python爬取网页表格_求教如何通过python抓取网页中表格信息

展开全部

看你2113抓的是静态还是动5261态的了，这里是静态表4102格信息的代码：1653from BeautifulSoup import BeautifulSoup

import urllib2

import re

import string

def earse(strline,ch) :

left = 0

right = strline.find(ch)

while right !=-1 :

strline = strline.replace(ch,'')

right = strline.find(ch)

return strline

url = r"http://www.bjsta.com"

resContent = urllib2.urlopen(url).read()

resContent = resContent.decode('gb18030').encode('utf8')

soup = BeautifulSoup(resContent)

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 :

span = tdIter('span')

for i in range(len(span)) :

if span[i].string :

print earse(span[i].string,' ').strip(),

else :

pass

print