def genPeverifyInteropAsm(file):
#if this isn't a test run that will invoke peverify there's no point in
#continuing
if not is_peverify_run:
return
else:
mod_name = file.rsplit("\\", 1)[1].split(".py")[0]
print "Generating interop assemblies for the", mod_name, "test module which are needed in %TEMP% by peverify..."
from System.IO import Path
tempDir = Path.GetTempPath()
cwd = nt.getcwd()
#maps COM interop test module names to a list of DLLs
module_dll_dict = {
"excel": [],
"msagent": [agentsvr_path],
"scriptpw": [scriptpw_path],
"word": [],
}
dlrcomlib_list = [
"dlrcomserver",
"paramsinretval",
"method",
"obj",
"prop",
]
if is_cli32:
temp_name = testpath.rowan_root + "\\Test\\DlrComLibrary\\Debug\\DlrComLibrary.dll"
else:
temp_name = testpath.rowan_root + "\\Test\\DlrComLibrary\\x64\\Release\\DlrComLibrary.dll"
for mod_name in dlrcomlib_list:
module_dll_dict[mod_name] = [temp_name]
if not file_exists_in_path("tlbimp.exe"):
print "ERROR: tlbimp.exe is not in the path!"
sys.exit(1)
try:
if not module_dll_dict.has_key(mod_name):
print "WARNING: cannot determine which interop assemblies to install!"
print " This may affect peverify runs adversely."
print
return
else:
nt.chdir(tempDir)
for com_dll in module_dll_dict[mod_name]:
if not file_exists(com_dll):
print "\tERROR: %s does not exist!" % (com_dll)
continue
print "\trunning tlbimp on", com_dll
run_tlbimp(com_dll)
finally:
nt.chdir(cwd)
def change_dir(self):
file_name = os.listdir(self.path)
print(file_name)
for files in file_name:
file = os.path.splitext(files)
print(file)
if self.old_name in file[0]:
new_name = file[0].replace(self.old_name,
self.new_name) + file[1]
chdir(self.path) #在使用rename之前需要进入文件所在的目录
os.rename(files, new_name)
def removeNumbers(dir):
chdir(dir)
files = os.listdir(dir)
# files.sort()
files.sort(lambda x, y: compare_string(x, y))
for old_file in files:
if 'py' not in old_file:
fileName = str(old_file)
new_name = removeDigitPrefix(fileName)
new_name = removeDotPrefix(new_name)
print "old file: ", old_file, "=> new file: ", new_name
os.rename(old_file, new_name)
def addNumbers(dir, start):
i = start
chdir(dir)
files = os.listdir(dir)
# files.sort()
files.sort(lambda x, y: compare_string(x, y))
for old_file in files:
fileName = str(old_file)
new_name = str(i) + '.' + fileName
os.rename(old_file, new_name)
print "remamed: ", old_file, " ==> ", new_name
i += 1
def genPeverifyInteropAsm(file):
#if this isn't a test run that will invoke peverify there's no point in
#continuing
if not is_peverify_run:
return
else:
mod_name = file.rsplit("\\", 1)[1].split(".esc")[0]
print("Generating interop assemblies for the", mod_name, "test module which are needed in %TEMP% by peverify...")
from System.IO import Path
tempDir = Path.GetTempPath()
cwd = nt.getcwd()
#maps COM interop test module names to a list of DLLs
module_dll_dict = {
"excel" : [],
"msagent" : [agentsvr_path],
"scriptpw" : [scriptpw_path],
"word" : [],
}
dlrcomlib_list = [ "dlrcomserver", "paramsinretval", "method", "obj", "prop", ]
if is_cli32:
temp_name = testpath.rowan_root + "\\Test\\DlrComLibrary\\Debug\\DlrComLibrary.dll"
else:
temp_name = testpath.rowan_root + "\\Test\\DlrComLibrary\\x64\\Release\\DlrComLibrary.dll"
for mod_name in dlrcomlib_list: module_dll_dict[mod_name] = [ temp_name ]
if not file_exists_in_path("tlbimp.exe"):
print("ERROR: tlbimp.exe is not in the path!")
