Merge pull request Show-Me-the-Code#48 from JiYouMCC/master

Add 0013

Author: horx

JiYouMCC/0013/0013.md

@@ -0,0 +1,9 @@
+# 第 0013 题： 用 Python 写一个爬图片的程序，爬 [这个链接里](http://tieba.baidu.com/p/2166231880)的日本妹子图片 :-) #
+
+----
+
+其实我是我为了爬我自己一个[老博客](http://ycool.com/post/ae3u4zu)上面的图片才做这题的。。
+
+我很懒惰没用啥爬虫架构请无视..
+
+百度贴吧上面格式绝对没有我老博客上那么老实，就将就下吧

JiYouMCC/0013/0013.py

@@ -0,0 +1,49 @@
+import urllib2
+import re
+import os
+import uuid
+
+
+def get_images(html_url='http://ycool.com/post/ae3u4zu',
+               folder_name='jiyou_blog_PingLiangRoad',
+               extensions=['gif', 'jpg', 'png']):
+    request_html = urllib2.Request(html_url)
+    try:
+        response = urllib2.urlopen(request_html)
+        html = response.read()
+        r1 = r'<img.+src=\".+?\"'
+        r2 = r'<img.+src=\"(.+?)\"'
+        results = []
+        imgs = []
+        p = re.compile(r1)
+        for m in p.finditer(html):
+            results.append(m.group())
+        for result in results:
+            compile_result = re.compile(r2)
+            imgs.append(compile_result.sub(r'\1', result))
+        if not os.path.exists(folder_name):
+            os.makedirs(folder_name)
+        for img in imgs:
+            filename = str(uuid.uuid1())
+            ex = ''
+            for extension in extensions:
+                if '.%s' % extension in img:
+                    ex = '.%s' % extension
+            if ex is '':
+                continue
+            filename += ex
+            file_request = urllib2.Request(img)
+            try:
+                file_response = urllib2.urlopen(file_request)
+                output = open(os.path.join(folder_name, filename), 'w+')
+                output.write(file_response.read())
+                print 'Image save at %s' % output.name
+                output.close()
+            except Exception, ex:
+                print ex
+    except Exception, e:
+        print e
+
+get_images()
+# japanese girls
+get_images(html_url='http://tieba.baidu.com/p/2166231880', folder_name='jp')