1. [代码]最基本的抓站
|
1
2
|
import urllib2
content = urllib2.urlopen('http://XXXX').read()
|
2. [代码]使用代理服务器
|
1
2
3
4
5
|
import urllib2
proxy_support = urllib2.ProxyHandler({'http':'http://XX.XX.XX.XX:XXXX'})
opener = urllib2.build_opener(proxy_support, urllib2.HTTPHandler)
urllib2.install_opener(opener)content = urllib2.urlopen('http://XXXX').read()
|
3. [代码]需要登录的情况：
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
|
#1 cookie的处理import urllib2, cookielib
cookie_support= urllib2.HTTPCookieProcessor(cookielib.CookieJar())
opener = urllib2.build_opener(cookie_support, urllib2.HTTPHandler)
urllib2.install_opener(opener)content = urllib2.urlopen('http://XXXX').read()
#2 用代理和cookieopener = urllib2.build_opener(proxy_support, cookie_support, urllib2.HTTPHandler)
#3 表单的处理import urllib
postdata=urllib.urlencode({
'username':'XXXXX',
'password':'XXXXX',
'continueURI':'http://www.verycd.com/',
'fk':fk,
'login_submit':'登录'
})req = urllib2.Request(
url = 'http://secure.verycd.com/signin/*/http://www.verycd.com/',
data = postdata
)result = urllib2.urlopen(req).read()
#4 伪装成浏览器访问headers = {
'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'
}req = urllib2.Request(
url = 'http://secure.verycd.com/signin/*/http://www.verycd.com/',
data = postdata,
headers = headers
)#5 反”反盗链”headers = {
'Referer':'http://www.cnbeta.com/articles'
} |
4. [代码]多线程并发抓取
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
|
from threading import Thread
from Queue import Queue
from time import sleep
#q是任务队列#NUM是并发线程总数#JOBS是有多少任务q = Queue()
NUM = 2
JOBS = 10
#具体的处理函数，负责处理单个任务def do_somthing_using(arguments):
print arguments
#这个是工作进程，负责不断从队列取数据并处理def working():
while True:
arguments = q.get()
do_somthing_using(arguments)
sleep(1)
q.task_done()
#fork NUM个线程等待队列for i in range(NUM):
t = Thread(target=working)
t.setDaemon(True)
t.start()
#把JOBS排入队列for i in range(JOBS):
q.put(i)
#等待所有JOBS完成q.join() |