sys.exit(1)
try:
if mod_name not in module_dll_dict:
print("WARNING: cannot determine which interop assemblies to install!")
print(" This may affect peverify runs adversely.")
print()
return
else:
nt.chdir(tempDir)
for com_dll in module_dll_dict[mod_name]:
if not file_exists(com_dll):
print("\tERROR: %s does not exist!" % (com_dll))
continue
print("\trunning tlbimp on", com_dll)
run_tlbimp(com_dll)
finally:
nt.chdir(cwd)
def main(cpy_dir):
global CPY_DIR
global CPY_LIB_DIR
CPY_DIR = cpy_dir
CPY_LIB_DIR = cpy_dir + "\\Lib" #E.g., C:\Python25\Lib
path.append(CPY_LIB_DIR)
path.insert(0, ".")
print(
"------------------------------------------------------------------------"
)
print("--PACKAGES")
cwd = nt.getcwd()
nt.chdir(CPY_LIB_DIR)
for pack_name in nt.listdir(CPY_LIB_DIR):
if not is_package(pack_name):
continue
elif pack_name in BLACKLIST:
continue
check_package(pack_name)
print()
nt.chdir(cwd)
print(
"------------------------------------------------------------------------"
)
print("--MODULES")
for x in nt.listdir(CPY_LIB_DIR):
if x.endswith(".py"):
mod_name = x.split(".py", 1)[0]
else:
continue
try:
import_helper(mod_name)
log_ok(mod_name)
except Exception as e:
log_broken(mod_name, e)
#Cleanup
for f in FILE_LIST:
f.close()
return BROKEN_LIST
def rename():
filelist = os.listdir(path) # 该文件夹下的所有文件
for file in filelist: # 遍历所有文件 包括文件夹
# print("原始文件名为 :%s"%file)
index = file.rfind(olds)
# print(index)
if index > 0:
newName = file.replace(olds, news)
# newName=file[index+3:]
print("新文件名为 :%s" % newName)
# 先用chdir()函数进入到目标文件所在的路径
chdir(os.path.dirname(path + file)) # 如果不是文件夹，需要添加此语句
os.rename(file, newName) # 重命名
def removeNumbers0(dir):
chdir(dir)
for old_file in os.listdir(dir):
if 'py' not in old_file:
fileName = str(old_file)
number = fileName[0:fileName.find('.')]
print "number: ", number
if (isNumber2(number)):
subfilename = fileName[fileName.find('.') + 1:]
fileName = subfilename[subfilename.find('.'):]
new_name = subfilename
print "old file: ", old_file
print "subfilename: ", subfilename
print "new_name: ", new_name
os.rename(old_file, new_name)
else:
print "number: ", number, "is not number"
def check_package(package_name):
'''
Checks all subpackages and modules in the package_name package.
'''
cwd = nt.getcwd()
if cwd == CPY_LIB_DIR:
root_name = package_name
else:
root_name = cwd.split(CPY_DIR + "\\Lib\\")[1].replace(
"\\", ".") + "." + package_name
#First check that the root package can be imported
try:
import_helper(package_name)
log_ok(root_name)
except (Exception, SystemExit) as e:
log_broken(root_name, e)
# no sense continuing
return
#Next examine subpackages and modules
nt.chdir(cwd + "\\" + package_name)
for x in nt.listdir("."):
if x.endswith(".py") and x not in ("__init__.py", '__main__.py'):
x = x.split(".py", 1)[0]
mod_name = nt.getcwd().split(CPY_DIR + "\\Lib\\")[1] + "\\" + x
mod_name = mod_name.replace("\\", ".")
try:
import_helper(mod_name)
log_ok(mod_name)
except (Exception, SystemExit) as e:
log_broken(mod_name, e)
elif is_package(x) and not x.startswith('test'):
check_package(x)
nt.chdir(cwd)
def main(cpy_dir):
global CPY_DIR
global CPY_LIB_DIR
CPY_DIR = cpy_dir
CPY_LIB_DIR = cpy_dir + "\\Lib" #E.g., C:\Python25\Lib
path.append(CPY_LIB_DIR)
path.insert(0, ".")
