学习大数据DAY57 新的接口配置

#!/bin/python3
import requests
from hdfs import *
import os
# *客户需求: 把 https://zhiyun.pub:9099/site/c-class?page=1 所有
数据定时同步到 Hive 数仓
lines = []
page = 1
pages = 1
def get_data(page=1):
global pages
print(f"正在抽取第{page}页的数据")
url = f"https://zhiyun.pub:9099/site/c-class?page={page}"
r = requests.get(url)
data = r.json()
if data["status"] == 1:
page_data = data["data"]
# 更新页数
pages = data["pages"]
# print(f"pages: {pages}")
# print(page_data)
for item in page_data:
# {'id': '1', 'levels': '1', 'classcode': '01',
'classname': '中西成药', 'saletax': '0.00', 'createtime':
'1900-01-20 11:16:47', 'createuser': '1002', 'notes': 'null',
'stamp': '562664386'}
# 字典 => Hive 数据格式# A B C D ...
values = item.values()
# print(values)
# dict_values(['1', '1', '01', '中西成药', '0.00',
'1900-01-20 11:16:47', '1002', 'null', '562664386'])
# 把所有元素转换成字符串
str_list = []
for value in values:
str_list.append(f"{value}")
# print(str_list)
# ['1', '1', '01', '中西成药', '0.00', '1900-01-20
11:16:47', '1002', 'null', '562664386']
# 字符串的 join 方法, 把列表的所有元素拼接起来
line = "\t".join(str_list)
# print(line)
# 1
1
01
中西成
药
0.00
1900-01-20
11:16:47
1002
null
562664386
lines.append(line)
# print(lines)
def do_get_data():
global page, pages
while page <= pages:
# print(f"pages: {pages}")
get_data(page)
# print(f"pages: {pages}")
page = page + 1
# 写入到数据文件
with
open("/zhiyun/shihaihong/data/c_class.data","w",encoding="utf-
8") as f:
content = "\n".join(lines)
f.write(content)
print("文件写入成功")
# 上传到 HDFSdef upload_data_hdfs():
# 创建 HDFS 目录
client = Client("http://192.168.200.100:9870")
client.makedirs("/zhiyun/shihaihong/ods/c_class")
# 上传
# 注意再次上传会报已存在错误
client.upload("/zhiyun/shihaihong/ods/c_class",
"/zhiyun/shihaihong/data/c_class.data");
print("上传成功")
# Hive 建表
def craete_hive_table():
os.system('''
hive -e '
create database if not exists ods_shihaihong location
"/zhiyun/shihaihong/ods";
create external table if not exists ods_shihaihong.c_class(
id int,
levels int,
classcode string,
classname string,
saletax decimal(10,2),
createtime timestamp,
createuser string,
notes string,
stamp int
) row format delimited fields terminated by "\t"
lines terminated by "\n"
stored as textfile
location "/zhiyun/shihaihong/ods/c_class";
'
''')
# 验证数据
def check_data():
os.system('''
hive -e '
select count(1) from ods_shihaihong.c_class;
select * from ods_shihaihong.c_class limit 5;
'
''')# 爬取数据
do_get_data()
upload_data_hdfs()
craete_hive_table()
check_data()

#!/bin/python3
import requests
from hdfs import *
import os
import pandas
# *客户需求: 定时下载 https://zhiyun.pub:9099/设备清单.xlsx , 然后
上传到 HDFS 建表,更新
def get_data():
print(f"正在抽取数据")
url = f"https://zhiyun.pub:9099/设备清单.xlsx"
r = requests.get(url)
if r.status_code == 200:
with open("/zhiyun/shihaihong/data/download_设备清
单.xlsx","wb") as f:
f.write(r.content)
df=pandas.read_excel("/zhiyun/shihaihong/data/downl
oad_设备清单.xlsx")df.to_csv("/zhiyun/shihaihong/data/download_设备清
单.csv",index=False,header=False)
print("文件下载成功")
f.close()
else:
print("文件下载失败")
# 上传到 HDFS
def upload_data_hdfs():
# 创建 HDFS 目录
client = Client("http://192.168.200.100:9870")
client.makedirs("/zhiyun/shihaihong/ods/c_tools")
# 上传
# 注意再次上传会报已存在错误
client.upload("/zhiyun/shihaihong/ods/c_tools",
"/zhiyun/shihaihong/data/download_设备清单.csv");
print("上传成功")
# Hive 建表
def create_hive_table():
os.system('''
hive -e '
create database if not exists ods_shihaihong location
"/zhiyun/shihaihong/ods";
create external table if not exists ods_shihaihong.c_tools(
id int,
hospital string,
tool_name string,
manufacturer string,
produce_date string,
administrative_officer string,
picture string
) row format delimited fields terminated by ","
lines terminated by "\n"
stored as textfile
location "/zhiyun/shihaihong/ods/c_tools";
'
''')
# 验证数据
# def check_data():#
os.system('''
#
hive -e '
#
select count(1) from ods_shihaihong.c_class;
#
select * from ods_shihaihong.c_class limit 5;
# '
#
''')
# 爬取数据
get_data()
upload_data_hdfs()
create_hive_table()
# check_data()