首页 > 代码库 > Python爬虫之路——简单网页抓图升级版(增加多线程支持)

Python爬虫之路——简单网页抓图升级版(增加多线程支持)

转载自我的博客:http://www.mylonly.com/archives/1418.html

经过两个晚上的奋斗,将上一篇文章介绍的爬虫稍微改进了下(Python爬虫之路——简单网页抓图),主要是将获取图片链接任务和下载图片任务用线程分开来处理了,而且这次的爬虫不仅仅可以爬第一页的图片链接的,整个http://desk.zol.com.cn/meinv/下面的图片都会被爬到,而且提供了多种分辨率图片的文件下载,具体设置方法代码注释里面有介绍。

这次的代码仍然有点不足,Ctrl-C无法终止程序,应该是线程无法响应主程序的终止消息导致的,(最好放在后台跑程序)还有线程的分配还可以优化的更好一点,后续会陆续改进.

#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:'