python妹子圖簡單爬蟲執行個體

本文執行個體講述了python妹子圖簡單爬蟲實現方法。分享給大家供大家參考。具體如下：

#!/usr/bin/env python#coding: utf-8import urllibimport urllib2import osimport reimport sys#顯示下載進度def schedule(a,b,c):  '''''  a:已經下載的資料區塊  b:資料區塊的大小  c:遠程檔案的大小  '''  per = 100.0 * a * b / c  if per > 100 :    per = 100  print '%.2f%%' % per#擷取html源碼def getHtml(url):  page = urllib.urlopen(url)  html = page.read()  return html#下載圖片def downloadImg(html, num, foldername):  picpath = '%s' % (foldername) #下載到的本地目錄  if not os.path.exists(picpath): #路徑不存在時建立一個    os.makedirs(picpath)  target = picpath+'/%s.jpg' % num  myItems = re.findall('
',html,re.S)  print 'Downloading image to location: ' + target  urllib.urlretrieve(myItems[0], target, schedule)#正則匹配分頁def findPage(html):  myItems = re.findall('(\d*)', html, re.S)  return myItems.pop()#正則匹配列表def findList(html):  myItems = re.findall('
.*?
', html, re.S)  return myItems#總下載def totalDownload(modelUrl):  listHtml5 = getHtml(modelUrl)  listContent = findList(listHtml)  for list in listContent:    html = getHtml('http://www.mzitu.com/' + str(list[0]))    totalNum = findPage(html)    for num in range(1, int(totalNum)+1):      if num == 1:        url = 'http://www.mzitu.com/' + str(list[0])        html5 = getHtml(url)        downloadImg(html5, str(num), str(list[1]))      else:        url = 'http://www.mzitu.com/' + str(list[0]) + '/'+str(num)        html5 = getHtml(url)        downloadImg(html5, str(num), str(list[1]))if __name__ == '__main__':  listHtml = getHtml('http://www.mzitu.com/model')  #這是其中一個模組的url，可以添加不同的模組url從而達到整站爬取。  for model in range(1, int(findPage(listHtml))+1):    if model == 1:      modelUrl = 'http://www.mzitu.com/model'      totalDownload(modelUrl)    else:      modelUrl = 'http://www.mzitu.com/model/page/' + str(model)      totalDownload(modelUrl)  print "Download has finished."

希望本文所述對大家的Python程式設計有所協助。

