class Translator(object):
"""翻译组件"""
def __init__(self, config):
super(Translator, self).__init__()
self.config = config
self.log = Log()
def transTag(self):
#翻译标签的方法
try:
db = Database(self.log,self.config)
tags = db.getAllTagWithoutCN()
if tags:
for tagOne in tags:
postfix = tagOne[1].replace(' ','+')
url = self.config.transURL+postfix
cookie = cookielib.CookieJar()
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookie))
req = urllib2.Request(
url = url
)
htmlData = ""
#获取网页原始数据
htmlData = opener.open(req).read()
result = json.loads(htmlData)
t_name_cn = ''
if result:
if 'translation' in result.keys():
#print('dic:'+result['translation'][0])
t_name_cn = result['translation'][0]
elif 'web' in result.keys():
#print('web:'+result['web'][0]['value'][0])
t_name_cn = result['web'][0]['value'][0]
else:
continue
if t_name_cn:
db.updateTagCN(tagOne[0],t_name_cn)
else:
continue
else:
return
return
except Exception, TransErr:
self.log.takeLog('ERROR','Translator Error in tag:' + str(TransErr))
class Reader(object):
"""读取HTML的类"""
def __init__(self, config):
reload(sys)
sys.setdefaultencoding('utf-8')
self.config = config
self.log = Log()
#剧名的字母顺序表
self.AllShowsList = ['0','A','B','C','D','E','F','G','H','I','J','K','L','M','N','O','P','Q','R','S','T','U','V','W','X','Y','Z']
def allShowsWork(self):
#初步获取show的方法
for i in xrange(0,len(self.AllShowsList)): #注意这里是0~len，并不是0~len-1
try:
cookie = cookielib.CookieJar()
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookie))
#urlX = 'http://www.pogdesign.co.uk/cat/all-shows/0'
req = urllib2.Request(
#从config中取出Allshows的所需要的url，加上上面那个数组所对应的头字母
url = self.config.urlAllShows+self.AllShowsList[i]
)
htmlData = ""
#获取网页原始数据
htmlData = opener.open(req).read()
except Exception, connErr:
self.log.takeLog('ERROR','Connection Error:' + str(connErr))
if htmlData:
try:
for OneBox in BeautifulSoup(htmlData).findAll('div', attrs={'class' : 'contbox prembox removed'}) : #用bs取到所有的小box，每个box是一个剧名
showName = BeautifulSoup(str(OneBox)).h2.get_text()
#showName = MySQLdb.escape_string(showName)
imageURL = str(BeautifulSoup(str(OneBox)).a['style']) #此处获取到的是图片URL的一段style的js连接，需要精加工
statusStringArray = BeautifulSoup(str(OneBox)).find('span',attrs={'class':'hil selby'}) #此处是要获得剧状态的span标签
#edit on 20160520由于原网页出现格式变化，改从注释中提取播放状态，一旦注释消失记得修改此处注释内容
statusString = str(statusStringArray) #此处是要获得span标签中的内容，之后把|左半拉的内容取出来，但是由于含有空格需要精加工
#print(statusStringArray.get_text())#标签从这里入手
#print (str(statusStringArray))
#这个是标签
tag = statusString[24:-8]
tag = tag.replace('Â ',' ')#过滤空格
#tag = MySQLdb.escape_string(tag)
#print(tag)
aShow = {
's_name' : showName,
's_sibox_image' : imageURL[22:-2],
'link' : BeautifulSoup(str(OneBox)).a['href']
}
#print(aShow)
#if aShow['s_name'] == '' or aShow['link'] == '' or aShow['status'] == '' :
if aShow['s_name'] == '' or aShow['link'] == '' or aShow['s_sibox_image'] == '':
