(url)
if urls is None:
return "Error: no tgz files found!"
else:
hash1 = hashlib.sha1()
for url1 in urls:
hash1.update(url1)
# new dir name
newdir = hash1.hexdigest()
logger.debug("directory name for url %s is %s" % (url, newdir))
local_paths = downloadFiles(newdir, urls)
return local_paths
def dismissWorkers(self, threadNum, doJoin = False):
'''停用工作线程，doJoin为True则等待线程结束再返回,否则直接返回'''
logger.debug('Dismiss worker thread, Num : %d ', threadNum)
tmpList = []
for i in range(min(threadNum, len(self.__workers))):
worker = self.__workers.pop()
worker.dismiss()
tmpList.append(worker)
if doJoin:
for worker in tmpList:
worker.join()
else:
self.__dismissedWorkers.extend(tmpList)
def _load_dict_from_file():
current_dir = Path(__file__).resolve().parent
t1 = time.time()
acronymn_list = []
print(os.getcwd())
with open(current_dir / '/home/shihangyu/Scripts/tacotron2-nvidia-ysh/text/cleaner/wikipedia-acronyms-simple.json','r') as f:
while True:
text = f.readline()
if text == '':
break
acronymn_list.append(text.strip())
logger.debug(f'load acronymn dict use time {time.time() - t1}')
return acronymn_list
def doTransform(self):
sourceFiles = self.sourceFiles()
logger.info("transform {} source files", len(sourceFiles))
for dataEntry in self.dictData:
logger.debug("process 学号: {}/报名号: {}", int(dataEntry['学号']),
dataEntry['报名号'])
sourcePath1 = os.path.join(self.inputDir,
str(dataEntry['证件号码']) + ".jpg")
sourcePath2 = os.path.join(self.inputDir,
str(int(dataEntry['考生编号'])) + ".jpg")
sourcePath3 = os.path.join(
self.inputDir, '10673_18_' + str(dataEntry['报名号']) + ".jpg")
targetPath = os.path.join(self.outputDir,
str(int(dataEntry['学号'])) + ".jpg")
if os.path.exists(sourcePath1):
logger.debug("rename from (证件号码) {} to {}", sourcePath1,
targetPath)
os.rename(sourcePath1, targetPath)
elif os.path.exists(sourcePath2):
logger.debug("rename from (考生编号) {} to {}", sourcePath2,
targetPath)
os.rename(sourcePath2, targetPath)
elif os.path.exists(sourcePath3):
logger.debug("rename from (10673_18_报名号) {} to {}",
sourcePath3, targetPath)
os.rename(sourcePath3, targetPath)
else:
logger.warn("source file for {} does not exit, skip it",
int(dataEntry['学号']))
def dismissWorkers(self, threadNum, doJoin=False):
'''停用工作线程，doJoin为True则等待线程结束再返回,否则直接返回'''
logger.debug('Dismiss worker thread, Num : %d ', threadNum)
tmpList = []
for i in range(min(threadNum, len(self.__workers))):
worker = self.__workers.pop()
worker.dismiss()
tmpList.append(worker)
if doJoin:
for worker in tmpList:
worker.join()
else:
self.__dismissedWorkers.extend(tmpList)
def record_charging(
car,
charging_status,
charge_date: datetime,
level,
latitude, # pylint: disable=too-many-locals
longitude,
country_code,
charging_mode,
charging_rate,
autonomy):
conn = Database.get_db()
charge_date = charge_date.replace(microsecond=0)
if charging_status == "InProgress":
stop_at, start_at = conn.execute(
"SELECT stop_at, start_at FROM battery WHERE VIN=? ORDER BY start_at "
"DESC limit 1", (car.vin, )).fetchone() or [False, None]
try:
conn.execute(
"INSERT INTO battery_curve(start_at,VIN,date,level,rate,autonomy) VALUES(?,?,?,?,?,?)",
(start_at, car.vin, charge_date, level, charging_rate,
autonomy))
except IntegrityError:
logger.debug("level already stored")
if stop_at is not None:
conn.execute(
"INSERT INTO battery(start_at,start_level,charging_mode,VIN) VALUES(?,?,?,?)",
