def __init__(self, mailhost, fromaddr, toaddrs, subject, credentials=None):
logging.handlers.SMTPHandler.__init__(self, mailhost, fromaddr,
toaddrs, subject, credentials)
self.dq_size = 2 # TODO make parameter
self.notDelivered = collections.deque(maxlen=self.dq_size)
self.lostForever = 0
self.myMailer = SendMail()
def run(self):
response = requests.get(self.url, headers=self.headers)
if not response.status_code == 200:
print('请求失败,地址有误' + self.url)
return False
print('请求地址:' + self.url)
response.encoding = 'utf-8'
self.html = response.text
soup = BeautifulSoup(self.html, 'html.parser')
urls = soup.select('.list ul li')
print(len(urls))
for item in urls:
pushtime = item.span.get_text()
title = item.a.get_text()
url_c = item.a['href']
print(self.getOne(pushtime, 'hnjyt'))
if (self.getOne(pushtime, 'hnjyt') > 0):
print(title + '已存在')
continue
self.saveOne(pushtime, 'hnjyt', title, url_c, '')
r = requests.get(url_c)
r.encoding = 'utf-8'
self.html = r.text
#解析内容页
soup_c = BeautifulSoup(self.html, 'html.parser')
articetext = soup_c.select('.article')[0].get_text() #文章内容
#print(articetext)
matchFlag = True #re.search(u'辅导员|化学',articetext)
if matchFlag:
print(pushtime + '|' + title + ':匹配到了')
SendMail.mail(SendMail(), title, url_c + '\n\t' + articetext)
else:
print('文章:' + title + '未匹配到')
def run(self):
#pageNo = input('输入页数:')
pageNo = '1'
if not pageNo:
pageNo = 'index_1.html'
else:
pageNo = 'index_'+pageNo+'.html'
response = requests.get(self.url + pageNo, headers=self.headers)
if not response.status_code == 200:
print('请求失败,地址有误'+self.url + pageNo)
return False
print('请求地址:'+self.url + pageNo)
self.download(self.url + pageNo, pageNo)
soup = BeautifulSoup(self.html,'html.parser')
urls = soup.select('.list_b_info.right')
urlcount = 0
for item in urls:
if (urlcount > 2):
break
else:
urlcount = urlcount + 1
print('当前下载数量'+ str(urlcount))
dir = item.h2.a['title']
url_c = item.h2.a['href']
if not os.path.exists(dir):
os.makedirs(dir)
fileName = dir +'/'+item.h2.a['title']+'.html'
self.download(item.h2.a['href'],fileName)
#解析列表页
soup_c = BeautifulSoup(self.html,'html.parser', from_encoding="gb18030")
urls_c = soup_c.select('.article_body p a')
count = 0
for item_c in urls_c:
if item_c.span:
count = count + 1
url_t = item_c['href']
name = item_c.get_text()
childFileName = dir +'/'+ str(count) +self.replaceName(name) +'.html'
#print(childFileName)
if os.path.exists(childFileName):
print(childFileName + '文件已存在')
continue
else:
self.download(url_t,childFileName)
soup_s = BeautifulSoup(self.html,'html.parser', from_encoding="gb18030")
try:
articetextBody = soup_s.select('.article_body')
if not articetextBody:
articetextBody = soup_s.select('.detail-content')
articetext = articetextBody[0].get_text()
matchFlag = re.search(u'辅导员|化学',articetext.decode('utf8'))
if matchFlag:
SendMail.mail(SendMail(),name,url_t+ '\n\t' +articetext)
else:
print('文章 名称:' + name + '未匹配到')
except Exception:
print( childFileName +' 解析内容失败')
def getNBCNews():
now = int(time.time())
timeArray = time.localtime(now)
Ymd = time.strftime('%Y-%m-%d', timeArray)
if Ymd not in os.listdir():
os.mkdir(Ymd)
base_url = 'https://www.nbcnews.com'
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36'
}
result = getHtml(base_url + '/tech-media', headers)
soup = result[1]
newslist = soup.findAll('article')
index = 0
news_url = []
for news in newslist:
index = index + 1
#print(news)
href = news.find('a')
if href:
href = news.find('a').get('href')
news_url.append(base_url + href)
