本文以实例形式讲述了python实现抓取网页并解析的功能。主要解析问答与百度的首页。分享给大家供大家参考之用。
主要功能代码如下：
#!/usr/bin/python
#coding=utf-8
import sys
import re
import urllib2
from urllib import urlencode
from urllib import quote
import time
maxline = 2000
wenda = re.compile(“href=\”http://wenda.so.com/q/.+\?src=(.+?)\””)
baidu = re.compile(“更多知道相关问题.*?”)
f1 = open(“baidupage.txt”,”w”)
f2 = open(“wendapage.txt”,”w”)
for line in sys.stdin:
if maxline == 0:
break
query = line.strip();
time.sleep(1);
recall_url = “http://www.so.com/s?&q=” + query;
response = urllib2.urlopen(recall_url);
html = response.read();
f1.write(html)
m = wenda.search(html);
if m:
if m.group(1) == “110”:
print query + “\twenda\t0”;
else:
print query + “\twenda\t1”;
else:
print query + “\twenda\t0”;
recall_url = “http://www.baidu.com/s?wd=” + query +”&ie=utf-8″;
response = urllib2.urlopen(recall_url);
html = response.read();
f2.write(html)
m = baidu.search(html);
if m:
print query + “\tbaidu\t1”;
else:
print query + “\tbaidu\t0”;
maxline = maxline – 1;
f1.close()
f2.close()
希望本文所述对大家python程序设计的学习有所帮助。