Merge pull request Show-Me-the-Code#148 from Jaccorot/master

add 004-009

Author: horx

Jaccorot/0004/0004.py

@@ -0,0 +1,18 @@
+#!/usr/local/bin/python
+#coding=utf-8
+
+"""
+第 0004 题：任一个英文的纯文本文件，统计其中的单词出现的个数。
+"""
+import re
+
+def count_the_words(path):
+    with open(path) as f:
+        text = f.read()
+        words_list = re.findall(r'[a-zA-Z0-9]+', text)
+        count = len(words_list)
+    return count
+
+if __name__ == '__main__':
+    nums = count_the_words('file.txt')
+    print nums

Jaccorot/0004/file.txt

@@ -0,0 +1,3 @@
+cocococo  asdf asdf asdf sdf  
+sdf
+sdf

Jaccorot/0005/0.jpg

@@ -0,0 +1,37 @@
+#!/usr/local/bin/python
+#coding=utf-8
+
+"""
+第 0005 题：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。
+"""
+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):
+        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('./')

Jaccorot/0005/0005.py

@@ -0,0 +1,37 @@
+#!usr/bin/python
+#coding=utf-8
+
+"""
+第 0006 题：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。
+"""
+
+import os
+import re
+
+def walk_dir(path):
+    file_path = []
+    for root, dirs, files in os.walk(path):
+        for f in files:
+            if f.lower().endswith('txt'):
+                file_path.append(os.path.join(root, f))
+    return file_path
+
+def find_key_word(filepath):
+    word_dic = {}
+    filename = os.path.basename(filepath)
+    with open(filepath) as f:
+        text = f.read()
+        words_list = re.findall(r'[A-Za-z]+', text.lower())
+        for w in words_list:
+            if w in word_dic:
+                word_dic[w] += 1
+            else:
+                word_dic[w] = 1
+        sorted_word_list = sorted(word_dic.items(), key=lambda d: d[1])
+        print u"在%s文件中，%s为关键词，共出现了%s次" %(filename, sorted_word_list[-1][0], sorted_word_list[-1][1])
+
+if __name__ == "__main__":
+    for file_path in walk_dir(os.getcwd()):
+        find_key_word(file_path)
+

Jaccorot/0006/0006.py

@@ -0,0 +1 @@
+a b c d a  a d

Jaccorot/0006/1.txt

@@ -0,0 +1 @@
+a b c d a  a d d b d d x zx fd fd fd fd fd fd fd fd fd  FD FD FD FD D FD FD FD FD fD FD FD FD

Jaccorot/0006/2.txt

@@ -0,0 +1,48 @@
+#!/usr/bin/python
+#coding:utf-8
+
+"""
+第 0007 题：有个目录，里面是你自己写过的程序，统计一下你写过多少行代码。包括空行和注释，但是要分别列出来。
+"""
+
+import os
+
+def walk_dir(path):
+    file_path = []
+    for root, dirs, files in os.walk(path):
+        for f in files:
+            if f.lower().endswith('py'):
+                file_path.append(os.path.join(root, f))
+    return file_path
+
+
+def count_the_code(path):
+    file_name = os.path.basename(path)
+    note_flag = False
+    line_num = 0
+    empty_line_num = 0
+    note_num = 0
+    with open(path) as f:
+        for line in f.read().split('\n'):
+            line_num += 1
+            if line.strip().startswith('\"\"\"') and not note_flag:
+                note_flag =True
+                note_num += 1
+                continue
+
+            if line.strip().startswith('\"\"\"'):
+                note_flag = False
+                note_num += 1
+
+            if line.strip().startswith('#') or note_flag:
+                note_num += 1
+
+            if len(line) == 0:
+                empty_line_num += 1
+
+    print u"在%s中，共有%s行代码，其中有%s空行，有%s注释"% (file_name, line_num, empty_line_num, note_num)
+
+
+if __name__ == '__main__':
+    for f in walk_dir('.'):
+        count_the_code(f)

Jaccorot/0007/0007.py

@@ -0,0 +1,19 @@
+#!/usr/bin/python
+#coding=utf-8
+
+"""
+第 0008 题：一个HTML文件，找出里面的正文。
+"""
+
+from bs4 import BeautifulSoup
+
+def find_the_content(path):
+    with open(path) as f:
+        text = BeautifulSoup(f, 'lxml')
+        content = text.get_text().strip('\n')
+
+        return content.encode('gbk','ignore')
+
+
+if __name__ == '__main__':
+    print find_the_content('Show-Me-the-Code_show-me-the-code_1.html')