Python实现多线程抓取妹子图


Posted in Python onAugust 08, 2015

心血来潮写了个多线程抓妹子图,虽然代码还是有一些瑕疵,但是还是记录下来,分享给大家。

Pic_downloader.py

# -*- coding: utf-8 -*-
"""
Created on Fri Aug 07 17:30:58 2015
 
@author: Dreace
"""
import urllib2
import sys
import time
import os
import random
from 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 name
def 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 + "下载超时,跳过!".decode("utf-8").encode(type_)
def Filter(content):
  for line in Filter_list:
    line=line.strip('\n')
    if content.find(line) == -1:
      return True
def 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 "获取图片超时,跳过!".decode("utf-8").encode(type_)
MAX = 2
count = 0
time_out = 60
thread_num = 30
pic_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 "获取到".decode("utf-8").encode(type_),len(pic_list),"张图片,开始下载!".decode("utf-8").encode(type_)
pool = ThreadPool(thread_num) 
pool.map(download_pic,pic_list)
pool.close() 
pool.join()
print count,"张图片保存在".decode("utf-8").encode(type_) + dir_name
print "共耗时".decode("utf-8").encode(type_),time.time() - start_time,"s"

我们来看下一个网友的作品

#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/python

import re,urllib2,HTMLParser,threading,Queue,time

#各图集入口链接
htmlDoorList = []
#包含图片的Hmtl链接
htmlUrlList = []
#图片Url链接Queue
imageUrlList = Queue.Queue(0)
#捕获图片数量
imageGetCount = 0
#已下载图片数量
imageDownloadCount = 0
#每个图集的起始地址,用于判断终止
nextHtmlUrl = ''
#本地保存路径
localSavePath = '/data/1920x1080/'

#如果你想下你需要的分辨率的,请修改replace_str,有如下分辨率可供选择1920x1200,1980x1920,1680x1050,1600x900,1440x900,1366x768,1280x1024,1024x768,1280x800
replace_str = '1920x1080'

replaced_str = '960x600'

#内页分析处理类
class ImageHtmlParser(HTMLParser.HTMLParser):
def __init__(self):
self.nextUrl = ''
HTMLParser.HTMLParser.__init__(self)
def handle_starttag(self,tag,attrs):
global imageUrlList
if(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 imageGetCount
imageGetCount = imageGetCount + 1
print url
elif(tag == 'a' and len(attrs) == 4):
if(attrs[0] == ('id','pageNext') and attrs[1] == ('class','next')):
global nextHtmlUrl
nextHtmlUrl = attrs[2][1];

#首页分析类
class IndexHtmlParser(HTMLParser.HTMLParser):
def __init__(self):
self.urlList = []
self.index = 0
self.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):
#第一层找到了
self.index = 1
else:
#第二层找到了
self.index = 0
print attrs[1][1]
self.urlList.append(attrs[1][1])
break
elif(tag == 'a'):
for attr in attrs:
if (attr[0] == 'id' and attr[1] == 'pageNext'):
self.nextUrl = attrs[1][1]
print 'nextUrl:',self.nextUrl
break

#首页Hmtl解析器
indexParser = IndexHtmlParser()
#内页Html解析器
imageParser = ImageHtmlParser()

#根据首页得到所有入口链接
print '开始扫描首页...'
host = 'http://desk.zol.com.cn'
indexUrl = '/meinv/'
while (indexUrl != ''):
print '正在抓取网页:',host+indexUrl
request = urllib2.Request(host+indexUrl)
try:
m = urllib2.urlopen(request)
con = m.read()
indexParser.feed(con)
if (indexUrl == indexParser.nextUrl):
break
else:
indexUrl = indexParser.nextUrl
except urllib2.URLError,e:
print e.reason

print '首页扫描完成,所有图集链接已获得:'
htmlDoorList = indexParser.urlList

#根据入口链接得到所有图片的url
class getImageUrl(threading.Thread):
def __init__(self):
threading.Thread.__init__(self)
def run(self):
for door in htmlDoorList:
print '开始获取图片地址,入口地址为:',door
global nextHtmlUrl
nextHtmlUrl = ''
while(door != ''):
print '开始从网页%s获取图片...'% (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 '下一个页面地址为:',nextHtmlUrl
if(door == nextHtmlUrl):
break
except urllib2.URLError,e:
print e.reason
print '所有图片地址均已获得:',imageUrlList

class getImage(threading.Thread):
def __init__(self):
threading.Thread.__init__(self)
def run(self):
global imageUrlList
print '开始下载图片...'
while(True):
print '目前捕获图片数量:',imageGetCount
print '已下载图片数量:',imageDownloadCount
image = imageUrlList.get()
print '下载文件路径:',image
try:
cont = urllib2.urlopen(image).read()
patter = '[0-9]*\.jpg';
match = re.search(patter,image);
if match:
print '正在下载文件:',match.group()
filename = localSavePath+match.group()
f = open(filename,'wb')
f.write(cont)
f.close()
global imageDownloadCount
imageDownloadCount = imageDownloadCount + 1
else:
print 'no match'
if(imageUrlList.empty()):
break
except urllib2.URLError,e:
print e.reason
print '文件全部下载完成...'

