bs4取数

# -*- coding: utf-8 -*-
from bs4 import BeautifulSoup

def file2soup(ffile):
    with open(ffile,‘r+b‘) as f:
        f.encoding=‘utf-8‘
        soup=BeautifulSoup(f,‘lxml‘)
        # print (soup)
        return soup
    pass

# def soup2list(soup,ulist):
#     # print (soup.div)
#     for i in soup.find(‘tbody‘).children:
#         if isinstance(i,bs4.element.Tag):
#             o=i(‘td‘)
#             ulist.append([o[0].string,o[1].string,o[3].string])
#     return ulist

# def soup2list(soup,ulist):
#     # print (soup.div)
#     for i in soup.find(‘tbody‘).children:
#         if len(i)>1:#去空行
#             o=i(‘td‘)#取出td标签  "td"加引号 o:<class ‘bs4.element.ResultSet‘> !!!
#             a,b,c=0,1,3
#             ulist.append([o[a].string,o[b].string,o[c].string])
#     return ulist

def soup2list(soup,ulist):
    i=soup.find(‘tbody‘,id="hidden_zhpm")
    # print (len(i))
    print (i)



url = ‘http://bj.58.com/pinpaigongyu/pn/{ppp}/?minprice=2000_4000‘
ffile=‘d://best.txt‘
ulist=[]

soup=file2soup(ffile)
ulist=soup2list(soup,ulist)
# print (ulist)
# print (‘{:0>3}\t  {:+<15}\t  {: >5}\t‘.format(‘排名‘,‘校名‘,‘总分‘))
# for i in range(11):
#     u=ulist[i]
#     #{:起头+一个填充符+对齐方式+字符长度}
#     print (‘{:0>3}\t  {:+<15}\t  {: >5}\t‘.format(u[0], u[1], u[2] ))

bs4取数

原文：http://www.cnblogs.com/e35t/p/7040051.html