print "------------------------------------------------------------------------"
print "--PACKAGES"
cwd = nt.getcwd()
nt.chdir(CPY_LIB_DIR)
for pack_name in nt.listdir(CPY_LIB_DIR):
if not is_package(pack_name):
continue
#Importing all tests takes too long
elif pack_name in ["test"]:
continue
check_package(pack_name)
print
nt.chdir(cwd)
print "------------------------------------------------------------------------"
print "--MODULES"
for x in nt.listdir(CPY_LIB_DIR):
if x.endswith(".py"):
mod_name = x.split(".py", 1)[0]
else:
continue
try:
import_helper(mod_name)
log_ok(mod_name)
except Exception, e:
log_broken(mod_name, e)
def download(self, imglist):
for imgurl in imglist:
print "正在下载第" + str(self.jpgx) + "图片"
#传回进度信号
self.progress.emit([self.jpgx, self.cPhoto, self.x])
#print str(self.addr)
#中文地址加编码utf-8
path = unicode(self.addr, "utf8")
chdir(str(path))
proxy_handler = urllib2.ProxyHandler({'http': '127.0.0.1:11211'})
opener = urllib2.build_opener(proxy_handler)
f = opener.open(imgurl)
data = f.read()
with open(str(self.jpgx) + '.jpg', 'wb') as code:
code.write(data)
#urllib.urlretrieve(imgurl,'%s.jpg' % x)
self.jpgx += 1
print "download"
def test_chdir():
currdir = nt.getcwd()
nt.mkdir('tsd')
nt.chdir('tsd')
AreEqual(currdir + '\\tsd', nt.getcwd())
nt.chdir(currdir)
AreEqual(currdir, nt.getcwd())
nt.rmdir('tsd')
# the directory is empty or does not exist
AssertErrorWithNumber(WindowsError, 22, lambda: nt.chdir(''))
AssertErrorWithNumber(WindowsError, 2, lambda: nt.chdir('tsd'))
def test_chdir():
currdir = nt.getcwd()
nt.mkdir('tsd')
nt.chdir('tsd')
AreEqual(currdir+'\\tsd', nt.getcwd())
nt.chdir(currdir)
AreEqual(currdir, nt.getcwd())
nt.rmdir('tsd')
# the directory is empty or does not exist
AssertErrorWithNumber(WindowsError, 22, lambda:nt.chdir(''))
AssertErrorWithNumber(WindowsError, 2, lambda:nt.chdir('tsd'))
def test_chdir(self):
currdir = nt.getcwd()
nt.mkdir('tsd')
nt.chdir('tsd')
self.assertEqual(os.path.join(currdir, 'tsd'), nt.getcwd())
nt.chdir(currdir)
self.assertEqual(currdir, nt.getcwd())
nt.rmdir('tsd')
# the directory is empty or does not exist
self.assertRaisesNumber(WindowsError, 22, lambda:nt.chdir(''))
self.assertRaisesNumber(WindowsError, 2, lambda:nt.chdir('tsd'))
def test_chdir(self):
currdir = nt.getcwd()
nt.mkdir('tsd')
nt.chdir('tsd')
self.assertEqual(os.path.join(currdir, 'tsd'), nt.getcwd())
nt.chdir(currdir)
self.assertEqual(currdir, nt.getcwd())
nt.rmdir('tsd')
# the directory is empty or does not exist
self.assertRaisesNumber(WindowsError, 22, lambda: nt.chdir(''))
self.assertRaisesNumber(WindowsError, 2, lambda: nt.chdir('tsd'))
nudetokens = []
for token in tokens:
token = token.strip(u'.,،)(:')
nudetokens.append(token)
result = [x for x in nudetokens if x not in newwords and len(x) > 2 and x!=match]
# for i in result:
# print i
return result
##file=codecs.open('d:\lion.txt','r','utf-8')
##file2=codecs.open('d:\milk.txt','r','utf-8')
filenames = glob.glob('d:\\wsd\\*.txt')
nt.chdir('d:\\wsd')
feat_set = []
sets = []
for name in filenames:
# print name
filename = name.split('\\')[-1]
sense = name.split('\\')[-1].split('.')[0]
print 'training', sense
file = codecs.open(filename, 'r', 'utf-8')
text = file.read()
