Python爬取表格及图片

import urllib
import re
from bs4 import BeautifulSoup  
url='https://baike.baidu.com/item/https/285356?fr=aladdin'
#def getHtml(url):
page = urllib.request.urlopen(url)
html=page.read().decode(encoding='utf-8',errors='strict')
#    return html
print(html)
def earse(strline,ch) :  
   # left = 0  
    right = strline.find(ch)  
       
    while right !=-1 :  
            strline = strline.replace(ch,'')  
            right = strline.find(ch)  
    return strline 


#爬取table
#def getTable(html):
   # reg=''
    #tablere=re.compile(reg)
    #tablelist=re.findall(tablere,html)
#爬取table结束
        
soup = BeautifulSoup(html)  
min_salary=[]
min_salary_rows=[]
print (soup('title')[0].string)  
   
tab= soup.findAll('table')  
   
trs = tab[len(tab)-1].findAll('tr')  
   
for trIter in trs :  
        tds = trIter.findAll('td')  
        for tdIter in tds :  
                p = tdIter('p')  
                for i in range(len(p)) :  
                        if p[i].string :  
                            min_salary_rows.append((earse(p[i].string,' ').strip()))
                            print (earse(p[i].string,' ').strip()),  
                        else :  
                                pass  
                min_salary.append(min_salary_rows)      
        print
print(min_salary)


#html = getHtml("http://www.mohrss.gov.cn/ldgxs/LDGXqiyegongzi/LDGXzuidigongzibiaozhun/201612/t20161213_261789.html")

#爬取图片地址
def getImg(html):
    reg = r'src="(.+?\.jpg)" pic_ext'
    imgre = re.compile(reg)
    imglist = re.findall(imgre,html)
    x = 0
    for imgurl in imglist:
        urllib.urlretrieve(imgurl,'%s.jpg' % x)
        x+=1
#爬取图片地址结束