初步的百度爬虫

from bs4 import BeautifulSoup
import urllib2
import urllib
import re
import urlparse

param = raw_input('Please input what your want search')
#   www.baidu.com/s?&wd=kkkkkkkkkkkk
yeshu = int(raw_input('Please input page number 1-10'))
#www.baidu.com/s?wd=11111&pn=20
for i in range(yeshu):
    i = i * 10
    url = 'http://www.baidu.com/s?&wd='+param+'&pn='+str(i)
    try:
        req = urllib2.urlopen(url)
    except urllib2.URLError,e:
        continue
    content = req.read()

    soap = BeautifulSoup(content)

    link = soap.find_all(class_ = 't')

    href = []
    for i in range(len(link)):
        pattern = re.compile('href=\"(.+?)\"')
        rs = pattern.findall(str(link[i]))
        if len(rs) == 0:
            break
        href.append(str(rs[0]))

    for t in range(len(href)):
        try:
            ss = urllib2.urlopen(href[t])
        except urllib2.URLError,e:
            continue
        real = ss.geturl()
        domain = urlparse.urlparse(real)
        realdomain = domain.netloc
        fp = open('url.txt','a+')
        fp.write(realdomain+'\n')
        fp.close()

    

 

你可能感兴趣的:(初步的百度爬虫)