[root@~]# python
Python 2.4.3 (#1, May 5 2011, 16:39:10)
[GCC 4.1.2 20080704 (Red Hat 4.1.2-50)] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>;>>
[root@~]#
下載新版本的python
[root@~]# wget
解壓縮 以及編譯
[root@~]# tar jxvf Python-2.7.3.tar.bz2
[root@wangyuelou Python-2.7.2]# ./configure --prefix=/usr/local/python27
[root@wangyuelou Python-2.7.2]# make
[root@wangyuelou Python-2.7.2]# make install
[root@wangyuelou Python-2.7.2]# ls /usr/local/python27/ -al
total 28
drwxr-xr-x 6 root root 4096 Jul 14 00:21 .
drwxr-xr-x 20 root root 4096 Jul 14 00:17 ..
drwxr-xr-x 2 root root 4096 Jul 14 00:21 bin
drwxr-xr-x 3 root root 4096 Jul 14 00:21 include
drwxr-xr-x 4 root root 4096 Jul 14 00:21 lib
drwxr-xr-x 3 root root 4096 Jul 14 00:21 share
覆蓋原來的python連結
[root@wangyuelou Python-2.7.2]# mv /usr/bin/python /usr/bin/python_old
[root@wangyuelou Python-2.7.2]# ln -s /usr/local/python27/bin/python /usr/bin/
[root@wangyuelou Python-2.7.2]# python
Python 2.7.2 (default, Jul 14 2011, 00:20:14)
[GCC 4.1.2 20080704 (Red Hat 4.1.2-50)] on linux2
Type "help", "copyright", "credits" or "license" for more information.
>>>
此處已經可以正常使用python2.7了
但是因為yum是使用的2.4的版本來用的,所以 還需要修改一下
[root@~]# yum
There was a problem importing one of the Python modules
required to run yum. The error leading to this problem was:
No module named yum
Please install a package which provides this module, or
verify that the module is installed correctly.
It's possible that the above module doesn't match the
current version of Python, which is:
2.7.2 (default, Jul 14 2011, 00:20:14)
[GCC 4.1.2 20080704 (Red Hat 4.1.2-50)]
If you cannot solve this problem yourself, please go to
the yum faq at:
[root@wangyuelou Python-2.7.2]# vim /usr/bin/yum
#!/usr/bin/python #修改此處為2.4的位置
[root@~]# vim /usr/bin/yum
#!/usr/bin/python2.4
[root@~]# yum
Loaded plugins: fastestmirror
You need to give some command
usage: yum [options] COMMAND
List of Commands:
check-update Check for available package updates
clean Remove cached data
deplist List a package's dependencies
downgrade downgrade a package
erase Remove a package or packages from your system
groupinfo Display details about a package group
groupinstall Install the packages in a group on your system
grouplist List available package groups
groupremove Remove the packages in a group from your system
help Display a helpful usage message
info Display details about a package or group of packages
install Install a package or packages on your system
list List a package or groups of packages
localinstall Install a local RPM
yum 又可以使用了)
# Process the JSON string.
results = simplejson.load(response)
# now have some fun with the results...
實際應用中可能需要抓取google的很多網頁,所以還需要使用多執行緒來分擔抓取任務。使用google web search api的參考詳細介紹,請看此處(這裡介紹了Standard URL Arguments)。另外要特別注意,url中引數rsz必須是8(包括8)以下的值,若大於8,會報錯的!
(3)程式碼實現
程式碼實現還存在問題,但是能夠執行,魯棒性差,還需要進行改進,希望各路大神指出錯誤(初學Python),不勝感激。
#-*-coding:utf-8-*-
import urllib2,urllib
import simplejson
import os, time,threading
import common, html_filter
#input the keywords
keywords = raw_input('Enter the keywords: ')
#define rnum_perpage, pages
rnum_perpage=8
pages=8
#定義執行緒函式
def thread_scratch(url, rnum_perpage, page):
url_set = []
try:
request = urllib2.Request(url, None, {'Referer': 'http://www.sina.com'})
response = urllib2.urlopen(request)
# Process the JSON string.
results = simplejson.load(response)
info = results['responseData']['results']
except Exception,e:
print 'error occured'
print e
else:
for minfo in info:
url_set.append(minfo['url'])
print minfo['url']
#處理連結
i = 0
for u in url_set:
try:
request_url = urllib2.Request(u, None, {'Referer': 'http://www.sina.com'})
request_url.add_header(
'User-agent',
'CSC'
)
response_data = urllib2.urlopen(request_url).read()
#過濾檔案
#content_data = html_filter.filter_tags(response_data)
#寫入檔案
filenum = i+page
filename = dir_name+'/related_html_'+str(filenum)
print ' write start: related_html_'+str(filenum)
f = open(filename, 'w+', -1)
f.write(response_data)
#print content_data
f.close()
print ' write down: related_html_'+str(filenum)
except Exception, e:
print 'error occured 2'
print e
i = i+1
return
#建立資料夾
dir_name = 'related_html_'+urllib.quote(keywords)
if os.path.exists(dir_name):
print 'exists file'
common.delete_dir_or_file(dir_name)
os.makedirs(dir_name)
#抓取網頁
print 'start to scratch web pages:'
for x in range(pages):
print "page:%s"%(x+1)
page = x * rnum_perpage
url = ('https://ajax.googleapis.com/ajax/services/search/web'
'?v=1.0&q=%s&rsz=%s&start=%s') % (urllib.quote(keywords), rnum_perpage,page)
print url
t = threading.Thread(target=thread_scratch, args=(url,rnum_perpage, page))
t.start()
#主執行緒等待子執行緒抓取完
main_thread = threading.currentThread()
for t in threading.enumerate():
if t is main_thread:
continue
t.join()