修改库里文件





![在这里插入图片描述](/static/img/images/02530.png)

```python
#!/usr/bin/python
# -*- coding: UTF-8 -*-
import os
import sys
import glob
from PyPDF2 import PdfFileMerger, PdfFileReader, PdfFileWriter
def merger_pdf():
    pdf_writer = PdfFileWriter()
    for name in glob.glob(r"E:\Cheats\*.pdf"):
        pdf_reader = PdfFileReader(name)
        for page in range(pdf_reader.getNumPages()):
            pdf_writer.addPage(pdf_reader.getPage(page))
    with open("merges.pdf", "wb") as output_file:
        pdf_writer.write(output_file)
if __name__ == '__main__':
    merger_pdf()
```

或者

```python
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
'''
   #文件名：pdfmerge.py
   本脚本用来合并pdf文件，输出的pdf文件按输入的pdf文件名生成书签
   使用示例如下：
   python pdfmerge.py -p "D:\pdf-files" -o "merged-out.pdf" -b True'
   示例说明：
   要合并的pdf文件所在的路径： D:\pdf-files
   合并后的pdf文件的输出文件名：merged-out.pdf
   是否从pdf文件中导入书签的值：True
'''
import os, sys, codecs
from argparse import ArgumentParser, RawTextHelpFormatter
from PyPDF2 import PdfFileReader, PdfFileWriter, PdfFileMerger
def getfilenames(filepath='',filelist_out=[],file_ext='all'):
    # 遍历filepath下的所有文件，包括子目录下的文件
    for fpath, dirs, fs in os.walk(filepath):
        for f in fs:
            fi_d = os.path.join(fpath, f)
            if  file_ext == 'all':
                filelist_out.append(fi_d)
            elif os.path.splitext(fi_d)[1] == file_ext:
                filelist_out.append(fi_d)
            else:
                pass
    return filelist_out
def mergefiles(path, output_filename, import_bookmarks=False):
    # 遍历目录下的所有pdf将其合并输出到一个pdf文件中，输出的pdf文件默认带书签，书签名为之前的文件名
    # 默认情况下原始文件的书签不会导入，使用import_bookmarks=True可以将原文件所带的书签也导入到输出的pdf文件中
    merger = PdfFileMerger()
    filelist = getfilenames(filepath=path, file_ext='.pdf')
    if len(filelist) == 0:
        print("当前目录及子目录下不存在pdf文件")
        sys.exit()
    for filename in filelist:
        f = codecs.open(filename, 'rb')
        file_rd = PdfFileReader(f)
        short_filename = os.path.basename(os.path.splitext(filename)[0])
        if file_rd.isEncrypted == True:
            print('不支持的加密文件：%s'%(filename))
            continue
        merger.append(file_rd, bookmark=short_filename, import_bookmarks=import_bookmarks)
        print('合并文件：%s'%(filename))
        f.close()
    out_filename=os.path.join(os.path.abspath(path), output_filename)
    merger.write(out_filename)
    print('合并后的输出文件：%s'%(out_filename))
    merger.close()
if __name__ == "__main__":
    description="\n本脚本用来合并pdf文件，输出的pdf文件按输入的pdf文件名生成书签\n使用示例如下："
    description=description+'\npython pdfmerge.py -p "D:\pdf-files" -o "merged-out.pdf" -b True'
    description=description+'\n\n'+"示例说明："
    description=description+'\n'+"要合并的pdf文件所在的路径： D:\pdf-files"
    description=description+'\n'+"合并后的pdf文件的输出文件名：merged-out.pdf"
    description=description+'\n'+"是否从pdf文件中导入书签的值：True"
    # 添加程序帮助，程序帮助支持换行符号
    parser = ArgumentParser(description=description, formatter_class=RawTextHelpFormatter)
    # 添加命令行选项
    parser.add_argument("-p", "--path",
                        dest="path",
                        default=".",
                        help="PDF文件所在目录")
    parser.add_argument("-o", "--output",
                        dest="output_filename",
                        default="merged.pdf",
                        help="合并PDF的输出文件名",
                        metavar="FILE")
    parser.add_argument("-b", "--bookmark",
                    dest="import_bookmarks",
                    default="False",
                    help="是否从pdf文件中导入书签，值可以是'True'或者'False'")
    args = parser.parse_args()
    #try:
    mergefiles(args.path, args.output_filename, args.import_bookmarks)
    #except:
    #    print('Error to merge pdf file:')
    #    print(sys.exc_info()[0],sys.exc_info()[1])
```

python 合并pdf

代码




```python
#!/usr/bin/python
# -*- coding: UTF-8 -*-
import tkinter
import http.client
import time
def get_webservertime(host):
    conn = http.client.HTTPConnection(host)
    conn.request("GET", "/")
    r = conn.getresponse()
    ts = r.getheader('date')  # 获取http头date部分
    # 将GMT时间转换成北京时间
    ltime = time.strptime(ts[5:25], "%d %b %Y %H:%M:%S")
    ttime = time.localtime(time.mktime(ltime) + 8 * 60 * 60)
    dat = "%u-%02u-%02u" % (ttime.tm_year, ttime.tm_mon, ttime.tm_mday)
    tm = "%02u:%02u:%02u" % (ttime.tm_hour, ttime.tm_min, ttime.tm_sec)
    return tm
def tick():
    global time1
    # 获取时间
    time2 = get_webservertime('www.taobao.com')
    # 如果时间发生变化，代码自动更新显示的系统时间
    if time2 != time1:
        time1 = time2
        clock.config(text=time2)
        # calls itself every 200 milliseconds
        # to update the time display as needed
        # could use >200 ms, but display gets jerky
    clock.after(200, tick)
win = tkinter.Tk()
win.title("获取淘宝服务器时间")
time1 = ''
clock = tkinter.Label(win, font=('times', 100, 'bold'), bg='green')
clock.grid(row=0, column=1)
tick()
win.mainloop()
```

效果

![在这里插入图片描述](/static/img/images/02657.png)

PYTHON 获取淘宝服务器时间 显示在tkinter的UI

代码





```
import numpy as np
def normalization(x):
    """"
    归一化到区间{0,1]
    返回副本
    """
    _range = np.max(x) - np.min(x)
    return (x - np.min(x)) / _range
def standardization(x):
    """"
     将输入x 正态标准化  (x - mu) / sigma   ~   N(0,1)
     返回副本
    """
    mu = np.mean(x, axis=0)
    sigma = np.std(x, axis=0)
    return (x - mu) / sigma
YUAN = np.random.randint(3, 70, size=5)
a = normalization(YUAN)
b = standardization(YUAN)
print(YUAN, "normalization:", a)
print(YUAN is a)
print(YUAN, "standardization:", b)
print(YUAN is b)
```

结果

    [33 50 60 12 32] normalization: [0.4375     0.79166667 1.         0.         0.41666667]

    False

    [33 50 60 12 32] standardization: [-0.26647587  0.76308999  1.36871697 -1.53829253 -0.32703857]

    False

**sklearn.preprocessing.scale 能沿某个轴标准化**
```
import numpy as np
from sklearn import  preprocessing
def standardization(x):
    """"
     将输入x 正态标准化  (x - mu) / sigma   ~   N(0,1)
     返回副本
    """
    mu = np.mean(x, axis=0)
    sigma = np.std(x, axis=0)
    return (x - mu) / sigma
YUAN = np.random.randint(3, 70, size=5)
a = standardization(YUAN)
b = preprocessing.scale(YUAN)
print(YUAN, "normalization:", a)
print(YUAN, "preprocessing.scale:", b)
print(a == b)
```

结果

```
[ 8 14 64 51 61] normalization: [-1.32656065 -1.07468204  1.02430632  0.47856935  0.89836702]
[ 8 14 64 51 61] preprocessing.scale: [-1.32656065 -1.07468204  1.02430632  0.47856935  0.89836702]
[ True  True  True  True  True]
```

numpy 归一化 与 标准化

**代码**




```
import numpy as np
def NormMinandMax(npdarr, min=0, max=1):
    """"
    将数据npdarr 归一化到[min,max]区间的方法
    返回 副本
    """
    arr = npdarr.flatten()
    Ymax = np.max(arr)  # 计算最大值
    Ymin = np.min(arr)  # 计算最小值
    k = (max - min) / (Ymax - Ymin)
    last = min + k * (arr - Ymin)
    return last
YUAN = np.random.randint(3, 70, size=5)
print(np.max(YUAN),np.min(YUAN))
print(YUAN, NormMinandMax(YUAN,4,6))
```

结果

    64 5

    [34  7 63 64  5] [4.98305085 4.06779661 5.96610169 6.         4.        ]

numpy 将数据npdarr 归一化到[min,max]区间的方法

numpy教程：





[https://numpy.org/devdocs/user/quickstart.html#array-creation](https://numpy.org/devdocs/user/quickstart.html#array-creation)

https://numpy.org/devdocs/user/index.html



# **1、创建数组**



```python
import numpy as np
a = np.arange(15).reshape(3, 5) #np.arange
a = np.arange( 10, 30, 5 ) 
start:可忽略不写，默认从0开始;起始值
stop:结束值；生成的元素不包括结束值
step:可忽略不写，默认步长为1；步长
dtype:默认为None，设置显示元素的数据类型
a = np.array([2,3,4]) #列表导入
b = np.array([(1.5,2,3), (4,5,6)])  #多维
c = np.array( [ [1,2], [3,4] ], dtype=complex ) #显式给出类型
a =  np.zeros( (3,4) )
a =  np.ones( (2,3,4), dtype=np.int16 ) 
a =  np.empty( (2,3) )
# shape和矩阵a一样的 全0矩阵b
b =  np.zeros_like(a)
# np.linspace函数
a =  np.linspace( 0, 2, 9 )                 # 9 numbers from 0 to 2
>>> u = np.eye(2) # unit 2x2 matrix; "eye" represents "I"
>>> u
array([[ 1.,  0.],
       [ 0.,  1.]])
# 服从“0~1”均匀分布的随机样本值。随机样本取值范围是[0,1)，不包括1
a =  np.random.rand(3,2)
array([[ 0.14022471,  0.96360618],  #random
       [ 0.37601032,  0.25528411],  #random
       [ 0.49313049,  0.94909878]]) #random
# 返回服从正态分布X ~ N(3, 6.25)  来源于 (x-mu)/sigma ~ N(0,1)
# np.random.randn(2, 4)返回标准正态分布
a =  6.25 * np.random.randn(2, 4) + 3
# 返回随机的整数，位于半开区间 [low, high) 
a =   np.random.randint(5, size=(2, 4)) #区间[0, 5) 
a =   np.random.randint(3，5, size=(2, 4)) #区间[3, 5) 
# ranf = random = sample = random_sample 返回在半开区间 [0.0, 1.0)
np.random.random((3, 2))
```



# 2、排列



```python
np.random.shuffle(arr) #洗牌
```



# 3、形状



```python
a.ravel()：# 引用  返回的是视图  (3,)
         # 修改引用 就是修改原数据
a.flatten()：# 深拷贝  返回副本  (3,)
a.squeeze()：# 删除一条维度  (3,)或者(3, 1)
a.reshape((3,4))
```



# 4、堆叠

**np.vstack() #在竖直方向上堆叠**

**np.hstack() #在水平方向上平铺**

```python
>>> a = np.array((1,2,3))
>>> b = np.array((2,3,4))
>>> np.hstack((a,b))
array([1, 2, 3, 2, 3, 4])
>>> a = np.array([[1],[2],[3]])
>>> b = np.array([[2],[3],[4]])
>>> np.hstack((a,b))
array([[1, 2],
       [2, 3],
       [3, 4]])
```





# 4、拼接

**np.concatenate **沿着现有的轴连接一系列数组。

```python
>>> a = np.array([[1, 2], [3, 4]])
>>> b = np.array([[5, 6]])
>>> np.concatenate((a, b), axis=0)
array([[1, 2],
       [3, 4],
       [5, 6]])
>>> np.concatenate((a, b.T), axis=1)
array([[1, 2, 5],
       [3, 4, 6]])
>>> np.concatenate((a, b), axis=None)
array([1, 2, 3, 4, 5, 6])
```



# 5、拆分

**numpy.array_split(ary, indices_or_sections, axis=0) 拆分，不均等就报错****

```python
>>> x = np.arange(8.0)
>>> np.array_split(x, 3)
    [array([ 0.,  1.,  2.]), array([ 3.,  4.,  5.]), array([ 6.,  7.])]
```

**numpy.split(ary, indices_or_sections, axis=0)  拆分， 可接受列表**

```python
>>> x = np.arange(9.0)
>>> np.split(x, 3)
[array([ 0.,  1.,  2.]), array([ 3.,  4.,  5.]), array([ 6.,  7.,  8.])]
>>> x = np.arange(8.0)
>>> np.split(x, [3, 5, 6, 10])
[array([ 0.,  1.,  2.]),
 array([ 3.,  4.]),
 array([ 5.]),
 array([ 6.,  7.]),
 array([], dtype=float64)]
```

# 7、奇淫技巧

7.1 矩阵赋值技巧

代码
```
sequences=[[1,2],[8,2]]
import numpy as np
results = np.zeros((len(sequences), 10))
for i, sequence in enumerate(sequences):
    results[i, sequence] = 1.
    print(i,sequence)
print(results)
```

结果

0 [1, 2]

1 [8, 2]

[[0. 1. 1. 0. 0. 0. 0. 0. 0. 0.]

 [0. 0. 1. 0. 0. 0. 0. 0. 1. 0.]]

 要点

 矩阵results的某一行的某些索引进行赋值。

 results[0,[1,2,5]]=1 表示把第0的第1、2、5处的值换成1