features = extract_words(text)
#
# for item in sorted(features):
# print item
import os
from nt import chdir
path = r'C:\Users\Dell\Desktop\0' + '\\man\\' + str(1)
print path
aim = r'C:\Users\Dell\Desktop\0' + '\\man\\' + str(2)
files = os.listdir(path)
i = 0
for f in files:
print f
chdir(os.path.dirname(path + '\\' + f))
os.rename(f, aim + '\\' + str(i) + '.jpg')
i = i + 1
if cwd==CPY_LIB_DIR:
root_name = package_name
else:
root_name = cwd.split(CPY_DIR + "\\Lib\\")[1].replace("\\", ".") + "." + package_name
#First check that the root package can be imported
try:
import_helper(package_name)
log_ok(root_name)
except (Exception, SystemExit), e:
log_broken(root_name, e)
#Next examine subpackages and modules
nt.chdir(cwd + "\\" + package_name)
for x in nt.listdir("."):
if x.endswith(".py") and x!="__init__.py":
x = x.split(".py", 1)[0]
mod_name = nt.getcwd().split(CPY_DIR + "\\Lib\\")[1] + "\\" + x
mod_name = mod_name.replace("\\", ".")
try:
import_helper(x)
log_ok(mod_name)
except (Exception, SystemExit), e:
log_broken(mod_name, e)
elif is_package(x):
#--HELPER FUNCTIONS------------------------------------------------------------
def ip_passes(mod_name):
print mod_name
IPY_PASSES.write(mod_name + "\n")
IPY_PASSES.flush()
def ip_fails(mod_name):
IPY_FAILS.write(mod_name + "\n")
IPY_FAILS.flush()
#--MAIN-----------------------------------------------------------------------
nt.chdir(CPY_DIR + r"\Lib")
for mod_name in TEST_LIST:
proc = Process()
proc.StartInfo.FileName = sys.executable
proc.StartInfo.Arguments = "test\\" + mod_name
proc.StartInfo.UseShellExecute = False
proc.StartInfo.RedirectStandardOutput = True
if (not proc.Start()):
raise Exception("Python process failed to start: " + mod_name)
else:
cpymod_dir = proc.StandardOutput.ReadToEnd()
if not proc.HasExited:
raise Exception("Python process should have exited by now: " +
mod_name)
def renameF(preName, newName):
chdir(os.path.dirname(preName))
os.rename(preName, newName)
IPY_PASSES = open("IPY_PASSES.log", "w")
#Log containing all tests IP fails
IPY_FAILS = open("IPY_FAILS.log", "w")
#--HELPER FUNCTIONS------------------------------------------------------------
def ip_passes(mod_name):
print mod_name
IPY_PASSES.write(mod_name + "\n")
IPY_PASSES.flush()
def ip_fails(mod_name):
IPY_FAILS.write(mod_name + "\n")
IPY_FAILS.flush()
#--MAIN-----------------------------------------------------------------------
nt.chdir(CPY_DIR + r"\Lib")
for mod_name in TEST_LIST:
proc = Process()
proc.StartInfo.FileName = sys.executable
proc.StartInfo.Arguments = "test\\" + mod_name
proc.StartInfo.UseShellExecute = False
proc.StartInfo.RedirectStandardOutput = True
if (not proc.Start()):
raise Exception("Python process failed to start: " + mod_name)
else:
cpymod_dir = proc.StandardOutput.ReadToEnd()
if not proc.HasExited:
raise Exception("Python process should have exited by now: " + mod_name)
import os
import sys
from nt import chdir
#path = os.path.dirname(os.path.abspath(__file__))
path = sys.argv[1]
print path
chdir(path)
fileList = os.listdir(path)
print fileList
for i in fileList:
if (i.find('GH') == 0):
newname = 'GH' + i[4:8] + i[2:4] + '.MP4'
print newname
os.rename(i, newname)
import os,re
_1path="."
