{python·图片下载}

 用python写了一个下载topit.me整个专辑中的图片

import re
import os 
from urllib import request
import threading
from time import sleep,ctime
from html import parser
import getpass
import time
__author__ = 'Dino'
class album:
    albumid=""
    def __init__(self,albumid):
        self.albumid=albumid
    #下载
    def downloadAlbum(self):
        self.WebUrl="http://topit.me/album/%s"%self.albumid
        rootUrl="http://topit.me"
        pageRoot="/album/%s?p="%self.albumid
        
        pparser=parserPages(self.albumid)
        lparser = parserLinks(self.albumid)
        iparser=parserImageUrl()
        t=tools(self.albumid)
        
        web = request.urlopen( self.WebUrl )
        for context in web.readlines():
            _str="%s"%context
            try:
                pparser.feed(_str)
            except parser.HTMLParseError:
                print("parser error")
                pass
        
        pages=pparser.getpagelist()
        print("分页总数：",pages)
        for page in range(1,pages+1):
            lparser.filelist=[]
            print("访问分页：","%s%s%s"%(rootUrl,pageRoot,page))
            web = request.urlopen("%s%s%s"%(rootUrl,pageRoot,page))
            
            for context in web.readlines():
                _str="%s"%context
                try:
                    lparser.feed( _str)
                except parser.HTMLParseError:
                    print( "parser error")
                    pass
                web.close()
                imageurllist= lparser.getfileurllist()
                imageurllist=list(set(imageurllist))#去重
                print(imageurllist)
                for url in imageurllist:
                    ihtmlurl=request.urlopen("http://topit.me%s"%url)
                    print("http://topit.me%s"%url)
                    for imagecontext in ihtmlurl.readlines():
                        _str="%s"%imagecontext
                        try:
                            iparser.feed( _str)
                        except parser.HTMLParseError:
                            print( "parser error")
                            pass
        imagelist=iparser.getfilelist()
        print(imagelist)
        t.downjpgmutithread(imagelist)

class tools:
    def __init__(self,albumid):
        self.albumname=albumid

    def downjpg(self, fileurl,filepath,FileName ="default.jpg" ):
        try:
            web = request.urlopen( fileurl)
            print("访问网络文件"+fileurl+"\n")
            jpg = web.read()

            print("保存文件"+filepath+FileName+"\n")
            try:
                File = open( filepath+FileName,"wb" )
                File.write( jpg)
                File.close()
                return
            except IOError:
                print("error\n")
                return
        except Exception:
            print("error\n")
            return

    def downjpgmutithread(self, filepathlist ):
        uname=getpass.getuser()#获取用户名
        DstDir="C:\\Users\\%s\\Pictures\\topit_me\\"%uname
        tempdir="%s%s\\"%(DstDir,time.strftime("%Y%m%d%H%M%S",time.localtime(time.time())))
        os.mkdir(tempdir)
        print("共有%d个文件需要下载"%len(filepathlist))
        for file in filepathlist:
            print( file )
        print("开始多线程下载")
        task_threads=[] #存储线程
        count=1
        for file in filepathlist:
            t= threading.Thread( target=self.downjpg,args=(file,tempdir,"%d.jpg"%count) )
            count=count+1
            task_threads.append(t)
        for task in task_threads:
            task.start()
        for task in task_threads:
            task.join() #等待所有线程结束
        print("线程结束")

class parserLinks( parser.HTMLParser):
    filelist=[]
    
    def __init__(self,albumid):
        parser.HTMLParser.__init__(self)
        self.albumid=albumid
        self.p=re.compile('/album/%s/item/*'%self.albumid)
        
    def handle_starttag(self,tag,attrs):
        if tag == 'a':
            for name,value in attrs:
                if name == 'href':
                    if self.p.match(value):
                        self.filelist.append(value)

    def getfileurllist(self):
        return self.filelist


class parserPages(parser.HTMLParser):
    pagelist=[]
    def __init__(self,albumid):
        parser.HTMLParser.__init__(self)
        print('/album/%s[?]p=[0-9]+'%albumid)
        self.page=re.compile('/album/%s[?]p=(?P<page>[0-9]+)'%albumid)
        
    def handle_starttag(self,tag,attrs):
        if tag == 'a':
            for name,value in attrs:
                if name == 'href':
                    m=self.page.match(value)
                    if m:
                        self.pagelist.append(int(m.group("page")))
                            
    def getpagelist(self):
        return max(set(self.pagelist))
        
class parserImageUrl(parser.HTMLParser):
    filelist=[]
    def handle_starttag(self,tag,attrs):
        if tag=="img":
            if [x[0] for x in attrs  ].count('class')>0:
                for name,value in attrs:
                    if name=="class":
                        if value!="img":
                            break
                    if name=="src":
                        self.filelist.append(value)
    def getfilelist(self):
        return self.filelist

topit_me=album("296107")
topit_me.downloadAlbum()