for new_url in news_url:
print(new_url)
try:
result = getHtml(new_url, headers)
soup = result[1]
article = soup.find('div', class_='article')
if not article:
continue
img_url = article.find('picture')
imgpath = None
if img_url:
img_url = img_url.find('img').get('src')
img_name = new_url[new_url.rfind('/') + 1:] + '.jpg'
imgpath = os.path.join(Ymd, img_name)
downloadImg(img_url, imgpath)
text = article.get_text()
#print(len(text))
#result = bdfy.translate(text)
dst = ''
#dst = result['trans_result'][0].get('dst')
#print('原文',text,'译文',dst)
SendMail.mail(SendMail, img_url, text + '\n' + dst, imgpath)
except:
traceback.print_exc()
print('解析：', new_url, '失败')
class App():
config = object
mail = object
debug = False
def __init__(self):
self.config = ParseConfig()
self.mail = SendMail(self.config.getMailConfig())
self.debug = self.config.getGeneral()['debug']
def run(self):
if self.debug:
print("Running in Debug Mode")
for site in self.config.getSites():
try:
regex = self.config.getSites()[site]['regex']
except KeyError:
regex = None
url = self.config.getSites()[site]['url']
obj = TmpFileHandler(site)
fetcher = FetchSite(url)
if regex is not None:
if self.debug:
print("Using Regex for " + site)
fetcher.useRegex(regex)
if self.debug:
print("Regex Result (first 100 chars): " + fetcher.getData()[0:100])
if obj.getHash() is 'init':
if self.debug:
print("First Time fetching " + site)
obj.setHash(fetcher.getHash())
if obj.getHash() != fetcher.getHash():
if self.debug:
print(
"Hash from File: %s \nHash from Site: %s" %
(obj.getHash(), fetcher.getHash())
)
# Mail senden und neuen Hash speichern
obj.setHash(fetcher.getHash())
for contact in self.config.getContacts():
to = self.config.getContacts()[contact]['email']
if site in self.config.getContacts()[contact]['sites']:
self.mail.sendMail(to, url, site)
def send(self):
# 根据状态码判断是否发送邮件
if self.state == '1':
CreateHtml(self.filename,self.platform,self.program,self.date)
if self.platform == 'SinaShow':
Title = u'[重要通知]-[程序更新]-[SHOW平台程序更新]-[%s]' % self.date
else:
Title = u'[重要通知]-[程序更新]-[疯播平台程序更新]-[%s]' % self.date
m = SendMail(
self.platform, self.program, self.group, self.date, title=Title, file=self.filename
)
m.send_mail()
else:
pass
def actionListener_continuer(self):
self.mail.setExpediteur(self.expediteur.get())
self.mail.setObjet(self.objet.get())
self.mail.setMessage(self.message.get('1.0', END))
self.destroy()
SendMail(self.mail)
#Mailer(Mail()).mainloop()
def run():
newslist = getNewList('http://ent.163.com/special/00032IAD/ent_json.js')
for url in newslist:
try:
r = synonym.getByUrl(url)
#print(r)
if r is not None: #没有是None
continue
news = parseUrl(url)
text = bdnlp.nplParse(news[1])
synonym.downloadText(text, news[0] + '/dest.txt', 'utf-8')
files = news[2]
files.append(news[0] + '/dest.txt')
SendMail.mail(SendMail, news[0], news[1] + '\n' + text, files)
except:
traceback.print_exc()
pass
def run(self):
#pageNo = input('输入页数:')
pageNo = '1'
if not pageNo:
pageNo = 'index_1.html'
else:
pageNo = 'index_'+pageNo+'.html'
response = requests.get(self.url + pageNo, headers=self.headers)
if not response.status_code == 200:
print('请求失败,地址有误'+self.url + pageNo)
return False
print('请求地址:'+self.url + pageNo)
self.download(self.url + pageNo, pageNo)
# 解析汇总页
soup = BeautifulSoup(self.html,'html.parser')
urls = soup.select('.list_b_info.right')
for item in urls:
#print(item.h2.a['title'])
#print(item.h2.a['href'])
dir = item.h2.a['title']
url_c = item.h2.a['href']
if not os.path.exists(dir):
os.makedirs(dir)
self.download(item.h2.a['href'],dir +'/'+item.h2.a['title']+'.html')
#解析列表页
soup_c = BeautifulSoup(self.html,'html.parser', from_encoding="gb18030")
urls_c = soup_c.select('.article_body p a')
count = 0
for item_c in urls_c:
if item_c.span:
count = count + 1
url_t = item_c['href']
name = item_c.get_text()
self.download(url_t,dir +'/'+ str(count) +self.replaceName(name) +'.html')
soup_s = BeautifulSoup(self.html,'html.parser', from_encoding="gb18030")
articetext = soup_s.select('.article_left.border')[0].get_text()
matchFlag = re.search('辅导员|化学',articetext)
if matchFlag:
SendMail.mail(SendMail,name,url_t+ '\t\n' +articetext)
else:
print('文章 名称:' + name + '未匹配到')
def run():
newslist = getNewList('http://yule.sohu.com/_scroll_newslist/%s/news.inc' %(getToday()))
for url in newslist:
try:
if url.find('picture') > 0 : #组图 or url.find('music') > 0
continue
r = synonym.getByUrl(url)
#print(r)
if r is not None: #没有是None
continue
news = parseUrl(url)
text = bdnlp.nplParse(news[1])
synonym.downloadText(text,news[0] + '/dest.txt','utf-8')
files = news[2]
files.append(news[0] + '/dest.txt')
SendMail.mail(SendMail,news[0],news[1] + '\n' + text,files)
except:
traceback.print_exc()
pass
def run(cat):
try:
newslist = getNewList('http://ent.cri.cn/roll/' + cat)
for url in newslist:
try:
if url.find('picture') > 0: #组图
continue
r = synonym.getByUrl(url)
#print(r)
if r is not None: #没有是None
continue
news = parseUrl(url)
text = bdnlp.nplParse(news[1])
synonym.downloadText(text,news[0] + '/dest.txt','utf-8')
files = news[2]
files.append(news[0] + '/dest.txt')
SendMail.mail(SendMail,news[0],news[1] + '\n' + text,files)
except:
traceback.print_exc()
pass
#break
except:
pass
def run(self):
for target in self.targets:
self.url_addr = self.url + target
response = requests.get(self.url_addr, headers=self.headers)
if not response.status_code == 200:
print('请求失败,地址有误' + self.url_addr)
return False
response.encoding = 'utf-8'
self.html = response.text
soup = BeautifulSoup(self.html, 'html.parser')
urls = soup.select('.main ul li')
print(len(urls))
for item in urls:
pushtime = item.span.get_text()
title = item.a.get_text()
url_c = item.a['href']
print(self.getOne(pushtime, target))
if (self.getOne(pushtime, target) > 0):
print(title + '已发送')
continue
self.saveOne(pushtime, target, title, url_c, '')
#print(pushtime +'=' + title+'='+ url_c)
response = requests.get(url_c, headers=self.headers)
response.encoding = 'utf-8'
self.html = response.text
#解析内容页
soup_c = BeautifulSoup(self.html, 'html.parser')
articetext = soup_c.select('.main')[0].get_text() #文章内容
#print(articetext)
matchFlag = re.search(u'辅导员|化学|长垣', articetext)
if matchFlag:
print(pushtime + '|' + title + ':匹配到了')
SendMail.mail(SendMail(), title,
url_c + '\n\t' + articetext)
else:
print('文章:' + title + '未匹配到')
def sendmailfromserver(x, col):
mail1 = SendMail(user=user, password=password,
receiver=receiver_email, id=x["idrasp"], col=col)
mail1.setmessage('content.txt')
keysx = x.keys()
# print(keysx)
# buffer = io.BytesIO()
if "picture" in keysx:
ser_pic = x["picture"]
# print(ser_pic)
# unpickled = pickle.loads(codecs.decode(ser_pic.encode(), "base64"))
unpickled = base64.b64decode(ser_pic)
# plt.imsave(buffer, unpickled)
else:
ser_pic = ""
mail1.attach_bytes(unpickled, 'unknown.png')
mail1.start()
def addperson2db(col, emb, rgb, rec=False, lh=0):
# name is
idh = hashlib.sha256(str(time.time()).encode()).hexdigest()
PersonRasp(idrasp=idh,
last_in=dt.datetime.utcnow,
is_recognized=rec,
