Python爬取并分析网页【基本版】

#!/usr/bin/python
# -*- coding: UTF-8 -*-

import urllib
from pyquery import PyQuery as pq
import codecs


# fetch page
print 'fetch page...'
url = 'http://www.7dsw.com/toplastupdate/1.html'
resp = urllib.urlopen(url)
page = resp.read()
page = page.decode('gbk')

#get data


print 'parse page...'
doc = pq(page)
wanted = doc('#newscontent ul a')

n = len(wanted)

books = []
caps = []


i = 0
while i<n:
    bookname = wanted[i].text
    captitle = wanted[i+1].text
    books.append(bookname)
    caps.append(captitle)
    i+=2



print 'save data...'
#save data
#fp = open('save.txt','wb')
fp = codecs.open('intimate.txt','a','utf-8')



for i in range(len(books)):
    fp.write(books[i])
    fp.write(",")
    fp.write(caps[i])

    fp.write("\r\n")

fp.close()