(charge_date, level, charging_mode, car.vin))
Ecomix.get_data_from_co2_signal(latitude, longitude, country_code)
else:
try:
start_at, stop_at, start_level = conn.execute(
"SELECT start_at, stop_at, start_level from battery WHERE VIN=? ORDER BY start_at DESC limit 1",
(car.vin, )).fetchone()
in_progress = stop_at is None
except TypeError:
logger.debug("battery table is probably empty :",
exc_info=True)
in_progress = False
if in_progress:
co2_per_kw = Ecomix.get_co2_per_kw(start_at, charge_date,
latitude, longitude,
country_code)
consumption_kw = (level -
start_level) / 100 * car.battery_power
Charging.update_chargings(conn, start_at, charge_date, level,
co2_per_kw, consumption_kw, car.vin)
conn.commit()
conn.close()
def _run(self, str, func, *args):
logger.debug(str)
if func(*args):
logger.debug('%s... 成功' % (str))
else:
logger.debug('%s... 失败' % (str))
logger.debug('[*] 退出程序')
exit(1)
def retrieve_messages(self):
url = self.base_uri + '/webwxsync?sid=%s&skey=%s&pass_ticket=%s' % (self.sid, self.skey, self.pass_ticket)
dic = self._post(url, {'BaseRequest': self.BaseRequest,
'SyncKey': self.SyncKey,
'rr': ~int(time.time())
})
if dic == '':
return None
logger.debug("retrieve message: %s", dic)
if dic['BaseResponse']['Ret'] == 0:
self.SyncKey = dic['SyncKey']
self.synckey = '|'.join(["%s_%s" % (keyVal['Key'], keyVal['Val']) for keyVal in self.SyncKey['List']])
return dic['AddMsgList']
def doTransform(self):
sourceFiles = self.sourceFiles()
logger.info("transform {} source files", len(sourceFiles))
for dataEntry in self.dictData:
logger.debug("process 学号: {}/报名号: {}", int(dataEntry['学号']),
int(dataEntry['报名号']))
sourcePath = os.path.join(self.inputDir,
str(int(dataEntry['报名号'])) + ".jpg")
targetPath = os.path.join(self.outputDir,
str(int(dataEntry['学号'])) + ".jpg")
if not os.path.exists(sourcePath):
logger.warn("{} does not exit, skip it", sourcePath)
else:
logger.debug("rename {} to {}", sourcePath, targetPath)
os.rename(sourcePath, targetPath)
def get_otp_code(self):
self.mode = Otp.OTP_MODE
otp_code = None
if self.activation_start():
res = self.activation_finalyze()
if res != Otp.NOK:
if res == Otp.OTP_TWICE:
self.mode = Otp.OTP_MODE
self.activation_start()
self.activation_finalyze()
otp_code = self._get_otp_code()
logger.debug("otp code: %s", otp_code)
if otp_code is None:
raise ConfigException("Can't get otp code")
return otp_code
def start(self):
'''创建并启动各个模块'''
logger.debug('Init start urls...')
self.__initUrlQueue(self.__startUrls)
# 启动threadNum个下载器并为它们分配下载队列
logger.debug('Put downloader to thread pool...')
for i in range(self.__threadNum):
dlQueue = Queue.Queue()
self.__downloadQueueList.append(dlQueue)
downloadReq = Downloader(dlQueue, self.__downloadMode, self.__htmlQueue, self.__exitEvent, self.__downloadingFlag)
self.__threadPool.putRequest(downloadReq)
# 创建解析模块并添加到线程池运行
logger.debug('Put parser to thread pool...')
parserReq = Parser(self.__depth, self.__startUrls, self.__keyword, self.__htmlQueue, self.__dataQueue, self.__urlQueue, self.__exitEvent)
self.__threadPool.putRequest(parserReq)
# 创建存储模块并添加到线程池运行
logger.debug('Put storage to thread pool...')
storageReq = Storage(self.__dbName, self.__dataQueue, self.__exitEvent)
self.__threadPool.putRequest(storageReq)
# 主循环用于为各个下载队列分配url以及输出日志信息
logger.debug('start main loop...')
