def extract_email_by_re(self):
email = ''
try:
emailgrp = re.search("(\w+-*[.|\w]*)*@(\w+[.])*\w+",self.text)
if emailgrp:
email = emailgrp.group()
except Exception,e:
cprint("FAIL","Seaching email timeout,maybe there is no email info in this resume,please check it by yourself.")
def main():
if(len(sys.argv)!= 2):
bcolors.cprint('WARNING',"usage: python main.py input_file")
sys.exit(1)
filename = sys.argv[1]
cprint('HEADER',"Input file is "+filename)
filelist = sys.argv[1].split('.')
cprint('HEADER',"File suffix is "+filelist[-1])
efactory = ExtractFactory(filename,filelist[-1])
efactory.extract_control()
def store_2_db(self,name,email,phone,filepath,filetext):
cprint("HEADER",'**************************************')
cprint("OK",name)
cprint("OK",email)
cprint("OK",phone)
cprint("OK",filepath)
cprint("HEADER",'**************************************')
#store file
cprint("OK","File size : "+str(os.path.getsize( filepath )) + " bytes" )
fileID = GFS.fs.put( open( filepath, 'rb') )
cprint("OK","File ID MD5 : "+str(fileID) )
###
# out = fs.get(fileID)
# output = open(name+email+'.doc', 'wb')
# output.write(out.read())
# output.close()
# print out.length
###
#get one collection
# print GFS.db.collection_names()
posts = GFS.db.cvtext
strlist = filepath.split('.')
filename=name+'_'+email+'_'+phone+'.'+strlist.pop()
cprint("OK","Create new file name : "+filename)
post = {"name": name,"email": email,"phone": phone,"filename":filename,"filetext": filetext,"fileid":fileID}
cprint("OK","Record MD5 : "+str(posts.insert(post)) )
def __init__(self):
cprint("HEADER","__init__")
GFS._connect()
cprint("HEADER","server info " + " * " * 40)
cprint("HEADER",str(GFS.conn.server_info) )
cprint("HEADER","server info " + " * " * 40)
def extract_control(self):
gfs = GFS()
if self.suffix == "pdf":
cprint("HEADER", "Enter extract pdf...")
pdf = ExtractPdf(self.filename)
return_list = pdf.extract_text_from_pdf1()
if return_list[0] == 0:
print pdf.get_all_text()
cprint("OK", return_list[1])
# extract name, email, phone number
info_list = self.extract_info(pdf.text)
# import mongoDB
if info_list[0] and info_list[1] and info_list[2]:
gfs.store_2_db(info_list[0], info_list[1], info_list[2], self.filename, pdf.text)
elif return_list[0] == -1:
cprint(
"WARNING",
return_list[1]
+ ",make sure the pdf file is not produced by scanned images and no space/special characters in file name as well.",
)
else:
cprint("FAIL", return_list[1])
elif self.suffix == "docx":
cprint("HEADER", "Enter extract docx...")
docx = ExtractDocx(self.filename)
return_list = docx.extract_text_from_docx1()
if return_list[0] == 0:
print docx.get_all_text()
cprint("OK", return_list[1])
# extract name, email, phone number
info_list = self.extract_info(docx.text)
# import mongoDB
if info_list[0] and info_list[1] and info_list[2]:
gfs.store_2_db(info_list[0], info_list[1], info_list[2], self.filename, docx.text)
elif return_list[0] == -1:
cprint(
"WARNING",
return_list[1]
+ ",make sure the file is not empty and no space/special characters in file name as well.",
)
else:
cprint("FAIL", return_list[1])
elif self.suffix == "txt":
cprint("HEADER", "Enter extract txt...")
txt = ExtractTxt(self.filename)
return_list = txt.extract_text_from_txt()
if return_list[0] == 0:
# print txt.get_all_text()
cprint("OK", return_list[1])
# extract name, email, phone number
info_list = self.extract_info(txt.text)
# import mongoDB
if info_list[0] and info_list[1] and info_list[2]:
gfs.store_2_db(info_list[0], info_list[1], info_list[2], self.filename, txt.text)
elif return_list[0] == -1:
cprint(
"WARNING",
return_list[1]
+ ",make sure the file is not empty and no space/special characters in file name as well.",
)
else:
cprint("FAIL", return_list[1])
elif self.suffix == "doc":
cprint("HEADER", "Enter extract doc...")
doc = ExtractDoc(self.filename)
return_list = doc.extract_text_from_doc()
if return_list[0] == 0:
print doc.get_all_text()
cprint("OK", return_list[1])
# extract name, email, phone number
info_list = self.extract_info(doc.text)
# import mongoDB
if info_list[0] and info_list[1] and info_list[2]:
gfs.store_2_db(info_list[0], info_list[1], info_list[2], self.filename, doc.text)
elif return_list[0] == -1:
cprint(
"WARNING",
return_list[1]
+ ",make sure the file is not empty and no space/special characters in file name as well.",
)
else:
cprint("FAIL", return_list[1])
else:
cprint(
"WARNING", "Warning:Input a wrong formated file,currently,this tool only accept .pdf/.docx/.doc/.txt"
)
def extract_info(self, text):
name = "tester"
phonenum = ""
email = ""
# extract phone number
ps = PhoneStrategy(text)
phone = ps.extract_phone_interface()
if phone:
cprint("OK", "Phone:" + phone)
phonenum = phone
else:
cprint("FAIL", "Extract phone number failed")
# extract email
es = EmailStrategy(text)
email_tmp = es.extract_email_interface()
if email_tmp:
cprint("OK", "Email:" + email_tmp)
email = email_tmp
else:
cprint("FAIL", "Extract email failed")
# extract name
ns = NameStrategy(text)
name_tmp = ns.extract_name_interface()
if name_tmp:
cprint("OK", "Name:" + name_tmp)
name = name_tmp
else:
cprint("FAIL", "Extract name failed")
return [name, email, phonenum]