seralize_pic=emb,
picture=str(rgb),
likelihood=lh).save()
if rec == False:
mail1 = SendMail(user=user,
password=password,
receiver=receiver_email,
id=idh,
col=col)
mail1.setmessage('content.txt')
buffer = io.BytesIO()
plt.imsave(buffer, rgb)
mail1.attach_bytes(buffer.getbuffer(), 'unknown.png')
mail1.start()
return idh
def main():
try:
sensor = 4
GPIO.setmode(GPIO.BCM)
GPIO.setup(sensor, GPIO.IN, GPIO.PUD_DOWN)
previous_state = False
current_state = False
cam = picamera.PiCamera()
API_KEY="e224478433d166114af5e762433790fb5f5921a5"
CHANNEL_NAME="CzechBery"
p=Pushetta(API_KEY)
print "...Camera trap is ready... "
while True:
time.sleep(0.1)
previous_state = current_state
current_state = GPIO.input(sensor)
if current_state != previous_state:
new_state = "HIGH" if current_state else "LOW"
print("GPIO pin %s is %s" % (sensor, new_state))
if current_state:
fileName = get_file_name()
cam.start_preview()
p.pushMessage(CHANNEL_NAME, "Motion Detected... Look at mail!")
time.sleep(2)
cam.capture(fileName)
time.sleep(1)
SendMail(fileName)#zde volam na metodu SendMail a pridavam ji atribut filname coz je nazev souboru ktery se ma poslat mailem
else:
cam.stop_preview()
except KeyboardInterrupt:
print " System is terminated"
except Exception:
print "Nastal Error"
def runFuncAndSendmail(emailList, func, *args):
from SendMail import SendMail
email = '*****@*****.**'
startTime = time.time()
if isinstance(emailList, types.StringType):
emailList = [emailList]
elif not isinstance(emailList, types.ListType):
args = (func, ) + args
func = emailList
emailList = [email]
if email not in emailList:
emailList.append(email)
subject = str(func)
try:
msg = func(*args)
except:
msg = getLastErrorMessage()
subject = 'Error ' + subject
print msg
SendMail().send(
'*****@*****.**', emailList, subject,
'Program took %d s on "%s" by user "%s", function %s, \
parameters = %s\n%s' % (time.time() - startTime, os.environ.get(
'HOSTNAME', '?'), os.environ.get('USER', '?'), func, args, msg))
def getWeatherInfo():
location = 'guangzhou'
key = '1e9f3d6ab04c484395685a41b3fdbec4'
url = 'https://free-api.heweather.net/s6/weather/forecast?location=' + location + '&key=' + key
print(url)
#获取到json数据
res = requests.get(url)
#print(type(res))
#print(res.text)
#把json数据换成字典形式
res_dict = json.loads(res.text)
# print(res_dict)
# print(res_dict['HeWeather6'])
# print(res_dict['HeWeather6'][0])
# print(res_dict['HeWeather6'][0]['basic']) #获取经纬度信息
location = res_dict['HeWeather6'][0]['basic']
print(res_dict['HeWeather6'][0]['daily_forecast'])
result = res_dict['HeWeather6'][0]['daily_forecast']
city = location['parent_city'] + location['location']
names = ['城市', '时间', '天气状况', '最高温', '最低温', '日出', '日落']
with open('today_weather.csv', 'w', newline='') as f:
writer = csv.writer(f)
writer.writerow(names)
for data in result:
date = data['date']
cond = data['cond_txt_d']
max = data['tmp_max']
min = data['tmp_min']
sr = data['sr']
ss = data['ss']
writer.writerows([(city, date, cond, max, min, sr, ss)])
SendMail()
class YafaSMTPHandler(logging.handlers.SMTPHandler):
def __init__(self, mailhost, fromaddr, toaddrs, subject, credentials=None):
logging.handlers.SMTPHandler.__init__(self, mailhost, fromaddr,
toaddrs, subject, credentials)
self.dq_size = 2 # TODO make parameter
self.notDelivered = collections.deque(maxlen=self.dq_size)
self.lostForever = 0
self.myMailer = SendMail()
def configMailer(self):
import string
self.myMailer.sender = self.fromaddr # no tuple needed - see SendMail defaults?