lastTime = time.time()
while True:
for dlQueue in self.__downloadQueueList:
if self.__urlQueue.qsize() > 0 and dlQueue.qsize() < 1:
node = self.__urlQueue.get()
dlQueue.put(node)
now = time.time()
if now - lastTime > PRINT_TIME_INTERVAL:
logger.info('URL QUEUE SIZE : %d', self.__urlQueue.qsize())
logger.info('HTML QUEUE SIZE : %d', self.__htmlQueue.qsize())
logger.info('DATA QUEUE SIZE : %d', self.__dataQueue.qsize())
logger.info('REPEAT SET SIZE : %d', parserReq.getRepeatSetSize())
# 延迟检测退出事件，防止程序启动时即退出
if now - lastTime > 30:
if self.__urlQueue.qsize() < 1 and self.__htmlQueue.qsize() < 1 and \
self.__dataQueue.qsize() < 1 and self.__downloadingFlag < 1:
self.__exitEvent.set()
self.__threadPool.close(True)
return
lastTime = now
def __initDB(self):
'''初始化数据库文件路径，并创建数据库'''
try:
dbDir = os.getcwd() + '/db/'
if not os.path.exists(dbDir):
os.makedirs(dbDir)
self.__dbPath = dbDir + self.__dbName
conn = sqlite3.connect(self.__dbPath)
sqlCreateTable = '''CREATE TABLE IF NOT EXISTS zspider(
id integer primary key, url text, html text, time text, depth integer)'''
conn.execute(sqlCreateTable)
conn.close()
logger.debug('Create database success.')
return True
except Exception, e:
logger.error('Init database error : %s', str(e))
return False
def downloadFile(local_new_dir, url):
filename = os.path.basename(url)
logger.debug("Downloading " + filename)
local_path = os.path.abspath(os.path.join(local_new_dir, filename))
if(os.path.exists(local_path)):
logger.debug("%s already exists, won't download again" % local_path)
return local_path
#req = urlopen(url)
#CHUNK = 512*1024
#with open(local_path, 'wb') as f:
# while True:
# chunk = req.read(CHUNK)
# if not chunk: break
# f.write(chunk)
# f.flush()
# f.close()
ret, out, err = RunCmd('/usr/local/bin/axel -q -n 8 -o %s %s' % (local_path, url))
if ret != 0:
raise Exception('Cannot download file: %s, out: %s, err: %s' % (url, out, err))
return local_path
def run(self):
'''线程函数，工作线程在此函数中不断轮询任务队列，如果有任务则取出执行'''
logger.debug('Work thread is running...')
while True:
# 检查停用事件
if self.__dismissed.isSet():
break
try:
# 从任务队列中获取WorkRequest实例
request = self.__requestsQueue.get(True, self.__pollTimeout)
except Queue.Empty:
continue
if self.__dismissed.isSet():
self.__requestsQueue.put(request)
break
try:
self.__isWorking = True
# 执行请求实例的doWork方法
request.doWork()
self.__isWorking = False
except Exception,e:
pass
def joinAllDismissedWorkers(self):
'''等待所有停用线程结束运行'''
for worker in self.__dismissedWorkers:
Worker.join()
logger.debug('All dismissed woker is quit...')
self.__dismissedWorkers = []
def test_downloadUrl(self):
# make sure all the tgz files for a url is downloaded correctly
url = "http://engweb.eng.vmware.com/bugs/files/0/1/2/4/9/0/9/7/esx-w2-erqa230-2014-05-09--23.23.tgz"
local_path = downloadFile("/tmp/", url)
logger.debug(local_path)
self.assertEqual(os.path.getsize(local_path), 162180210)
def createWorkers(self, threadNum, pollTimeout):
'''创建工作线程并将它们添加到线程池中'''
logger.debug('Start create work thread...')
for i in range(min(MAX_THREAD_NUM, threadNum)):
# 为工作线程传递任务队列
self.__workers.append(WorkerThread(self.__requestsQueue, pollTimeout))
def dismiss(self):
'''停用此线程'''
logger.debug('work thread is dismiss...')
self.__dismissed.set()
def dumpLogRecords(records):
for entity in records.keys():
for record in records[entity]:
logger.debug(("%s, %s,%s") % (entity, record.timestamp, record.log))
def close(self, doJoin = False):
'''关闭所有线程，doJoin为True则等待所有线程结束再返回，否则直接返回'''
self.dismissWorkers(len(self.__workers) , doJoin)
if doJoin:
self.joinAllDismissedWorkers()
logger.debug('All thread is quit...')
