Design a downloading tool

.gitattributes

@@ -0,0 +1,22 @@
+# Auto detect text files and perform LF normalization
+* text=auto
+
+# Custom for Visual Studio
+*.cs     diff=csharp
+*.sln    merge=union
+*.csproj merge=union
+*.vbproj merge=union
+*.fsproj merge=union
+*.dbproj merge=union
+
+# Standard to msysgit
+*.doc	 diff=astextplain
+*.DOC	 diff=astextplain
+*.docx diff=astextplain
+*.DOCX diff=astextplain
+*.dot  diff=astextplain
+*.DOT  diff=astextplain
+*.pdf  diff=astextplain
+*.PDF	 diff=astextplain
+*.rtf	 diff=astextplain
+*.RTF	 diff=astextplain

.gitignore

@@ -0,0 +1,215 @@
+#################
+## Eclipse
+#################
+
+*.pydevproject
+.project
+.metadata
+bin/
+tmp/
+*.tmp
+*.bak
+*.swp
+*~.nib
+local.properties
+.classpath
+.settings/
+.loadpath
+
+# External tool builders
+.externalToolBuilders/
+
+# Locally stored "Eclipse launch configurations"
+*.launch
+
+# CDT-specific
+.cproject
+
+# PDT-specific
+.buildpath
+
+
+#################
+## Visual Studio
+#################
+
+## Ignore Visual Studio temporary files, build results, and
+## files generated by popular Visual Studio add-ons.
+
+# User-specific files
+*.suo
+*.user
+*.sln.docstates
+
+# Build results
+
+[Dd]ebug/
+[Rr]elease/
+x64/
+build/
+[Bb]in/
+[Oo]bj/
+
+# MSTest test Results
+[Tt]est[Rr]esult*/
+[Bb]uild[Ll]og.*
+
+*_i.c
+*_p.c
+*.ilk
+*.meta
+*.obj
+*.pch
+*.pdb
+*.pgc
+*.pgd
+*.rsp
+*.sbr
+*.tlb
+*.tli
+*.tlh
+*.tmp
+*.tmp_proj
+*.log
+*.vspscc
+*.vssscc
+.builds
+*.pidb
+*.log
+*.scc
+
+# Visual C++ cache files
+ipch/
+*.aps
+*.ncb
+*.opensdf
+*.sdf
+*.cachefile
+
+# Visual Studio profiler
+*.psess
+*.vsp
+*.vspx
+
+# Guidance Automation Toolkit
+*.gpState
+
+# ReSharper is a .NET coding add-in
+_ReSharper*/
+*.[Rr]e[Ss]harper
+
+# TeamCity is a build add-in
+_TeamCity*
+
+# DotCover is a Code Coverage Tool
+*.dotCover
+
+# NCrunch
+*.ncrunch*
+.*crunch*.local.xml
+
+# Installshield output folder
+[Ee]xpress/
+
+# DocProject is a documentation generator add-in
+DocProject/buildhelp/
+DocProject/Help/*.HxT
+DocProject/Help/*.HxC
+DocProject/Help/*.hhc
+DocProject/Help/*.hhk
+DocProject/Help/*.hhp
+DocProject/Help/Html2
+DocProject/Help/html
+
+# Click-Once directory
+publish/
+
+# Publish Web Output
+*.Publish.xml
+*.pubxml
+
+# NuGet Packages Directory
+## TODO: If you have NuGet Package Restore enabled, uncomment the next line
+#packages/
+
+# Windows Azure Build Output
+csx
+*.build.csdef
+
+# Windows Store app package directory
+AppPackages/
+
+# Others
+sql/
+*.Cache
+ClientBin/
+[Ss]tyle[Cc]op.*
+~$*
+*~
+*.dbmdl
+*.[Pp]ublish.xml
+*.pfx
+*.publishsettings
+
+# RIA/Silverlight projects
+Generated_Code/
+
+# Backup & report files from converting an old project file to a newer
+# Visual Studio version. Backup files are not needed, because we have git ;-)
+_UpgradeReport_Files/
+Backup*/
+UpgradeLog*.XML
+UpgradeLog*.htm
+
+# SQL Server files
+App_Data/*.mdf
+App_Data/*.ldf
+
+#############
+## Windows detritus
+#############
+
+# Windows image file caches
+Thumbs.db
+ehthumbs.db
+
+# Folder config file
+Desktop.ini
+
+# Recycle Bin used on file shares
+$RECYCLE.BIN/
+
+# Mac crap
+.DS_Store
+
+
+#############
+## Python
+#############
+
+*.py[co]
+
+# Packages
+*.egg
+*.egg-info
+dist/
+build/
+eggs/
+parts/
+var/
+sdist/
+develop-eggs/
+.installed.cfg
+
+# Installer logs
+pip-log.txt
+
+# Unit test / coverage reports
+.coverage
+.tox
+
+#Translations
+*.mo
+
+#Mr Developer
+.mr.developer.cfg

ImageDownload.py

@@ -0,0 +1,52 @@
+# -*- coding: utf-8 -*-
+
+import os
+import sys
+import re
+import urllib
+
+url_addr = sys.argv[1]
+save_path = sys.argv[2]
+# url_addr = r"http://www.douban.com/"
+# save_path = r"C:\Users\naril\Desktop\new"
+html = urllib.urlopen(url_addr).read()
+
+
+class Get_Picture(object):
+    def __init__(self, html_content):
+        self.html_content = html_content
+
+    def get_image_list(self):
+        """Get all the image url from the website url,
+        and return a list to save it."""
+        image_list = []
+        # print self.html_content
+        pattern = r'<img.*?src="(.*\..{3})"/?>?'  # match the image with re
+        match_result = re.findall(pattern, self.html_content)
+        # print match_result
+        for i in match_result:
+            # url = url_addr + i  # ganerate the absolute address of picture
+            image_list.append(i)
+        # print image_list
+        self.image_list = image_list
+        return self.image_list
+
+    def downloader(self):
+        """Download all the images into some dir"""
+        for each_url in self.image_list:
+            filename = each_url.split("/")[-1]
+            savedfile = os.path.join(save_path, filename)
+            try:
+                urllib.urlretrieve(each_url, savedfile)
+            except:
+                pass
+        print "Downloading completed!"
+
+
+def run():
+    a = Get_Picture(html)
+    a.get_image_list()
+    a.downloader()
+
+if __name__ == '__main__':
+    run()

README.md

@@ -0,0 +1,11 @@
+Designed by Ran.
+
+Description：
+Download all the pictures of some website.
+1. And keep their names on the website.
+2. Then print their size.
+3. Download all the images and save them to one directory
+
+Usage：
+Run this program in cmd or linux bash:
+   "python ImageDownloader.py <url_address> <Directory>"