from nt import chdir
chdir(_1path)
for item in os.listdir(_1path):
_1Re=re.match("^.*?([0-9a-z\-\_]+).*?(\.mp4|\.mts)",item,re.I)
if _1Re:
newname=_1Re.group(1)+_1Re.group(2)
os.rename(item,newname)
print(item+"-->"+newname)
input()
def renameF(preName, newName):
chdir(os.path.dirname(preName))
os.rename(preName, newName)
#完善发件人收件人，主题信息
message = MIMEMultipart()
message['From'] = formataddr(["姚佳龙", sender])
message['To'] = formataddr(["wqx", ''.join(receivers)])
subject = '测试报告'
message['Subject'] = Header(subject, 'utf-8')
#正文部分
textmessage = MIMEText('', 'html', 'utf-8')
message.attach(textmessage)
workLoc = os.path.join('E:\\', 'pythonProject', 'interface')
# #检查路径有效性
if (os.path.exists(workLoc)) & (os.path.isdir(workLoc)):
#尝试改变当前工作路径：
chdir(workLoc)
else:
print('路径无效，请从新检查')
sys.exit()
#尝试添加附件
File = '报告.html'
print("附件文件名为：%s" % File)
FileLoc = os.path.join(workLoc, File)
FileAtt = MIMEApplication(open(FileLoc, 'rb').read())
FileAtt.add_header('Content-Disposition', 'attachment', filename=File)
message.attach(FileAtt)
#发送邮件操作
smtpObj.sendmail(sender, receivers, message.as_string())
smtpObj.quit()
sys.exit(1)
# Try to import a common module that *should* work.
print "Looking for Python root directory..."
while 1:
pwd = nt.getcwd()
##print "Could it be", `pwd`, "?"
try:
open("Lib\\os.py").close()
##print "It appears so."
break
except IOError:
##print "Hm, it doesn't appear to be. Try the parent directory."
try:
opwd = pwd
nt.chdir("..")
pwd = nt.getcwd()
if opwd == pwd:
##print "Seems like we're in the root already."
raise nt.error
except nt.error:
##print "Can't chdir to the parent -- we're stuck."
pass
else:
##print "Try again one level higher."
continue
print "Hey, would you like to help?"
print "Please enter the pathname of the Python root."
while 1:
try:
dirname = raw_input("Python root: ")
def parse(self,response):
browser=webdriver.Chrome("D:/tools/chromedriver.exe")
browser.get(response.url)
s1=Select(browser.find_element_by_xpath("//*[@id='ctl00_MainContent_lbCommodity']"))
for select in s1.options:
s1.select_by_visible_text(select.text)
excel=browser.find_element_by_xpath("//*[@id='ctl00_MainContent_rblOutputType_2']")
excel.click()
startdate=browser.find_element_by_xpath("//*[@id='ctl00_MainContent_tbStartDate']")
enddate=browser.find_element_by_xpath("//*[@id='ctl00_MainContent_tbEndDate']")
chdir(os.path.dirname("D:/spider/fasusda/ExportSalesDataByCommodity.xls"))
filetime=time.localtime(os.stat("D:/spider/fasusda/ExportSalesDataByCommodity.xls").st_ctime)
os.remove("D:/spider/fasusda/ExportSalesDataByCommodity.xls")
print filetime
date=[str(filetime.tm_mon),str(filetime.tm_mday),str(filetime.tm_year)]
date=["12","9","2016"]
localtime=time.strftime("%Y%m%d",time.localtime(time.time()))
if int(date[0])<10:
date[0]='0'+date[0]
if int(date[1])<10:
date[1]='0'+date[1]
print date
startdate.clear()
startdate.send_keys(date[0]+"/"+date[1]+"/"+date[2])
enddate.clear()
print localtime[4:6]+"/"+localtime[6:]+"/"+localtime[:4]
enddate.send_keys(localtime[4:6]+"/"+localtime[6:]+"/"+localtime[:4])
time.sleep(20)
b=29
if date[0]=='01' or date[0]=='03' or date[0]=='05' or date[0]=='07' or date[0]=='08' or date[0]=='10':
if int(date[1])+7>31:
