def find_spids_and_holding_dates(self,date_string,verbose,mtime_after):
self.h = {}
self.current_date = date_string
filename = self.file_template % date_string
if os.path.exists(filename):
if mtime_after and get_file_mtime(filename) < mtime_after:
return self.h
# print filename
self.parser.parse(filename)
if verbose and len(self.h) == 0:
print " Warning: no questions found in "+filename
return self.h
def find_spids_and_holding_dates(self,date_string,verbose,mtime_after):
self.h = {}
self.current_date = date_string
filename = self.file_template % date_string
if os.path.exists(filename):
if mtime_after and get_file_mtime(filename) < mtime_after:
return self.h
# print filename
self.parser.parse(filename)
if verbose and len(self.h) == 0:
print " Warning: no questions found in "+filename
return self.h
# (c) Look through the Official Reports for questions that were
# actually asked in the parliament.
#
# ------------------------------------------------------------------------
# First (a) the Business Bulletins:
bulletin_prefix = "http://www.scottish.parliament.uk/business/businessBulletin/"
bulletins_directory = "../../../parldata/cmpages/sp/bulletins/"
bulletin_filenames = glob.glob( bulletins_directory + "day-*" )
bulletin_filenames.sort()
for day_filename in bulletin_filenames:
if modified and get_file_mtime(day_filename) < modified_after:
continue
m = re.search('(?i)day-(bb-(\d\d))_([ab]b-(\d\d)-(\d\d)-?(\w*)\.html?)$',day_filename)
if not m:
if verbose: print "Couldn't parse file %s" % ( day_filename )
continue
subdir = m.group(1)
two_digit_year = m.group(2)
page = m.group(3)
two_digit_month = m.group(4)
two_digit_day = m.group(5)
section = m.group(6)
# (c) Look through the Official Reports for questions that were
# actually asked in the parliament.
#
# ------------------------------------------------------------------------
# First (a) the Business Bulletins:
bulletin_prefix = "http://www.scottish.parliament.uk/business/businessBulletin/"
bulletins_directory = "../../../parldata/cmpages/sp/bulletins/"
bulletin_filenames = glob.glob(bulletins_directory + "day-*")
bulletin_filenames.sort()
for day_filename in bulletin_filenames:
if modified and get_file_mtime(day_filename) < modified_after:
continue
m = re.search('(?i)day-(bb-(\d\d))_([ab]b-(\d\d)-(\d\d)-?(\w*)\.html?)$',
day_filename)
if not m:
if verbose: print "Couldn't parse file %s" % (day_filename)
continue
subdir = m.group(1)
two_digit_year = m.group(2)
page = m.group(3)
two_digit_month = m.group(4)
two_digit_day = m.group(5)
section = m.group(6)