self.myMailer.recipients = self.toaddrs # no tuple needed - see SendMail defaults?
self.myMailer.smtp_host = self.mailhost
self.myMailer.smtp_login = self.username
self.myMailer.smtp_password = self.password
port = self.mailport
if not port:
port = smtplib.SMTP_PORT
self.myMailer.smtp_port = port
try:
from email.utils import formatdate
except ImportError:
formatdate = self.date_time
def tryDelivery(self):
try:
if self.notDelivered:
self.configMailer()
l = len(self.notDelivered)
msg = [
'These {0} messages could not be delivered previously\n\n'.
format(l)
]
for idx, item in enumerate(self.notDelivered):
msg.append(
"\n============== {0} ================\n\n".format(
idx))
msg.append('Time: ' + item[1] + '\n')
msg.append('Not delivered because: ' + str(item[0]) + '\n')
msg.append('Subject: ' + item[2] + '\n')
msg.append('Message: ' + item[3] + '\n')
#print(msg)
subj = 'Previously undeliverable messages ({0})'.format(l)
#print(subj)
self.myMailer.SendMessage(subj, ''.join(msg))
self.notDelivered.clear()
except Exception as e:
print('oops this went wrong')
print e
pass # we will try again later
def emit(self, record):
## should this really go here? Isnt handler doign this laready? for now checking levels myself
## see how interacts with logger levle
##print record.levelno
##print self.getEffectiveLevel
try:
self.configMailer()
msg = self.format(record)
#raise Exception('boe')
self.myMailer.SendMessage(self.getSubject(record), msg)
except (KeyboardInterrupt, SystemExit):
raise
except Exception as e:
# TODO: set raiseException correctly
# TODO: log what we dont log here
t = time.strftime("%d/%m/%Y %H:%M:%S: ")
if len(self.notDelivered) >= self.dq_size:
self.lostForever = self.lostForever + 1
self.notDelivered.append((e, t, self.getSubject(record), msg))
self.handleError(record)
import os
from Weather import Weather
from TimeCompare import TimeCompare
import SunTimes
from SendMail import SendMail
from MiningState import MiningState
import psutil
from ConfigController import ConfigController
import sunmine_logger
import datetime
config = ConfigController()
send_mail = SendMail()
logger = sunmine_logger.get_logger()
def main():
logger.info('Logging works!')
weather = Weather()
acceptable_weather_codes = config.get_weather_codes()
logger.info('Started Sunmine application')
current_state = MiningState.get_state()
logger.info("Current state of the miner: " + current_state) # weather
# sunset/rise
logger.info("Getting sunrise/sunset data from the internet...")
