python2.7爬图（BeautifulSoup）

背景

上一节说到，要求自学使用python爬图，但是上次的代码不具有通用性，所以使用了BeautifulSoup。

1. 安装
   pip install beautifulsoup4
2. 搜索BeautifulSoup用法
   很方便地提取出HTML或XML标签中的内容
   https://cuiqingcai.com/1319.html
3. 改编上节代码
4. 解释
   if((head!=’//tb2’)& (head!=’//tb1’)):
   因为 “http://tieba.baidu.com/p/2460150866“这个地址里面有些图片地址很奇怪，//tb2开头的，代码解析不了，所以我直接用判断做了过滤。
   fTail = ‘jpg’
   因为图片格式很多png…所以决定统一处理成jpg格式

# -*- coding: utf-8 -*-  
import urllib  
import urllib2
import os 
from bs4 import BeautifulSoup
def getContentFromUrl(url):
    html=urllib2.urlopen(url)
    page = html.read()
    soup = BeautifulSoup(page, "html.parser")
    print 2
    return soup
def mkdir(path):  
        path = path.strip()  
        isExists = os.path.exists(path)  
        if not isExists:  
            print u'新建了名字叫做',path,u'的文件夹'   
            os.makedirs(path)
            return True  
        else:   
            print u'名为',path,u'的文件夹已经创建成功'  
            return False    
def getInfoFromContent(soup,name):
       number = 1
       imglist = soup.find_all('img')
       for imageURL in imglist:
            imageURL=imageURL.get('src')
            splitPath = imageURL.split('.')  
            fTail = splitPath.pop()
            head=splitPath[0]
            if((head!='//tb2')& (head!='//tb1')):
                if len(fTail)>=3:  
                    fTail = 'jpg'
                number2=1
                fileName = name + "/" + str(number2) + "." + fTail
                print fileName 
                # 对于每张图片地址，进行保存  
                try:
                    u = urllib2.urlopen(imageURL)  
                    data = u.read()  
                    f = open(fileName,'wb+')  
                    f.write(data)
                    print u'正在保存的一张图片为',fileName  
                    f.close()  
                except urllib2.URLError as e:  
                    print (e.reason)  
            number += 1    
if __name__ == "__main__":  
     soup = getContentFromUrl("http://tieba.baidu.com/p/2460150866")
     path = u'图片2'  
     mkdir(path)
     getInfoFromContent(soup,path)  

这是爬的百度贴吧里面图片分享的帖子。下面是网易的，有细微的差别。

# -*- coding: utf-8 -*-  
import urllib  
import urllib2
import os 
from bs4 import BeautifulSoup
def getContentFromUrl(url):
    html=urllib2.urlopen(url)
    page = html.read()
    soup = BeautifulSoup(page, "html.parser")
    print 2
    return soup
def mkdir(path):  
        path = path.strip()  
        isExists = os.path.exists(path)  
        if not isExists:  
            print u'新建了名字叫做',path,u'的文件夹'   
            os.makedirs(path)
            return True  
        else:   
            print u'名为',path,u'的文件夹已经创建成功'  
            return False    
def getInfoFromContent(soup,name):
       imglist = soup.find_all('img')
       number=1
       for imageURL in imglist:
            imageURL=imageURL.get('src')
            print imageURL
            if imageURL:
                splitPath = imageURL.split('.')  
                fTail = splitPath.pop()
                if len(fTail)>=3:  
                    fTail = 'jpg'                    
                    fileName = name + "/" + str(number) + "." + fTail
                    print fileName 
                    # 对于每张图片地址，进行保存  
                    try:
                        u = urllib2.urlopen(imageURL)  
                        data = u.read()  
                        f = open(fileName,'wb+')  
                        f.write(data)
                        print u'正在保存的一张图片为',fileName  
                        f.close()  
                    except urllib2.URLError as e:  
                        print (e.reason)
                    number+=1

if __name__ == "__main__":  
     soup = getContentFromUrl("http://www.163.com/")
     path = u'图片3'  
     mkdir(path)
     getInfoFromContent(soup,path)