Python爬虫urllib2笔记(三)之使用正则表达式提取百度贴吧网页中的楼主发的图片

使用正则表达式提取百度贴吧网页中的楼主发的图片

# -*- coding:utf-8 -
import re  #正则模块
import urllib2
import urllib

#使用正则表达式提取百度贴吧网页中的楼主发的图片

def get_content(url):
    html = urllib.urlopen(url)
    content = html.read()
    html.close()
    return content

def get_imgs(info):
	"""
	<img class="BDE_Image" src="http://imgsrc.baidu.com/forum/w%3D580/sign=eadc62078094a4c20a23e7233ef51bac/63395bb5c9ea15ce0a876301b1003af33a87b24b.jpg"
	 size="65807" height="600" width="425">
	"""
	#正则表达式+?重复一次或多次 发现BDE_Image属性值是楼主发的图片--不会把签名和头像下载下
	regex = r'class="BDE_Image" src="(.+?\.jpg)"'
	pat=re.compile(regex)
	images_code=re.findall(pat,info)
	i = 0
	for img_url in images_code:
		print img_url
		urllib.urlretrieve(img_url,'F:\\data\\pachong\\pic2\\%s.jpg' % i)
		i +=1


# info=get_content("http://tieba.baidu.com/p/4311459540")	
info=get_content("http://tieba.baidu.com/p/4364768066")	
print get_imgs(info)

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

def get_content(url):
    response = urllib2.urlopen(url)
    content = response.read()
    return content

def get_pages(content):
    reg = re.compile(r'<span class="red">(\d+)</span>')
    pages = reg.search(content).groups()
    print "本帖子共%d页 " % int(pages[0])
    return str(pages[0])

def get_imgurls(content):
    ''' doc.'''
    global num
    regxt = r'class="BDE_Image" src="(.+?\.jpg)"'
    #urllist= regxt.search(content).groups()
    urllist= re.findall(regxt, content)
    if not urllist:
        regxt = r'class="BDE_Image" height=".+?" src="(.+?\.jpg)"'
        #urllist= regxt.search(content).groups()
        urllist= re.findall(regxt, content)
    print "第%d页一共%d张图片" % (num+1,len(urllist))
    return urllist
def get_imgs(urllist):
    global item
    global retre_sec
    retre_sec.clear()
    i = 0
    for ImgUrl in urllist:

        try:
            urllib.urlretrieve(ImgUrl, '%03d.jpg' % item)
            print "保存%03d图片成功。%d" % (item,i)
        except:
            retre_sec[ImgUrl] = item
            print "保存%03d图片失败。进行第二次保存。%d" % (item,i)
        finally:
            item += 1
            i += 1

def retre_images_sec(urldict):
    if len(urldict):
        print "现在开始第二次保存，共%03d张图片" % len(urldict)
        for url in urldict:
            try:
                urllib.urlretrieve(url, '%03d.jpg' % urldict[url])
                print "第二次保存%03d图片成功。" % urldict[url]
            except:
                print "第二次保存%03d图片失败" % item
                print "图片地址为 %s" % url
    else:
        print "第二次无图片需要保存。"

item = 1
retre_sec = dict()
url = 'http://tieba.baidu.com/p/2982230467'
url += '?see_lz=1'
content = get_content(url) 
pages = int(get_pages(content))    #得到帖子页数 只看楼主

for num in range(pages):
    url += '&pn=%d' % (num+1)
    content = get_content(url)             #得到html源码
    img_list = get_imgurls(content)     #得到所有图片的URL 以list形式返回
    get_imgs(img_list)                         #遍历list 保存图片