'添加远程下载文件脚本，并调整目录结构'

Author: cuizhongyi

qiangpiao.py renamed to 12306qiangpiao/qiangpiao.py

@@ -1,5 +1 @@
-## 1、12306抢票脚本---qiangpiao.py
-
-## 2、段友之家贴吧数据爬取---nhdz.py
-
-## 3、百思不得姐网站图片数据爬取---bsbdj.py
+## Python 小脚本，Python版本为3.6

README.md

@@ -0,0 +1,61 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+"""
+通过paramiko从远处服务器下载文件资源到本地
+author: gxcuizy
+time: 2018-08-01
+"""
+
+import paramiko
+import os
+from stat import S_ISDIR as isdir
+
+
+def down_from_remote(sftp_obj, remote_dir_name, local_dir_name):
+    """远程下载文件"""
+    remote_file = sftp_obj.stat(remote_dir_name)
+    if isdir(remote_file.st_mode):
+        # 文件夹，不能直接下载，需要继续循环
+        check_local_dir(local_dir_name)
+        print('开始下载文件夹：' + remote_dir_name)
+        for remote_file_name in sftp.listdir(remote_dir_name):
+            sub_remote = os.path.join(remote_dir_name, remote_file_name)
+            sub_remote = sub_remote.replace('\\', '/')
+            sub_local = os.path.join(local_dir_name, remote_file_name)
+            sub_local = sub_local.replace('\\', '/')
+            down_from_remote(sftp_obj, sub_remote, sub_local)
+    else:
+        # 文件，直接下载
+        print('开始下载文件：' + remote_dir_name)
+        sftp.get(remote_dir_name, local_dir_name)
+
+
+def check_local_dir(local_dir_name):
+    """本地文件夹是否存在，不存在则创建"""
+    if not os.path.exists(local_dir_name):
+        os.makedirs(local_dir_name)
+
+
+if __name__ == "__main__":
+    """程序主入口"""
+    # 服务器连接信息
+    host_name = '172.17.2.18'
+    user_name = 'dev'
+    password = 'dev@zdlh'
+    port = 22
+    # 远程文件路径（需要绝对路径）
+    remote_dir = '/data/nfs/zdlh/pdf/2018/07/31'
+    # 本地文件存放路径（绝对路径或者相对路径都可以）
+    local_dir = 'file_download/'
+
+    # 连接远程服务器
+    t = paramiko.Transport((host_name, port))
+    t.connect(username=user_name, password=password)
+    sftp = paramiko.SFTPClient.from_transport(t)
+
+    # 远程文件开始下载
+    down_from_remote(sftp, remote_dir, local_dir)
+
+    # 关闭连接
+    t.close()

bsbdj.py renamed to bsbdj/bsbdj.py

@@ -0,0 +1,22 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+import json
+
+# 程序主入口
+if __name__ == "__main__":
+    """解读字符串拼装成json写入文件，方便其他语言解析数据"""
+    file_path = 'json.txt'
+    file_obj = open(file_path, "r", encoding='UTF-8')
+    all_lines = file_obj.readlines()
+    data = {}
+    key_value = 0
+    for line in all_lines:
+        line_info = line.split(',')
+        if line_info:
+            info = {"name": line_info[0], "url": line_info[1].replace("\n", "")}
+            data[key_value] = info
+            key_value += 1
+    file_obj.close()
+    file = open('json.json', 'w', encoding='utf-8')
+    json.dump(data, file, ensure_ascii=False)

download_remote/download_folder.py

@@ -0,0 +1,6 @@
+111111,http://www.baidu.com
+222222,http://www.sina.com
+333333,http://www.google.com
+444444,http://www.163.com
+555555,http://www.qq.com
+666666,http://www.y0701.com

json/json.py

@@ -0,0 +1,15 @@
+#!/usr/bin/env python
+# -*- coding: utf-8 -*-
+
+import requests
+
+# 程序主入口
+if __name__ == "__main__":
+    """模仿浏览器，请求api信息"""
+    url = 'http://xssychina.com/plus/count.php?view=yes&aid=206&mid=1'
+    headers = {
+        'User-Agent': 'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'
+    }
+    request = requests.get(url, headers=headers)
+    html_text = request.text
+    print(html_text)