def main():
"""docstring"""
LOG.debug('Started')
with open(HTML_DIR + CDC_FILENAME, 'rU') as csv_file:
LOG.info("Reading URLs from %s", HTML_DIR+CDC_FILENAME)
reader = UnicodeReader(csv_file)
# skip the header
reader.next()
for rec in reader:
state = rec[STATE_INDEX]
filename = state.replace(' ', '_')
url = rec[URL_INDEX]
LOG.info("Processing %s", state)
# retrieve the webpage data
webpage_data = get_info_on_webpage(url)
# get the addresses from the local csv files
csv_addresses = get_addresses_from_csv(CSV_DIR + filename + ".csv")
unique_in_webpage = [rec for rec in webpage_data
if normalize_address(rec[ADDRESS_INDEX])
not in csv_addresses]
unique_in_webpage = sorted(unique_in_webpage,
key=operator.itemgetter(CITY_INDEX))
try:
with open(OUTPUT_DIR + filename + ".csv", "wb") as csv_f:
writer = UnicodeWriter(csv_f)
writer.writerows(unique_in_webpage)
except UnicodeEncodeError as error:
print "UnicodeEncode Error"
LOG.debug('Finished')
def file_Write(self,outputList):
with open('translated.csv', 'wb') as files:
writer = UnicodeWriter(files,quoting=csv.QUOTE_ALL)
writer.writerows(outputList)