the third commitment

roberttkay · Jun 6, 2015 · e9e9c04 · e9e9c04
1 parent f5b887e
commit e9e9c04
Show file tree

Hide file tree

Showing 8 changed files with 128 additions and 0 deletions.
diff --git a/Silocean/0000/icon.jpg b/Silocean/0000/icon.jpg
diff --git a/Silocean/0000/result.jpg b/Silocean/0000/result.jpg
diff --git a/Silocean/0007/Test.py b/Silocean/0007/Test.py
@@ -0,0 +1,39 @@
+__author__ = 'Tracy'
+
+import os, io, re
+
+commentLines = 0
+whiteLines = 0
+comment = False
+
+path = 'F:\AllKindsOfWorkplace\PyCharmWorkplace\PythonLearning'
+
+count = 0
+def tree(path):
+    filelist = os.listdir(path)
+    for file in filelist:
+        if os.path.isdir(os.path.join(path, file)):
+            tree(os.path.join(path, file))
+        else:
+            filename = os.path.basename(os.path.join(path, file))
+            if filename.endswith(".py"):
+                # print(filename)
+                file = io.open(os.path.join(path, file))
+                parse(file)
+                file.close()
+
+def parse(file):
+    global commentLines
+    global whiteLines
+    global comment
+    for line in file.readlines():
+        # line = line.strip("\n")
+        if line.startswith("#"):
+            commentLines += 1
+        elif re.match("^[\\s&&[^\\n]]*$", line):
+            whiteLines += 1
+
+tree(path)
+
+print(commentLines)
+print(whiteLines)
diff --git a/Silocean/0008/Test.html b/Silocean/0008/Test.html
@@ -0,0 +1,17 @@
+
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+<html xmlns="http://www.w3.org/1999/xhtml">
+<head>
+<title>This is the Title</title>
+
+</head>
+<body>
+<div id="container">
+
+<div id="nav">
+
+<div style="display:none">
+<script type="text/javascript" src="http://tajs.qq.com/stats?sId=9394293" charset="UTF-8"></script>
+</div>
+</body>
+</html>
diff --git a/Silocean/0008/Test.py b/Silocean/0008/Test.py
@@ -0,0 +1,11 @@
+
+# -*- coding=utf-8 -*-
+
+from bs4 import BeautifulSoup
+import io
+file = io.open('Test.html', 'r')
+soup = BeautifulSoup(file)
+print(soup.getText().strip("\n"))
+
+
+file.close()
diff --git a/Silocean/0009/Test.html b/Silocean/0009/Test.html
@@ -0,0 +1,19 @@
+<!DOCTYPE html>
+<html>
+<head lang="en">
+    <meta charset="UTF-8">
+    <title></title>
+</head>
+<body>
+<link rel="stylesheet" href="http://tb1.bdstatic.com/??/tb/_/thread_recommend_50cc234.css,/tb/_/grade_e31ce1c.css,/tb/_/interest_smiley_90ea01d.css,/tb/_/aside_float_bar_b8d73a2.css" />
+<p class="title"><b>The Dormouse's story</b></p>
+
+<p class="story">Once upon a time there were three little sisters; and their names were
+<a href="http://example.com/elsie" class="sister" id="link1">Elsie</a>
+<a href="http://example.com/lacie" class="sister" id="link2">Lacie</a>
+<a href="http://example.com/tillie" class="sister" id="link3">Tillie</a>
+and they lived at the bottom of a well.</p>
+<img pic_type="0" class="BDE_Image" src="http://imgsrc.baidu.com/forum/w%3D580/sign=527796ed1f178a82ce3c7fa8c603737f/d3af6ccb0a46f21f6e583272f7246b600c33ae0c.jpg" bdwater="shanshanyoumei,1280,860" width="560" height="376" changedsize="true">
+<p class="story">...</p>
+</body>
+</html>
diff --git a/Silocean/0009/Test.py b/Silocean/0009/Test.py
@@ -0,0 +1,21 @@
+__author__ = 'Tracy'
+
+from bs4 import BeautifulSoup
+import io
+
+with io.open('Test.html') as file:
+    html = file.read()
+    soup = BeautifulSoup(html)
+    listA = soup.find_all('a')
+    listL = soup.find_all('link')
+    listI = soup.find_all('img')
+    # print(listA)
+    # print(listL)
+    # print(listI)
+
+for x in listA:
+    print(x['href'])
+for x in listL:
+    print(x['href'])
+for x in listI:
+    print(x['src'])
diff --git a/Silocean/0013/Test.py b/Silocean/0013/Test.py
@@ -0,0 +1,21 @@
+__author__ = 'Tracy'
+from urllib import urlopen
+from bs4 import BeautifulSoup
+
+f = urlopen('http://tieba.baidu.com/p/2166231880').read()
+
+s = BeautifulSoup(f)
+
+images = s.find_all('img', pic_type='0')
+count = 1
+def download(src):
+    global count
+    file_name = str(count) + '.jpg'
+    content = urlopen(src).read()
+    with open(file_name, 'wb') as f:
+        f.write(content)
+    count += 1
+
+for image in images:
+    download(image['src'])
+