python爬取百度贴吧的图片1

python版本：2.7.10
学习python爬虫，首先写了一个爬取百度贴吧图片的程序。参考了静觅的系列博客

好了，先上代码：

# -*- coding : utf-8 -*-
import urllib
import urllib2
import re


class imgTest:

    def __init__(self, baseUrl, seeLZ):
        self.baseUrl = baseUrl
        self.seeLZ = '?see_lz='+str(seeLZ)
        # self.tool = Tool()
    #save a single img 
    def saveImg(self,imageURL,filename):
        u = urllib.urlopen(imageURL)
        data = u.read()
        f = open(filename,'wb')
        f.write(data)
        f.close()
    #download images
    def saveImgs(self, images, name, num):
        number = num
        for imageURL in images:
            splitPath = imageURL.split('.')
            fTail = splitPath.pop()
            if len(fTail)>3:
                fTail = "jpg"
            fileName = name+"/"+str(number)+"."+fTail
            self.saveImg(imageURL,fileName)
            number += 1
    #get img urls       
    def getAllImageURLs(self,pageNum):
        page = self.getPage(pageNum)        
        patternImg = re.compile(r'.*?(.*?)',re.S)
        result = re.search(pattern, page)
        if result:
            self.printToLog("page total num:"+result.group(1))
            return result.group(1).strip()
        else:
            return None
    #get the html source code
    def getPage(self, pageNum):
        
        try:
            url = self.baseUrl+self.seeLZ +'&pn='+str(pageNum)
            request = urllib2.Request(url)
            response = urllib2.urlopen(request)
            content = response.read()
            return content
        except urllib2.URLError, e:
            if hasattr(e, "reason"):
                print "failed to connect baidutieba.",e.reason
                return None

baseURL = 'http://tieba.baidu.com/p/3925387672'
imgtest = imgTest(baseURL,1)
totalnum = int(imgtest.getPageNum())

imageCount = 0
for i in range(1, totalnum+1):
    imageURLs = imgtest.getAllImageURLs(i)
    imgtest.saveImgs(imageURLs,"pic",imageCount)
    imageCount += len(imageURLs)
    print imageCount

由于我的sublime Text有一点编码问题我还没来及管，所以函数的注释就用英文注释了（好像只有我能看懂）。最关键的一步就是getAllImageURLs这个函数了，需要从网页中抽取到图片的url，学好正则表达式真的很重要啊。还有一点，就是我发现百度贴吧的帖子里的图片url格式不太一样，不同的帖子要具体的分析过才行的哦，不过呢，这个正则表达式只要稍作修改就可以满足要求了。

OK，我要去爬本漫画书来看咯：)