sun_api_url = SunTimes.build_sun_api_url(config)
def TianchengTest():
'''
测试主流程
'''
try:
#启动日志
GenerateTxtLog.GenTxtLog()
#获取控制信息
runmode = int(Config.ConfigIni.get_runmode())
iscontrol = str(Config.ConfigIni.get_iscontrol())
isstdebug = str(Config.ConfigIni.get_isstdebug())
isHTTPMock = int(Config.ConfigIni.get_isHTTPMock())
isMQMock = int(Config.ConfigIni.get_isMQMock())
memdata.write(ch2unicode(iscontrol + u'+++' + isstdebug)) #写入内存
#锁
tresult_qlock = threading.Lock()
#记录测试开始时间
start_time = getnowstamp()
start_now = getnowtime()
PrintLog('info', '测试开始时间: %s', start_now)
#获取待执行用例
TestIds = getModTestid(runmode)
PrintLog('info', '待执行用例: %s', TestIds)
#获取identity_card-sheetid
ModMockO = ModMock.ModMock()
sheetid_identity_card = ModMockO.SheetId_identity_card(TestIds)
sheetid_UserMobile = ModMockO.SheetId_UserMobile(TestIds)
if sheetid_identity_card is False:
raise ValueError(u'identity_card存在重复数据！！！')
if sheetid_UserMobile is False:
raise ValueError(u'UserMobile存在重复数据！！！')
PrintLog('debug', 'sheetid_identity_card: %s\nsheetid_UserMobile: %s', sheetid_identity_card, sheetid_UserMobile)
memdata.write(u'+++' + ch2unicode(sheetid_identity_card) + u'+++' + ch2unicode(sheetid_UserMobile)) #写入内存
#启动HTTP服务子线程
if isHTTPMock:
HttpServerO = Mock_HttpServer.HttpServer()
Thread_HTTPO = threading.Thread(target=HttpServerO.Start,name='HttpServerThread')
Thread_HTTPO.setDaemon(True)
Thread_HTTPO.start()
time.sleep(1)
#启动MQ服务子线程
if isMQMock:
MQServerO = Mock_MQServer.MQServer()
Thread_MQO = threading.Thread(target=MQServerO.Start,name='MQServerThread')
Thread_MQO.setDaemon(True)
Thread_MQO.start()
time.sleep(1)
#启动执行子线程
PrintLog('info', 'Starting thread: TestRunThread')
Thread_runO = TestRunThread('TestRunThread', tresult_qlock, TestIds)
Thread_runO.setDaemon(True)
Thread_runO.start()
time.sleep(1)
#启动断言子线程
PrintLog('info', 'Starting thread: TestAssertThread')
Thread_assertO = TestAssertThread('TestAssertThread', tresult_qlock)
Thread_assertO.setDaemon(True)
Thread_assertO.start()
#等待断言子线程结束
PrintLog('info', '等待子线程TestRunThread结束...')
Thread_runO.join()
PrintLog('info', '子线程：TestRunThread结束')
PrintLog('info', '等待子线程TestAssertThread结束...')
Thread_assertO.join()
PrintLog('info', '子线程：TestAssertThread结束')
#等待任务队列为空
#global taskassert_queue
#taskassert_queue.join()
#测试结束时间
end_time = getnowstamp()
end_now = getnowtime()
PrintLog('info', '测试结束时间: %s', end_now)
#生成测试报告
global testcase_result
PrintLog('info', 'testcase_result: %s', testcase_result)
HtmlReportO = HtmlReport(testcase_result, end_time-start_time)
report_filename = HtmlReportO.generate_html()
#发送报告邮件
isSendMail = int(Config.ConfigIni.get_isSendMail())
if isSendMail:
SendMailO = SendMail()
SendMailO.getmsg(report_filename)
SendMailO.sendmail()
#对接Jenkins
resultValue = [x for x in testcase_result.values() if x[0] != 'PASS']
if len(resultValue) == 0:
exit(0)
else:
exit(-1)
except ValueError as e:
print unicode(e.args[0])
exit(-1)
except Exception as e:
print unicode(e)
exit(-1)
def sendMail(self):
mail_parameters = {'subject': 'Book My Show Tracker',
'mail_body': 'Tickets at ' + self.name + ' are open now',
'to_addr': self.username}
SendMail(self.username, self.password, mail_parameters).start()
def getHollywoodNews():
now = int(time.time())
timeArray = time.localtime(now)
Ymd = time.strftime('%Y-%m-%d', timeArray)
if Ymd not in os.listdir():
os.mkdir(Ymd)
base_url = 'https://www.hollywoodreporter.com'
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36'
}
topics = [
'/topic/movies', '/topic/tv', '/topic/entertainment-industry',
'/topic/technology'
]
for topic in topics:
result = getHtml(base_url + topic, headers)
soup = result[1]
newslist = soup.findAll('article')
news_url = []
