本文以實(shí)例形式講述了Python實(shí)現(xiàn)抓取網(wǎng)頁并解析的功能。主要解析問答與百度的首頁。分享給大家供大家參考之用。

主要功能代碼如下：

?123456789101112131415161718192021222324252627282930313233343536373839404142434445 #!/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=\""") baidu = re.compile("<a href=\"".*?>更多知道相關(guān)問題.*?</a>") 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 = "=" + 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 = "=" + 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()

更多信息請(qǐng)查看IT技術(shù)專欄