def get_workbooks(self):
if self.temp_path is None:
return
filenames = []
for name in os.listdir(self.temp_path):
d = name.split('-',1)
d.append(name)
filenames.append(d)
filenames.sort()
for i,filename,pathname in filenames:
yield (
# We currently don't open with on_demand=True here
# as error filters should be lastish in the chain
# so there's not much win.
# However, if we did, getting rid of the temp dirs
# becomes a problem as, on Windows, they can't be
# deleted until the xlrd.Book object is done with
# and we don't know when that might be :-(
xlrd.open_workbook(
os.path.join(self.temp_path,pathname),
formatting_info=1,
on_demand=False,
ragged_rows=True
),
filename
)
def get_workbooks(self):
"""
If the data to be processed is not stored in files or if
special parameters need to be passed to :func:`xlrd.open_workbook`
then this method must be overriden.
Any implementation must return an iterable sequence of tuples.
The first element of which must be an :class:`xlrd.Book` object and the
second must be the filename of the file from which the book
object came.
"""
for path in self.get_filepaths():
yield (
xlrd.open_workbook(
path,
formatting_info=1,
on_demand=True,
ragged_rows=True),
os.path.split(path)[1]
)
msg = MIMEMultipart()
msg['From'] = send_from
msg['To'] = send_to
msg['Subject'] = unicode(subject, 'utf-8')
msg.attach(MIMEText(text))
with open(files, "rb") as fil:
part = MIMEApplication(fil.read(), Name=basename(files))
part['Content-Disposition'] = 'attachment; filename="%s"' % basename(files)
msg.attach(part)
smtp.sendmail(send_from, send_to, msg.as_string())
# smtp.quit()
w = xlrd.open_workbook("/home/jonatas/Downloads/email.xlsx")
s = w.sheet_by_index(0)
for r in range(s.nrows):
c = s.row_values(r)
if (re.match("(^[a-zA-Z0-9_.+-]+@[a-zA-Z0-9-]+\.[a-zA-Z0-9-.]+$)", c[1])):
print(c[1])
send_mail(
"*****@*****.**", c[1],
"Currículo estudante de enfermagem",
'Sou Débora de Andrade Turíbio, estudante de enfermagem cursando o quinto semestre. Desejo adquirir experiência e oportunidade para poder entrar no mercado de trabalho da saúde, alcançando os objetivos profissionais.',
"./debora.pdf")
def check_file(fname, verbose, do_punc=False, fmt_info=0, encoding='ascii', onesheet=''):
print
print fname
if do_punc:
checker = ispunc
else:
checker = None
try:
book = open_workbook(fname, formatting_info=fmt_info, on_demand=True)
except TypeError:
try:
book = open_workbook(fname, formatting_info=fmt_info)
except TypeError:
# this is becoming ridiculous
book = open_workbook(fname)
totold = totnew = totnotnull = 0
if onesheet is None or onesheet == "":
shxrange = range(book.nsheets)
else:
try:
shxrange = [int(onesheet)]
except ValueError:
shxrange = [book.sheet_names().index(onesheet)]
for shx in shxrange:
sheet = book.sheet_by_index(shx)
ngoodrows = number_of_good_rows(sheet, checker)
ngoodcols = number_of_good_cols(sheet, checker, nrows=ngoodrows)
oldncells = sheet.nrows * sheet.ncols
newncells = ngoodrows * ngoodcols
totold += oldncells
totnew += newncells
nnotnull = 0
sheet_density_pct_s = ''
if verbose >= 2:
colxrange = range(ngoodcols)
for rowx in xrange(ngoodrows):
rowtypes = sheet.row_types(rowx)
for colx in colxrange:
if rowtypes[colx] not in null_cell_types:
nnotnull += 1
totnotnull += nnotnull
sheet_density_pct = (nnotnull * 100.0) / max(1, newncells)
sheet_density_pct_s = "; den = %5.1f%%" % sheet_density_pct
if verbose >= 3:
# which rows have non_empty cells in the right-most column?
lastcolx = sheet.ncols - 1
for rowx in xrange(sheet.nrows):
cell = sheet.cell(rowx, lastcolx)
if cell.ctype != XL_CELL_EMPTY:
print "%s (%d, %d): type %d, value %r" % (
cellname(rowx, lastcolx), rowx, lastcolx, cell.ctype, cell.value)
if (verbose
or ngoodrows != sheet.nrows
or ngoodcols != sheet.ncols
or (verbose >= 2 and ngoodcells and sheet_density_pct < 90.0)
):
if oldncells:
pctwaste = (1.0 - float(newncells) / oldncells) * 100.0
else:
pctwaste = 0.0
shname_enc = safe_encode(sheet.name, encoding)
print "sheet #%2d: RxC %5d x %3d => %5d x %3d; %4.1f%% waste%s (%s)" \
% (shx, sheet.nrows, sheet.ncols,
ngoodrows, ngoodcols, pctwaste, sheet_density_pct_s, shname_enc)
if hasattr(book, 'unload_sheet'):
book.unload_sheet(shx)
if totold:
pctwaste = (1.0 - float(totnew) / totold) * 100.0
else:
pctwaste = 0.0
print "%d cells => %d cells; %4.1f%% waste" % (totold, totnew, pctwaste)