self.log.takeLog('WARNING','''allShowsWork function cannot collect data correctly, the vars are like below:\n s_name=%s,s_sibox_image=%s,link=%s'''%(aShow['s_name'],aShow['s_sibox_image'],aShow['link']))
db = Database(self.log,self.config)
Id = db.insertShowFirstTime(aShow)
if len(tag) != 0:
db.insertTag(Id,tag);
except Exception, syntaxErr:
raise syntaxErr
self.log.takeLog('ERROR','Syntax Tree Error:' + str(syntaxErr))
class Tools(object):
"""A class which is very simililar to ReadHtml class. The diffierence is it use step-forward method to handle data mannually"""
def __init__(self, config):
reload(sys)
sys.setdefaultencoding('utf-8')
self.config = config
self.log = Log()
#剧名的字母顺序表
self.AllShowsList = ['0','A','B','C','D','E','F','G','H','I','J','K','L','M','N','O','P','Q','R','S','T','U','V','W','X','Y','Z']
#月份换算表
#已废弃，处于兼容目的保留
self.month = {
'Jan' : '01',
'Feb' : '02',
'Mar' : '03',
'Apr' : '04',
'May' : '05',
'Jun' : '06',
'Jul' : '07',
'Aug' : '08',
'Sep' : '09',
'Oct' : '10',
'Nov' : '11',
'Dec' : '12'
}
def flush_one_page(self,character):
#刷新某一页所有剧的方法，character是一个大写字母
try:
cookie = cookielib.CookieJar()
opener = urllib2.build_opener(urllib2.HTTPCookieProcessor(cookie))
#urlX = 'http://www.pogdesign.co.uk/cat/all-shows/0'
req = urllib2.Request(
#从config中取出Allshows的所需要的url，加上上面那个数组所对应的头字母
url = self.config.urlAllShows+str(character)
)
htmlData = ""
#获取网页原始数据
htmlData = opener.open(req).read()
except Exception, connErr:
self.log.takeLog('ERROR','Connection Error:' + str(connErr))
if htmlData:
#try:
for OneBox in BeautifulSoup(htmlData).findAll('div', attrs={'class' : 'contbox prembox removed'}) : #用bs取到所有的小box，每个box是一个剧名
showName = BeautifulSoup(str(OneBox)).h2.get_text()
showName = showName.replace("'","\\'")
imageURL = str(BeautifulSoup(str(OneBox)).a['style']) #此处获取到的是图片URL的一段style的js连接，需要精加工
statusStringArray = BeautifulSoup(str(OneBox)).find('span',attrs={'class':'hil selby'}) #此处是要获得剧状态的span标签
#edit on 20160520由于原网页出现格式变化，改从注释中提取播放状态，一旦注释消失记得修改此处注释内容
#edit on 20160530原网页已将注释删除， 现在需要修改流程，该注释下一版本删除
statusString = str(statusStringArray) #此处是要获得span标签中的内容，之后把|左半拉的内容取出来，但是由于含有空格需要精加工
#标签从这里入手
#print (str(statusStringArray))
#这个是标签
tag = statusString[24:-8]
tag = tag.replace('Â ',' ')#过滤空格
tag = tag.replace("\'","\\'")
aShow = {
's_name' : showName,
's_sibox_image' : imageURL[22:-2],
'link' : BeautifulSoup(str(OneBox)).a['href'],
}
print(aShow)
#if aShow['s_name'] == '' or aShow['link'] == '' or aShow['status'] == '' :
if aShow['s_name'] == '' or aShow['link'] == '' or aShow['s_sibox_image'] == '':
self.log.takeLog('WARNING','''allShowsWork function cannot collect data correctly, the vars are like below:\n s_name=%s,s_sibox_image=%s,link=%s'''%(aShow['s_name'],aShow['s_sibox_image'],aShow['link']))
# db = Database(self.log,self.config)
# Id = db.insertShowFirstTime(aShow)
# if len(tag) != 0:
# db.insertTag(Id,tag);
#except Exception, syntaxErr:
# self.log.takeLog('ERROR','Syntax Tree Error:' + str(syntaxErr))
# raise syntaxErr
return
