使用python进行re拆分网页内容

这里简短的总结一下而不是完全的罗列python的re模块，python的re具有强大的功能，如下是一个从我们学校抓取数据然后拆分的程序，代码如下：

import httplib
import urllib
import re
import sys
reload(sys)

sys.setdefaultencoding("utf-8")

parameters = "__EVENTTARGET=&__EVENTARGUMENT=&__LASTFOCUS=&__VIEWSTATE=%2FwEPDwUKLTYwNjgwNDAyOQ8WBB4Jcm9vbXRhYmxlBQ9qZGRhdGFfcm9vbXZpZXceCWRhdGF0YWJsZQULamRkYXRhX3ZpZXcWAgIDD2QWBgIDDxBkZBYBAgFkAgUPEA8WBB4NRGF0YVRleHRGaWVsZAUIUk9PTU5BTUUeC18hRGF0YUJvdW5kZ2QQFRIPMDflj7flhazlr5MgICAgDzA45Y%2B35YWs5a%2BTICAgIA8wOeWPt%2BWFrOWvkyAgICAPMTDlj7flhazlr5MgICAgDzEy5Y%2B35YWs5a%2BTICAgIA8xM%2BWPt%2BWFrOWvkyAgICAPMTTlj7flhazlr5MgICAgDzE15Y%2B35YWs5a%2BTICAgIA8xNuWPt%2BWFrOWvkyAgICAPMTflj7flhazlr5MgICAgDzE45Y%2B35YWs5a%2BTICAgIA4xOeWPt%2BalvCAgICAgIA4yMOWPt%2BalvCAgICAgIA7mnKznp5E0ICAgICAgIA7mnKznp5E1ICAgICAgIA7mnKznp5E2ICAgICAgIA7noJTnqbYyICAgICAgIA7noJTnqbYzICAgICAgIBUSDzA35Y%2B35YWs5a%2BTICAgIA8wOOWPt%2BWFrOWvkyAgICAPMDnlj7flhazlr5MgICAgDzEw5Y%2B35YWs5a%2BTICAgIA8xMuWPt%2BWFrOWvkyAgICAPMTPlj7flhazlr5MgICAgDzE05Y%2B35YWs5a%2BTICAgIA8xNeWPt%2BWFrOWvkyAgICAPMTblj7flhazlr5MgICAgDzE35Y%2B35YWs5a%2BTICAgIA8xOOWPt%2BWFrOWvkyAgICAOMTnlj7fmpbwgICAgICAOMjDlj7fmpbwgICAgICAO5pys56eRNCAgICAgICAO5pys56eRNSAgICAgICAO5pys56eRNiAgICAgICAO56CU56m2MiAgICAgICAO56CU56m2MyAgICAgICAUKwMSZ2dnZ2dnZ2dnZ2dnZ2dnZ2dnZGQCFQ88KwANAGQYAQUJR3JpZFZpZXcxD2dks72pwRhFZXy7shqK0FV%2BHo%2BV6xw%3D&__EVENTVALIDATION=%2FwEWIwLCqrCECgKehO%2FXDgKS2sqQDQKbhO%2FXDgLvo6%2FWAQKchO%2FXDgKco5mFBAKo7ZuOCQKQtOGrAwLGtc2eAwKUkP3jDgKphpG2AgL3ot33AgL3ov2mCALP9anUDQLO9e2UAQLO9fEwAsHtjeQDAsHtlaACAsHtmdwCAsHtnfwCAs7toZgNAs7tpbgNAs7tqdQNAsHt7ZQBApnz9msChpiS3QMCtcKkWgL%2BhMCpBAK7ovXVAwLVvLqTBQKewdn%2BDgLeuZHECgK8w4S2BAKjm5WMBhrpaK%2FPVR7L%2BngMlHOw%2B5OLj989&DistrictDown=%E5%98%89%E5%AE%9A%E6%A0%A1%E5%8C%BA&BuildingDown=12%E5%8F%B7%E5%85%AC%E5%AF%93++++&RoomnameText="+sys.argv[1]+"&Submit=%E6%9F%A5%E8%AF%A2"

headers =  {"Content-type": "application/x-www-form-urlencoded","Accept": "text/plain"}

conn = httplib.HTTPConnection("nyglzx.tongji.edu.cn")

conn.request("POST","/web/datastat.aspx",parameters,headers)

response = conn.getresponse()

print response.status,response.reason

result = response.read()

pattern = r'<td><font color="Black">\d+-\d+-\d+</font></td><td><font color="Black">\d+,\d+.\d+</font></td><td><font color="Black">\d+,\d+.\d+</font></td><td><font color="Black">\d+.\d+</font></td>'

matchs = re.findall(pattern,result)

pattern = r'<td><font color="Black">(\d+-\d+-\d+)</font></td><td><font color="Black">(\d+,\d+.\d+)</font></td><td><font color="Black">(\d+,\d+.\d+)</font></td><td><font color="Black">(\d+.\d+)</font></td>'

for i in matchs:
	tm = re.match(pattern, i)
	print tm.group(1),tm.group(2),tm.group(3),tm.group(4)

　　这里面的re模块主要用到了两个,一个是result = re.match(pattern,content), 通过result.group(1:n)来访问pattern中以()括起来的内容。另一个是result = re.findall(pattern,content),它的结果用for来访问或者result[index]来访问即可了。