Python實現多線程抓取妹子圖

心血來潮寫了個多線程抓妹子圖，雖然代碼還是有一些瑕疵，但是還是記錄下來，分享給大家。

Pic_downloader.py

# -*- coding: utf-8 -*-"""Created on Fri Aug 07 17:30:58 2015 @author: Dreace"""import urllib2import sysimport timeimport osimport randomfrom multiprocessing.dummy import Pool as ThreadPool type_ = sys.getfilesystemencoding()def rename():  return time.strftime("%Y%m%d%H%M%S")def rename_2(name):   if len(name) == 2:     name = '0' + name + '.jpg'   elif len(name) == 1:     name = '00' + name + '.jpg'   else:     name = name + '.jpg'   return namedef download_pic(i):  global count  global time_out  if Filter(i):    try:       content = urllib2.urlopen(i,timeout = time_out)      url_content = content.read()      f = open(repr(random.randint(10000,999999999)) + "_" + rename_2(repr(count)),"wb")      f.write(url_content)      f.close()      count += 1    except Exception, e:      print i + "下載逾時，跳過！".decode("utf-8").encode(type_)def Filter(content):  for line in Filter_list:    line=line.strip('\n')    if content.find(line) == -1:      return Truedef get_pic(url_address):  global pic_list  try:    str_ = urllib2.urlopen(url_address, timeout = time_out).read()    url_content = str_.split("\"")    for i in url_content:      if i.find(".jpg") != -1:        pic_list.append(i)    except Exception, e:    print "擷取圖片逾時，跳過！".decode("utf-8").encode(type_)MAX = 2count = 0time_out = 60thread_num = 30pic_list = []page_list = []Filter_list = ["imgsize.ph.126.net","img.ph.126.net","img2.ph.126.net"]dir_name = "C:\Photos\\"+rename()os.makedirs(dir_name)os.chdir(dir_name)start_time = time.time()url_address = "http://sexy.faceks.com/?page="for i in range(1,MAX + 1):   page_list.append(url_address + repr(i))page_pool = ThreadPool(thread_num)page_pool.map(get_pic,page_list)print "擷取到".decode("utf-8").encode(type_),len(pic_list),"張圖片，開始下載！".decode("utf-8").encode(type_)pool = ThreadPool(thread_num) pool.map(download_pic,pic_list)pool.close() pool.join()print count,"張圖片儲存在".decode("utf-8").encode(type_) + dir_nameprint "共耗時".decode("utf-8").encode(type_),time.time() - start_time,"s"

