本节主要内容:
掌握python多线程下载文件的方法
代码:
#!/bin/python
#
#site: www.jb200.com
import httplib
import urllib2
import time
from threading import Thread
from Queue import Queue
from time import sleep
proxy = 'your proxy';
opener = urllib2.build_opener( urllib2.ProxyHandler({'http':proxy}) )
urllib2.install_opener( opener )
ids = {};
for i in range(1,110):
try:
listUrl = "http://www.jb200.com/sort/list_8_%d.shtml" % (i);
print listUrl;
page = urllib2.urlopen(listUrl).read();
speUrl = "http://www.jb200.com/soft/";
speUrlLen = len(speUrl);
idx = page.find(speUrl,0);
while idx!=-1:
dotIdx = page.find(".",idx + speUrlLen);
if dotIdx != -1:
id = page[idx + speUrlLen:dotIdx];
ids[id] = 1;
idx = page.find("http://www.jb200.com/soft/",idx + speUrlLen);
except:
pass;
q = Queue()
NUM = 5
failedId = [];
def do_somthing_using(id):
try:
url = "http://www.jb200.com/download.php?softid=%s&type=dx" % (id);
h2 = httplib.HTTPConnection("your proxy", "you port");
h2.request("HEAD", url);
resp = h2.getresponse();
header = resp.getheaders();
location = header[3][1];
sContent = urllib2.urlopen(location).read();
savePath = "C:someweb%s.rar" % (id);
file=open(savePath,'wb');
file.write(sContent);
file.close();
print savePath + " saved";
except:
pass;
def working():
while True:
arguments = q.get()
do_somthing_using(arguments)
sleep(1)
q.task_done()
for i in range(NUM):
t = Thread(target=working)
t.setDaemon(True)
t.start()
for id in ids:
q.put(id)
q.join()