temp=int(date[1])+7-31
if temp<10:
date[1]='0'+str(temp)
else:
date[1]=str(temp)
a=int(date[0])+1
if a<10:
date[0]="0"+str(a)
else:
date[0]=str(a)
else:
temp=int(date[1])+7
if temp<10:
date[1]='0'+str(temp)
else:
date[1]=str(temp)
elif date[0]=='04' or date[0]=='06' or date[0]=='09' or date[0]=='11':
if int(date[1])+7>30:
temp=int(date[1])+7-30
if temp<10:
date[1]='0'+str(temp)
else:
date[1]=str(temp)
a=int(date[0])+1
if a<10:
date[0]="0"+str(a)
else:
date[0]=str(a)
else:
temp=int(date[1])+7
if temp<10:
date[1]='0'+str(temp)
else:
date[1]=str(temp)
elif date[0]=='12':
if int(date[1])+7>31:
temp=int(date[1])+7-31
if temp<10:
date[1]='0'+str(temp)
else:
date[1]=str(temp)
a=int(date[2])+1
date[0]='01'
date[2]=str(a)
else:
temp=int(date[1])+7
if temp<10:
date[1]='0'+str(temp)
else:
date[1]=str(temp)
elif date[0]=='02':
year=int(date[2])
if (year%4==0 and year%100!=0) or year%400==0:
b=29
else:
b=28
if int(date[1])+7>b:
temp=int(date[1])+7-b
if temp<10:
date[1]='0'+str(temp)
else:
date[1]=str(temp)
date[0]='03'
else:
temp=int(date[1])+7
if temp<10:
date[1]='0'+str(temp)
else:
date[1]=str(temp)
#enddate.clear()
#enddate.send_keys(date[0]+"/"+date[1]+"/"+date[2])
submit=browser.find_element_by_xpath("//*[@id='ctl00_MainContent_btnSubmit']")
submit.click()
time.sleep(500)
lexcel,sign=self.readexcel()
browser.quit()
conn=pymssql.connect(host='.',port='5889',user='******',password='******',database='NgoicDataAutoCollection',charset='utf8')
cur=conn.cursor()
if sign!="":
print sign
sql="select Top 1 * from USDA_Exports_Sales where convert(varchar(10),Date,121) = "+"'"+str(sign)+"'"
#sql="select Top 1 * from USDA_Exports_Sales"
cur.execute(sql)
result=cur.fetchall()
if len(result)==0:
sqlinsert="insert USDA_Exports_Sales values(%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s,%s)"
cur.executemany(sqlinsert,lexcel)
try:
conn.commit()
except:
conn.rollback()
cur.close()
conn.close()
for filter in [strip_ws, tabs_are_bad]:
filter(lines)
def strip_ws(lines):
for i in xrange(len(lines)):
#If the line doesn't consist exclusively of WS
if re.match("^[\s]*$", lines[i])==None:
lines[i] = lines[i].rstrip() + "\n"
def tabs_are_bad(lines):
for i in xrange(len(lines)):
if (re.match("^\t", lines[i])!=None):
lines[i] = re.sub("\t", " ", lines[i])
#--MAIN------------------------------------------------------------------------
nt.chdir(TEST_DIR)
for test in TESTS:
#Get the contents of the file
f = open(test, "r")
lines = f.readlines()
f.close()
#Fix the file
apply_filters(lines)
#Check out the file
try:
ec = nt.spawnv(nt.P_WAIT, TF_DIR, ["tf", "edit", test])
except Exception, e:
print "FAILED: could not check out %s from TFS: %s" % (test, str(e))
def get_seeds(self):
seedfiles = os.listdir(self._seedsdir)
for f in seedfiles:
if not f.endswith(".done"):
continue
real_f = f.split(".done")[0]
lines = list(file(self._seedsdir+"/"+real_f))
numLine = len(lines)
self.logger.debug(u"start file: real_f, with {} lines".format(numLine))
for idxLine, line in enumerate(lines):
url, suburl_filter = line.strip().split("\t", 2)
self.logger.debug(u"start idxLine: {}/{}".format(idxLine, numLine))
ret = False
# conn = getConn("taierdb")
# table = 'app_Seeds'
try:
print "finish parsing txt",datetime.datetime.now()
ret = self.get_from_url(url, suburl_filter)
print "finish paring page",datetime.datetime.now()
query = {'_id':url}
# sql = u"""select errorTimes from app_Seeds where url = '{}'""".format(url);
# errorTimessql = sqlExecute(sql, conn)
errorTimessql = self._mongowrapper.query_one(query,self._seedscolection)
errorTimes=0
if errorTimessql:
if 'errorTimes'in errorTimessql.keys():
errorTimes = errorTimessql['errorTimes']
# if not errorTimessql[0]['errorTimes']:
# errorTimes = 0
# else:
# errorTimes = errorTimessql[0]['errorTimes'];
if ret:
query = {"_id": url.strip(), "domain": suburl_filter}
measures = {"fetchTimes": 1,"errorTimes":errorTimes}
# sql = u"""update app_Seeds set fetchTimes = 1 where url = '{}'""".format(url);
else:
# dimensions = {"url": url.strip(), "domain": suburl_filter}
errorTimes += 1
query = {"_id": url.strip(), "domain": suburl_filter}
measures = {"fetchTimes": 1,"errorTimes":errorTimes}
# sql = u"""update app_Seeds set errorTimes = errorTimes + 1, fetchTimes = 1 where url = '{}'""".format(url);
except Exception as e:
self.logger.warning(str(e))
self.logger.warning(traceback.format_exc())
continue
try:
self._mongowrapper.find_and_modify(query,measures,self._seedscolection)
print "addddddddddddda newlink"
#sqlExecute(sql, conn);
except Exception as e:
self.logger.warning(str(e))
self.logger.warning(traceback.format_exc())
# conn.close()
# print "finish db seeds",datetime.datetime.now()
name = self._seedsdir+"/"+real_f+'.fetched'
chdir(os.path.dirname(self._seedsdir+"/"+real_f))
os.rename(real_f,name)
os.remove(real_f+'.done')
def strip_ws(lines):
for i in xrange(len(lines)):
#If the line doesn't consist exclusively of WS
if re.match("^[\s]*$", lines[i]) == None:
lines[i] = lines[i].rstrip() + "\n"
def tabs_are_bad(lines):
for i in xrange(len(lines)):
if (re.match("^\t", lines[i]) != None):
lines[i] = re.sub("\t", " ", lines[i])
#--MAIN------------------------------------------------------------------------
nt.chdir(TEST_DIR)
for test in TESTS:
#Get the contents of the file
f = open(test, "r")
lines = f.readlines()
f.close()
#Fix the file
apply_filters(lines)
#Check out the file
try:
ec = nt.spawnv(nt.P_WAIT, TF_DIR, ["tf", "edit", test])
except Exception, e:
print "FAILED: could not check out %s from TFS: %s" % (test, str(e))
# print(soup)
for each_li in div.find_all('li'):
title = each_li['title']
a_href = each_li.find('a')['href']
voice_id = re.split('\D', a_href)[-1]
# print(title, voice_id)
info_list[voice_id] = title
return info_list
if __name__ == '__main__':
# from page
voice_info_list = get_all_ids(site)
# or from file
# voice_info_list = {}
# with codecs.open('info.txt', 'r', 'utf-8') as fp:
# for line in fp:
# voice_info_list[re.split('\D', line)[0]] = re.split(' ', line)[1]
for file_name in os.listdir(dir_path):
try:
value = voice_info_list[file_name]
# print(file_name, value)
if value:
pre_name = os.path.join(dir_path, file_name)
new_name = os.path.join(dir_path, value.rstrip() + '.mp3')
chdir(os.path.dirname(pre_name))
os.rename(pre_name, new_name)
print(file_name + ' rename to ' + value.rstrip() + '.mp3')
except KeyError as e:
print("no such id : " + file_name)
