104 lines
4.0 KiB
Python
104 lines
4.0 KiB
Python
import json
|
|
import time
|
|
|
|
import pymysql
|
|
import os
|
|
import wget
|
|
import random
|
|
|
|
from api_request import ApiRequest
|
|
|
|
|
|
def create_path(target_dir):
|
|
if not os.path.exists(target_dir):
|
|
os.mkdir(target_dir)
|
|
|
|
|
|
def custom_download(url, path):
|
|
try:
|
|
wget.download(url, path)
|
|
print('下载文件“{}”成功'.format(path.split("/")[-1]))
|
|
return True
|
|
except:
|
|
print('！！！下载文件“{}”失败'.format(path.split("/")[-1]))
|
|
return False
|
|
|
|
|
|
def exec_sql(local_db, local_cursor, sql):
|
|
try:
|
|
local_cursor.execute(sql)
|
|
local_db.commit()
|
|
except:
|
|
local_db = pymysql.connect(host='39.101.194.63', port=23306,
|
|
user='root', passwd='passok123A', db='jd_data', charset='utf8mb4')
|
|
local_cursor = local_db.cursor()
|
|
local_cursor.execute(sql)
|
|
local_db.commit()
|
|
|
|
|
|
if __name__ == '__main__':
|
|
target_root_path = "F:/jd_data"
|
|
create_path(target_root_path)
|
|
db = pymysql.connect(host='39.101.194.63', port=23306,
|
|
user='root', passwd='passok123A', db='jd_data', charset='utf8mb4')
|
|
cursor = db.cursor()
|
|
ar = ApiRequest()
|
|
|
|
count = 0
|
|
while True:
|
|
try:
|
|
sql_select = "SELECT id, experiment, variable, model, level, data_size FROM jd_data.data_detail " \
|
|
"WHERE available = 1 AND downloaded = 0 AND model != 'miroc_es2h' AND data_size < 20000000;"
|
|
cursor.execute(sql_select)
|
|
result = cursor.fetchall()
|
|
if len(result) == 0:
|
|
break
|
|
else:
|
|
print("剩余{}个小文件需要下载".format(len(result)))
|
|
row = result[random.choice(range(len(result)))]
|
|
row_id = row[0]
|
|
experiment = row[1]
|
|
variable = row[2]
|
|
model = row[3]
|
|
level = row[4]
|
|
data_size = row[5]
|
|
# experiment_path = target_root_path + '/' + experiment
|
|
# variable_path = experiment_path + '/' + variable
|
|
# create_path(experiment_path)
|
|
# create_path(variable_path)
|
|
target_file_name = " + ".join([experiment, variable, model, level]) + ".zip"
|
|
target_file_full_path = target_root_path + '/' + target_file_name
|
|
print('%s, %s, %s, %s' % (row_id, experiment, variable, model))
|
|
param = {
|
|
'experiment': experiment,
|
|
'variable': variable,
|
|
'model': model,
|
|
'level': level
|
|
}
|
|
reply = ar.get_reply(param)
|
|
if reply:
|
|
remarks = json.dumps(reply)
|
|
location = ''
|
|
content_length = 0
|
|
if reply['state'] == 'completed':
|
|
location = reply['location']
|
|
content_length = reply['content_length']
|
|
sent_to_rmq_at = 'null'
|
|
if 'sent_to_rmq_at' in reply:
|
|
sent_to_rmq_at = "'" + reply['sent_to_rmq_at'].replace("T", " ").replace("Z", "") + "'"
|
|
print(reply)
|
|
sql_update_status = "UPDATE data_detail " \
|
|
"SET available = 1, url = '%s', data_size = %d, update_time = %s, remarks = '%s' " \
|
|
"WHERE id = %d" \
|
|
% (location, content_length, sent_to_rmq_at, remarks.replace("'", "\\'"),
|
|
row_id)
|
|
exec_sql(db, cursor, sql_update_status)
|
|
if custom_download(location, target_file_full_path):
|
|
current_time = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
|
|
sql_update_download = "UPDATE jd_data.data_detail SET downloaded = 1, downloaded_time = '%s' " \
|
|
"WHERE id = %s" % (current_time, row_id)
|
|
exec_sql(db, cursor, sql_update_download)
|
|
except:
|
|
pass
|
|
db.close()
|