Last active
December 9, 2016 09:45
-
-
Save linroex/89b0919399fd70cc9a70bd33917fe957 to your computer and use it in GitHub Desktop.
高速公路 ETC 資料下載程式,請自行修改相關參數
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import tarfile | |
import os | |
import datetime | |
import csv | |
import urllib.error | |
from urllib import request | |
from glob import glob | |
from multiprocessing.dummy import Pool | |
# import mysql.connector | |
def main(): | |
s = datetime.datetime(2016,3,1) | |
e = datetime.datetime(2016,5,2) | |
pool= Pool(20) | |
# pool.map(download_and_extract_one_file, get_list(s, e)) | |
pool.map(handle_csv, glob(os.path.join(folder, 'temp/M03A/*/*/*.csv'))) | |
pool.close() | |
pool.join() | |
def download_and_extract_one_file(url): | |
f = download(url) | |
try: | |
with tarfile.open(f, 'r:gz') as tar: | |
tar.extractall('temp/') | |
os.remove(f) | |
except FileNotFoundError: | |
pass | |
print(f.split('/')[-1]) | |
def handle_csv(_from): | |
to=os.path.join(folder, 'temp/all.csv') | |
with open(to, 'a', encoding='utf8') as output: | |
with open(_from, 'r', encoding='utf8') as input: | |
input_rows = input.read().split("\n") | |
for row in input_rows: | |
row = row.split(",") | |
if row[0] != '': | |
row[0] = str(datetime.datetime.strptime(row[0], "%Y-%m-%d %H:%M").timestamp()) | |
output.write(",".join(row) + "\n") | |
print(_from) | |
def handle_sql(path): | |
connect = mysql.connector.connect(user='root', database='etc') | |
cursor = connect.cursor() | |
with open(path, 'r', encoding='utf8') as f: | |
for row in csv.reader(f): | |
cursor.execute('insert into flow (datetime, gantry, direction, vehicletype, number) values ("{}", "{}", "{}", {}, {})'.format( | |
row[0], | |
row[1], | |
row[2], | |
int(row[3]), | |
int(row[4]) | |
)) | |
connect.commit() | |
print(path) | |
cursor.close() | |
connect.close() | |
def get_list(start, end): | |
step = datetime.timedelta(days=1) | |
url_template = 'http://tisvcloud.freeway.gov.tw/history/TDCS/M03A/M03A_{}.tar.gz' | |
while end > start: | |
yield url_template.format(start.strftime('%Y%m%d')) | |
start = start + step | |
def download(url): | |
path = os.path.join(folder, 'temp/' + url.split("/")[-1]) | |
try: | |
request.urlretrieve(url, path) | |
except ConnectionResetError: | |
print('Connect Error') | |
except urllib.error.HTTPError: | |
print('File Not Found: ' + path) | |
return path | |
if __name__ == '__main__': | |
folder = os.path.dirname(os.path.realpath(__file__)) | |
main() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment