Python 练习册

01：将你的 QQ 头像（或者微博头像）右上角加上红色的数字，类似于微信未读信息数量那种提示效果

【图像处理】

类似于图中效果：

py 2.7代码：

from PIL import Image, ImageDraw, ImageFont
def add_word(img):
    char_size = 30
    fillcolor = "#ff0000"
    draw = ImageDraw.Draw(img)
    my_font = ImageFont.truetype(r'C:\Windows\Fonts\SIMYOU.TTF', char_size)#从本地载入字体文件
    width, height = img.size
    draw.text((width - char_size,char_size-20), '', font=my_font, fill=fillcolor)
    img.save('result.jpg','JPEG')
    del draw

if __name__ == "__main__":
    img = Image.open('test.jpg')
    add_word(img)

更多：

draw.line((0, 0) + im.size, fill=128)  #画一道线

参考文档：

pillow 函数接口查询 官方文档

---

02：任一个英文的纯文本文件，统计其中的单词出现的个数【文本处理】

import re

def statis_words(article):
        re_pat = re.compile("\W",re.S)
        pre_article = re.sub(re_pat," ",article)
        re_pat2 = re.compile(" *",re.S)
        list_words = re_pat2.split(pre_article)
        dict_re = dict.fromkeys(list_words)
        for i in list_words:
            if not dict_re[i]:
                dict_re[i] = 0
            if i in list_words:
                dict_re[i]+=1
        for i in dict_re.iteritems():#打印
            print i

if __name__ == "__main__":
    file_path = "words.txt"
    article = ""
    with open(file_path) as f:
        for i in f.readlines():
            article += i
    statis_words(article.replace("\n",' '))
    

---

03：你有一个目录，装了很多照片，把它们的尺寸变成都不大于 iPhone5 分辨率的大小【图像处理】

import os
from PIL import Image

iPhone5_WIDTH = 1136
iPhone5_HEIGHT = 640

def resize_iPhone5_pic(path, new_path, width=iPhone5_WIDTH, height=iPhone5_HEIGHT):
    im = Image.open(path)
    w,h = im.size

    if w > width:
        h = width * h // w
        w = width
    if h > height:
        w = height * w // h
        h = height

    im_resized = im.resize((w,h), Image.ANTIALIAS)
    im_resized.save(new_path)

def walk_dir_and_resize(path):
    for root, dirs, files in os.walk(path):#递归path下所有目录
        for f_name in files:
            if f_name.lower().endswith('jpg'):
                path_dst = os.path.join(root,f_name)
                f_new_name = 'iPhone5_' + f_name
                resize_iPhone5_pic(path=path_dst, new_path=f_new_name)

if __name__ == '__main__':
    walk_dir_and_resize('./')#当前目录

核心函数  image.resize()

Image.resize(size, resample=0)

Returns a resized copy of this image.

Parameters:	size – The requested size in pixels, as a 2-tuple: (width, height). resample – An optional resampling filter. This can be one of PIL.Image.NEAREST (use nearest neighbour), PIL.Image.BILINEAR (linear interpolation), PIL.Image.BICUBIC(cubic spline interpolation), or PIL.Image.LANCZOS (a high-quality downsampling filter). If omitted, or if the image has mode “1” or “P”, it is set PIL.Image.NEAREST.
Returns:	An Image object.

size: 图像宽度，长度

resample:

PIL.Image.NEAREST (use nearest neighbour)   最近邻插值法

PIL.Image.BILINEAR (linear interpolation),   双线性插值法

PIL.Image.BICUBIC(cubic spline interpolation), 双三次插值

or PIL.Image.LANCZOS (a high-quality downsampling filter)   Lanczos算法  采样放缩算法

缩小时 ANTIALIAS

更多图像处理请参考 opencv

reference：Image Module

---

04：你有一个目录，放了你一个月的日记，都是 txt，为了避免分词的问题，假设内容都是英文，请统计出你认为每篇日记最重要的词【字符串处理】【文件管理】

注：暂认为出现频率最多的为最重要的

#文件管理
#coding:utf-8
import os
import re

def analyse_article(article):
        re_pat = re.compile("(?=[\n\x21-\x7e]+)[^A-Za-z0-9]")#+|[{}【】。,;“‘”?]")#("^([\u4e00-\u9fa5]+|[a-zA-Z0-9]+)$")#("(?=[\x21-\x7e]+)[^A-Za-z0-9]+|["{}【】。,;’“‘”?"]")#("[\W\u4e00-\u9fa5] ",re.S)  \s  空格符
        pre_article = re.sub(re_pat," ",article)
        chinese_symbol = ["\xa1\xa3","\xa1\xb0","\xa1\xb1","\xa3\xac","\xa1\xbe","\xa1\xbf","\xa1\xb6","\xa1\xb7","\xa3\xba","\xa3\xbb"]#中文标点
        for i in chinese_symbol:
            pre_article = pre_article.replace(i," ")
        re_pat2 = re.compile(" *",re.S)
        list_words = re_pat2.split(pre_article)
        dict_re = dict.fromkeys(list_words)
        #print pre_article
        for i in list_words:
            if not dict_re[i]:
                dict_re[i] = 0
            if i in list_words:
                dict_re[i]+=1
        if dict_re.get(""):
            del dict_re[""]
        key_words = sorted(dict_re.items(),key = lambda e:e[1])[-1]
        return (key_words[0], key_words[1])

def walk_dir_and_analyse(path):
    text = ""
    key_words_list = []
    for root, dirs, files in os.walk(path):#递归path下所有目录
        for f_name in files:
            if f_name.lower().endswith('txt'):
                with open(os.path.join(root,f_name)) as f:
                    for i in f.readlines():
                        text += i
                    key_words_list.append(analyse_article(text))

    for i in key_words_list:
        print "\""+ i[0] + "\" for "+ str(i[1]) +" times"

if __name__ == "__main__":
    walk_dir_and_analyse("./")

输出

>python 4.py
"春眠不觉晓" for 2 times

---

05:敏感词文本文件 filtered_words.txt，当用户输入敏感词语，则用星号 * 替换，例如当用户输入「北京是个好城市」，则变成「**是个好城市」。

#[字符串处理]
#敏感词文本文件 filtered_words.txt，
#里面的内容为以下内容，当用户输入敏感词语时，
#python ' '中将自动加入结尾符号，要注意字串实际长度，包括读入txt文件时的字符串长度
#coding:utf-8

def words_filter(path,words_list):
    content = ""
    with open(path) as f:
        for i in f.readlines():
            for j in words_list:
                if j in i:
                    i = i.replace(j,"*"*(len(j)/(len('单')-1)))  #一个中文两个字节长度
            content += i
        return content

if __name__ == "__main__":
    word_path = "filtered_words.txt"
    path = "words.txt"

    words_list = []
    with open(word_path) as f:
        for i in f.readlines():
            words_list.append(i.replace("\n",""))
    print words_filter(path,words_list)