Python实现多线程抓取妹子图

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)