Python Get site pictures

# ZHOUXIANGLH 2013.05.03 python3.3import urllib.requestfrom html.parser import htmlparserimport reimport osimport Shutilimport Timeurl = "http://www.douban.com/" FilePath = "D:\\temp" # read ALSO htmlurlcontent = Urllib.request.urlopen (URL); data = str (Urlcontent.read ()) # Initialization file directory if Os.path.isdir (filePath): # os.removedirs (FilePath) shutil.rmtree (FilePath) Elif Os.path.isfile (FilePath): Os.remove (FilePath) os.makedirs (filePath) # Generate a unique file name Intflag = 0def gettimestr (): Global Intflag Intflag = intflag + 1 return time.strftime ("%h%m%s") + str (intflag) # parse html# htmlparser mode parsing, here htmlparser similar to pumping            Like Class Myhtmlparser (Htmlparser): Def handle_starttag (self, Tag, attrs): ' Get img tag ' if tag = = ' img ': For IMAGEURL in attrs: ' Get src attribute ' if imageurl[0] = = ' src ': imageur L = imageurl[1] ImageUrl = Re.sub ("[\\\\ ']", "", imageUrl) Iamgeurlarr = Imageurl.sp Lit ("/") Imgfilepath = Iamgeurlarr[len (Iamgeurlarr)-1] try:imgdata = Urllib.request.urlopen (ima                        Geurl). Read () Imgfilepath = FilePath + os.sep + Imgfilepath + gettimestr () + ". jpg" ImageFile = open (Imgfilepath, "WB") Imagefile.write (Imgdata) Imagefi                        Le.close () print ("Download file", IMAGEURL, "Success, save path:" + Imgfilepath) except: Print ("Download file", ImageUrl, "error:") parser = Myhtmlparser () # parse Htmlparser.feed (data) print ("Get Picture Operation complete")

