中谷教育Python视频（课件、源码）推荐

import urllib  
import re  
   
def getHtml(url):  
    """通过页面url获取其对应的html内容 
    """  
    page = urllib.urlopen(url) #打开页面  
    content = page.read() #读取页面内容  
    return content  
     
def getImage(html):  
    """通过解析html获取图片地址，实现图片的下载 
    """  
    regx =r'src="(.+?\.jpg)" pic_ext' #利用正则表达式获得图片url  
    imgreg = re.compile(regx)  
    imglist = re.findall(imgreg,html)  
    x = 0  
    for imgurl in imglist:  
        filepath ='F:\\Downloads\\'+str(x)+'.jpg'  
        urllib.urlretrieve(imgurl,filepath) #将图片下载到本地  
        x += 1  
    print 'completed!'  
     
html = getHtml('http://tieba.baidu.com/p/2505265675')  
imglist = getImage(html)

import Queue  
initial_page ="http://www.renminribao.com"  
url_queue =Queue.Queue()  
seen = set()  
seen.insert(initial_page)  
url_queue.put(initial_page)  
while True:  
    if url_queue.size()>0:  
        current_url = url_queue.get()    #取出队例中第一个的url  
        store(current_url)             #把这个url代表的网页存储好  
        for next_url inextract_urls(current_url): #提取把这个url里链向的url  
            if next_url not in seen:  
                seen.put(next_url)  
                url_queue.put(next_url)  
    else:  
        break