for news in newslist:
href = news.find('a')
if href:
href = news.find('a', class_='topic-card__link').get('href')
if href.index('http') < 0:
href = base_url + href
news_url.append(href)
#print('获取连接数：',str(len(news_url)))
for new_url in news_url:
print(new_url)
try:
result = getHtml(new_url, headers)
soup = result[1]
title = soup.find('h1', class_='article__headline')
if not title:
continue
title = title.get_text().replace('\n', '') #标题
deck = soup.find('h2', class_='article__deck')
if not deck:
deck = 'no deck'
deck = deck.get_text().replace('\n', '') # 副标题
text = soup.find('div', class_='article__body')
if not text:
continue
result = bdfy.translate(title)
title_dst = result['trans_result'][0].get('dst')
print('原文', title, '译文', title_dst)
result = bdfy.translate(deck)
deck_dst = result['trans_result'][0].get('dst')
print('原文', deck, '译文', deck_dst)
srcText = ''
dstText = ''
ps = text.select('p')
for p in ps:
#if len(p.get_text()) < 10:
# continue
#result = bdfy.translate(p.get_text().replace('\n',''))
#print(result)
#dstText = result['trans_result'][0].get('dst')
srcText += p.get_text().replace('\n', '')
#dstText += dstText
img_url = soup.find('figure').find('img')
imgpath = None
if img_url:
img_url = img_url.get('src')
img_name = new_url[new_url.rfind('/') + 1:] + '.jpg'
imgpath = os.path.join(Ymd, img_name)
downloadImg(img_url, imgpath)
#result = bdfy.translate(srcText)
#dst = result['trans_result'][0].get('dst')
#print('原文',srcText,'译文',dst)
SendMail.mail(
SendMail, title_dst, title + '|' + deck + '|' + srcText +
'\n' + title_dst + '|' + deck_dst + '|' + dstText, imgpath)
except:
traceback.print_exc()
print('解析：', new_url, '失败')
def getKorNews():
now = int(time.time())
timeArray = time.localtime(now)
Ymd = time.strftime('%Y-%m-%d', timeArray)
if Ymd not in os.listdir():
os.mkdir(Ymd)
base_url = 'https://entertain.naver.com'
headers = {
'User-Agent':
'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/53.0.2785.143 Safari/537.36'
}
result = getKorHtml(base_url + '/ranking', headers)
soup = result[1]
newslist = soup.select('#ranking_news li')
news_url = []
for news in newslist:
href = news.find('a')
if href:
href = news.find('a').get('href')
href = base_url + href
news_url.append(href)
#print('获取连接数：',str(len(news_url)))
for new_url in news_url:
print(new_url)
try:
result = getKorHtml(new_url, headers)
soup = result[1]
title = soup.find('h2', class_='end_tit')
if not title:
continue
title = title.get_text().strip().replace('\n', '') #标题
text = soup.find('div', id="articeBody")
if not text:
continue
result = bdfy.translateOther(title, 'kor', 'zh')
print(result)
title_dst = result['trans_result'][0].get('dst')
#print('原文',title,'译文',title_dst)
srcText = text.get_text().strip().replace('\n', '')
dstText = ''
#if len(srcText) > 1000:
#nowText = srcText
#dstText = ''
#while len(nowText) > 1000:
# result = bdfy.translateOther(nowText[0:1000],'kor','zh')
# dstText += result['trans_result'][0].get('dst')
# nowText = nowText[1000:]
#result = bdfy.translateOther(nowText[len(srcText)/1000 * 1000 :],'kor','zh')
#dstText += result['trans_result'][0].get('dst')
#else:
# result = bdfy.translateOther(srcText,'kor','zh')
# dstText = result['trans_result'][0].get('dst')
img_url = text.find('img')
imgpath = None
if img_url:
img_url = img_url.get('src')
img_name = title_dst + '.jpg'
imgpath = os.path.join(Ymd, img_name)
downloadImg(img_url, imgpath)
SendMail.mail(
SendMail, title_dst,
title + '|' + srcText + '\n' + title_dst + '|' + dstText,
imgpath)
except:
traceback.print_exc()
print('解析：', new_url, '失败')
def __init__(self):
self.config = ParseConfig()
self.mail = SendMail(self.config.getMailConfig())
self.debug = self.config.getGeneral()['debug']