爬虫抓取表格中的数据

#coding:utf-8

import re
import urllib2

url=‘http://58921.com/‘
header={‘User-Agent‘:‘Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/60.0.3112.90 Safari/537.36‘}

request=urllib2.Request(url,headers=header)
page_code=urllib2.urlopen(request).read()

# 从网页源码中找到你要抓取表格的下列信息

# 表格开头
start_code=‘<table class="table table table-bordered table-condensed">‘
# 表格结尾
end_code=‘</tbody>‘
# 表格中要抓取的数据
find_code=‘<td><a href=".*?" title=".*?">(.*?)</a></td><td>(.*?)</td><td>(.*?)</td><td>(.*?)</td><td>(.*?)</td>‘

# 这里通过 start和end指定在整个页面中你所寻找的表格
start=page_code.find(start_code)
end=page_code.find(end_code)
find=page_code[start:end]

final_find=re.findall(find_code,find)

for x in final_find:
    print ‘,‘.join(x)

print ‘finish‘