get = getImageUrl()
get.start()
print '获取图片链接线程启动:'

time.sleep(2)

download = getImage()
download.start()
print '下载图片链接线程启动:'

批量抓取指定网页上的所有图片

# -*- 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)#获得url指向的html内容
    imageList = getImageList(html)#获得所有图片的地址,返回列表
    download(imageList,page)#下载所有的图片
    page = page+1
 
if __name__ == '__main__':
  downImageNum(1)

以上就是给大家汇总的3款Python实现的批量抓取妹纸图片的代码了,希望对大家学习Python爬虫能够有所帮助。

Python 相关文章推荐
Python Web框架Flask中使用七牛云存储实例
Feb 08 Python
浅谈Python数据类型之间的转换
Jun 08 Python
Python中使用bidict模块双向字典结构的奇技淫巧
Jul 12 Python
Python连接SQLServer2000的方法详解
Apr 19 Python
Python实现简单网页图片抓取完整代码实例
Dec 15 Python
使用numpy和PIL进行简单的图像处理方法
Jul 02 Python
Python3+django2.0+apache2+ubuntu14部署网站上线的方法
Jul 07 Python
python得到qq句柄,并显示在前台的方法
Oct 14 Python
Python程序暂停的正常处理方法
Nov 07 Python
python 爬取疫情数据的源码
Feb 09 Python
为什么相对PHP黑python的更少
Jun 21 Python
Python Matplotlib绘图基础知识代码解析
Aug 31 Python
通过Python来使用七牛云存储的方法详解
Aug 07 #Python
Python爬虫框架Scrapy实战之批量抓取招聘信息
Aug 07 #Python
深入理解Python中命名空间的查找规则LEGB
Aug 06 #Python
举例详解Python中yield生成器的用法
Aug 05 #Python
Python中return语句用法实例分析
Aug 04 #Python
python函数形参用法实例分析
Aug 04 #Python
Python简明入门教程
Aug 04 #Python
You might like
PHP静态调用非静态方法的应用分析
2013/05/02 PHP
web站点获取用户IP的安全方法 HTTP_X_FORWARDED_FOR检验
2013/06/01 PHP
PHP在网页中动态生成PDF文件详细教程
2014/07/05 PHP
PHP实现与java 通信的插件使用教程
2019/08/11 PHP
javascript下操作css的float属性的特殊写法
2007/08/22 Javascript
Ext javascript建立超链接,进行事件处理的实现方法
2009/03/22 Javascript
javascript 全选与全取消功能的实现代码
2012/12/23 Javascript
javascript下拉框选项单击事件的例子分享
2015/03/04 Javascript
javascript实现youku的视频代码自适应宽度
2015/05/25 Javascript
JS两个数组比较,删除重复值的巧妙方法(推荐)
2016/06/03 Javascript
微信JS接口大全
2016/08/25 Javascript
ES6新特征数字、数组、字符串
2016/10/01 Javascript
详解JS中的快速排序与冒泡
2017/01/10 Javascript
node.js express中app.param的用法详解
2017/07/16 Javascript
微信小程序scroll-view实现滚动到锚点左侧导航栏点餐功能(点击种类,滚动到锚点)
2020/06/11 Javascript
[01:02:47]EG vs Secret 2019国际邀请赛淘汰赛 胜者组 BO3 第一场 8.21.mp4
2020/07/19 DOTA
[01:06:19]DOTA2-DPC中国联赛定级赛 LBZS vs SAG BO3第二场 1月8日
2021/03/11 DOTA
Python类的定义、继承及类对象使用方法简明教程
2015/05/08 Python
python字符串,数值计算
2016/10/05 Python
python 弹窗提示警告框MessageBox的实例
2019/06/18 Python
python读文件的步骤
2019/10/08 Python
解决pycharm同一目录下无法import其他文件
2020/02/12 Python
css3的过滤效果简单实例
2016/08/03 HTML / CSS
世界最大的票务市场:viagogo
2017/02/16 全球购物
速比涛英国官网:Speedo英国
2019/07/15 全球购物
莫斯科珠宝厂官方网站:Miuz
2020/09/19 全球购物
JSF如何进行表格处理及取值
2012/08/06 面试题
保荐人的岗位职责
2013/11/19 职场文书
秋季运动会活动方案
2014/02/05 职场文书
人事专员岗位职责说明书
2014/07/30 职场文书
工商局所长四风自我剖析及整改措施
2014/10/26 职场文书
2015年基层党支部工作总结
2015/05/21 职场文书
麦田里的守望者读书笔记
2015/06/30 职场文书
一文带你理解vue创建一个后台管理系统流程(Vue+Element)
2021/05/18 Vue.js
使用Redis实现实时排行榜功能
2021/07/02 Redis
Python3使用Qt5来实现简易的五子棋小游戏
2022/05/02 Python