我們來看下一個網友的作品

#coding: utf-8 ############################################################## File Name: main.py# Author: mylonly# mail: mylonly@gmail.com# Created Time: Wed 11 Jun 2014 08:22:12 PM CST##########################################################################!/usr/bin/pythonimport re,urllib2,HTMLParser,threading,Queue,time#各圖集入口連結htmlDoorList = []#包含圖片的Hmtl連結htmlUrlList = []#圖片Url連結QueueimageUrlList = Queue.Queue(0)#捕獲圖片數量imageGetCount = 0#已下載圖片數量imageDownloadCount = 0#每個圖集的起始地址，用於判斷終止nextHtmlUrl = ''#本地儲存路徑localSavePath = '/data/1920x1080/'#如果你想下你需要的解析度的，請修改replace_str,有如下解析度可供選擇1920x1200，1980x1920,1680x1050,1600x900,1440x900,1366x768,1280x1024,1024x768,1280x800replace_str = '1920x1080'replaced_str = '960x600'#內頁分析處理類class ImageHtmlParser(HTMLParser.HTMLParser):def __init__(self):self.nextUrl = ''HTMLParser.HTMLParser.__init__(self)def handle_starttag(self,tag,attrs):global imageUrlListif(tag == 'img' and len(attrs) > 2 ):if(attrs[0] == ('id','bigImg')):url = attrs[1][1]url = url.replace(replaced_str,replace_str)imageUrlList.put(url)global imageGetCountimageGetCount = imageGetCount + 1print urlelif(tag == 'a' and len(attrs) == 4):if(attrs[0] == ('id','pageNext') and attrs[1] == ('class','next')):global nextHtmlUrlnextHtmlUrl = attrs[2][1];#首頁分析類class IndexHtmlParser(HTMLParser.HTMLParser):def __init__(self):self.urlList = []self.index = 0self.nextUrl = ''self.tagList = ['li','a']self.classList = ['photo-list-padding','pic']HTMLParser.HTMLParser.__init__(self)def handle_starttag(self,tag,attrs):if(tag == self.tagList[self.index]):for attr in attrs:if (attr[1] == self.classList[self.index]):if(self.index == 0):#第一層找到了self.index = 1else:#第二層找到了self.index = 0print attrs[1][1]self.urlList.append(attrs[1][1])breakelif(tag == 'a'):for attr in attrs:if (attr[0] == 'id' and attr[1] == 'pageNext'):self.nextUrl = attrs[1][1]print 'nextUrl:',self.nextUrlbreak#首頁Hmtl解析器indexParser = IndexHtmlParser()#內頁Html解析器imageParser = ImageHtmlParser()#根據首頁得到所有入口連結print '開始掃描首頁...'host = 'http://desk.zol.com.cn'indexUrl = '/meinv/'while (indexUrl != ''):print '正在抓取網頁:',host+indexUrlrequest = urllib2.Request(host+indexUrl)try:m = urllib2.urlopen(request)con = m.read()indexParser.feed(con)if (indexUrl == indexParser.nextUrl):breakelse:indexUrl = indexParser.nextUrlexcept urllib2.URLError,e:print e.reasonprint '首頁掃描完成，所有圖集連結已獲得：'htmlDoorList = indexParser.urlList#根據入口連結得到所有圖片的urlclass getImageUrl(threading.Thread):def __init__(self):threading.Thread.__init__(self)def run(self):for door in htmlDoorList:print '開始擷取圖片地址,入口地址為:',doorglobal nextHtmlUrlnextHtmlUrl = ''while(door != ''):print '開始從網頁%s擷取圖片...'% (host+door)if(nextHtmlUrl != ''):request = urllib2.Request(host+nextHtmlUrl)else:request = urllib2.Request(host+door)try:m = urllib2.urlopen(request)con = m.read()imageParser.feed(con)print '下一個頁面地址為:',nextHtmlUrlif(door == nextHtmlUrl):breakexcept urllib2.URLError,e:print e.reasonprint '所有圖片地址均已獲得:',imageUrlListclass getImage(threading.Thread):def __init__(self):threading.Thread.__init__(self)def run(self):global imageUrlListprint '開始下載圖片...'while(True):print '目前捕獲圖片數量:',imageGetCountprint '已下載圖片數量:',imageDownloadCountimage = imageUrlList.get()print '下載檔案路徑:',imagetry:cont = urllib2.urlopen(image).read()patter = '[0-9]*\.jpg';match = re.search(patter,image);if match:print '正在下載檔案：',match.group()filename = localSavePath+match.group()f = open(filename,'wb')f.write(cont)f.close()global imageDownloadCountimageDownloadCount = imageDownloadCount + 1else:print 'no match'if(imageUrlList.empty()):breakexcept urllib2.URLError,e:print e.reasonprint '檔案全部下載完成...'get = getImageUrl()get.start()print '擷取圖片連結線程啟動:'time.sleep(2)download = getImage()download.start()print '下載圖片連結線程啟動:'

批量抓取指定網頁上的所有圖片

# -*- coding:utf-8 -*-# coding=UTF-8 import os,urllib,urllib2,re url = u"http://image.baidu.com/search/index?tn=baiduimage&ipn=r&ct=201326592&cl=2&lm=-1&st=-1&fm=index&fr=&sf=1&fmq=&pv=&ic=0&nc=1&z=&se=1&showtab=0&fb=0&width=&height=&face=0&istype=2&ie=utf-8&word=python&oq=python&rsp=-1"outpath = "t:\\" def getHtml(url):  webfile = urllib.urlopen(url)  outhtml = webfile.read()  print outhtml  return outhtml def getImageList(html):  restr=ur'('  restr+=ur'http:\/\/[^\s,"]*\.jpg'  restr+=ur'|http:\/\/[^\s,"]*\.jpeg'  restr+=ur'|http:\/\/[^\s,"]*\.png'  restr+=ur'|http:\/\/[^\s,"]*\.gif'  restr+=ur'|http:\/\/[^\s,"]*\.bmp'  restr+=ur'|https:\/\/[^\s,"]*\.jpeg'    restr+=ur'|https:\/\/[^\s,"]*\.jpeg'  restr+=ur'|https:\/\/[^\s,"]*\.png'  restr+=ur'|https:\/\/[^\s,"]*\.gif'  restr+=ur'|https:\/\/[^\s,"]*\.bmp'  restr+=ur')'  htmlurl = re.compile(restr)  imgList = re.findall(htmlurl,html)  print imgList  return imgList def download(imgList, page):  x = 1  for imgurl in imgList:    filepathname=str(outpath+'pic_%09d_%010d'%(page,x)+str(os.path.splitext(urllib2.unquote(imgurl).decode('utf8').split('/')[-1])[1])).lower()    print '[Debug] Download file :'+ imgurl+' >> '+filepathname    urllib.urlretrieve(imgurl,filepathname)    x+=1 def downImageNum(pagenum):  page = 1  pageNumber = pagenum  while(page <= pageNumber):    html = getHtml(url)#獲得url指向的html內容    imageList = getImageList(html)#獲得所有圖片的地址，返回列表    download(imageList,page)#下載所有的圖片    page = page+1 if __name__ == '__main__':  downImageNum(1)

以上就是給大家匯總的3款Python實現的批量抓取妹紙圖片的代碼了，希望對大家學習Python爬蟲能夠有所協助。

