使用Python的urllib和urllib2模块制作爬虫的实例教程

'''
@ urllib为python自带的一个网络库
@ urlopen为urllib的一个方法,用于打开一个连接并抓取网页,
 然后通过read()方法把值赋给read()
'''
import urllib

url = "http://www.lifevc.com"#多嘴两句,为什么要选lifevc呢,主要是最近它很惹我.
html = urllib.urlopen(url)
content = html.read()
html.close()
#可以通过print打印出网页内容
print content

<img class="BDE_Image" src="http://imgsrc.baidu.com/forum/w%3D580/
sign=3d5aacaab21c8701d6b6b2ee177e9e6e/17a6d439b6003af329aece2e342ac65c1138b6d8.
jpg" height="840" width="560" style="cursor: url(http://tb2.bdstatic.com/tb/
static-pb/img/cur_zin.cur), pointer;">

'''
@本程序用来下载百度贴吧图片
@re 为正则说明库
'''
import urllib
import re

# 获取网页html信息
url = "http://tieba.baidu.com/p/2336739808"
html = urllib.urlopen(url)
content = html.read()
html.close()

# 通过正则匹配图片特征,并获取图片链接
img_tag = re.compile(r'class="BDE_Image" src="(.+?\.jpg)"')
img_links = re.findall(img_tag, content)

# 下载图片 img_counter为图片计数器(文件名)
img_counter = 0
for img_link in img_links:
  img_name = '%s.jpg' % img_counter
  urllib.urlretrieve(img_link, "//Users//Sean//Downloads//tieba//%s" %img_name)
  img_counter += 1

'''
@本程序用来抓取blog.csdn.net网页
'''
import urllib

url = "http://blog.csdn.net/FansUnion"
html = urllib.urlopen(url)
#getcode()方法为返回Http状态码
print html.getcode()
html.close()
#输出

403

Request Method:GET
Host:blog.csdn.net
Referer:http://blog.csdn.net/?ref=toolbar_logo
User-Agent:Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/38.0.2125.104 Safari/537.36

# coding=utf-8
'''
@本程序用来抓取受限网页(blog.csdn.net)
@User-Agent:客户端浏览器版本
@Host:服务器地址
@Referer:跳转地址
@GET:请求方法为GET
'''
import urllib2

url = "http://blog.csdn.net/FansUnion"

#定制自定义Header,模拟浏览器向服务器提交请求
req = urllib2.Request(url)
req.add_header('User-Agent', 'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36')
req.add_header('Host', 'blog.csdn.net')
req.add_header('Referer', 'http://blog.csdn.net')
req.add_header('GET', url)

#下载网页html并打印
html = urllib2.urlopen(req)
content = html.read()
print content
html.close()

#input:
help(urllib2.Request)
#output(因篇幅关系,只取__init__方法)
__init__(self, url, data=None, headers={}, origin_req_host=None, unverifiable=False)
通过观察,我们发现headers={},就是说可以以字典的方式提交header信息.那就动手试试咯!!

#只取自定义Header部分代码
csdn_headers = {
  "User-Agent": "Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/39.0.2171.95 Safari/537.36",
  "Host": "blog.csdn.net",
  'Referer': 'http://blog.csdn.net',
  "GET": url
  }
req = urllib2.Request(url,headers=csdn_headers)

'''
@本程序是用来动态提交Header信息
@random 动态库,详情请参考<https://docs.python.org/2/library/random.html>
'''

# coding=utf-8
import urllib2
import random

url = 'http://www.lifevc.com/'

my_headers = [
  'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; .NET CLR 3.0.04506.30; .NET CLR 3.0.04506.648)',
  'Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 5.1; Trident/4.0; .NET CLR 2.0.50727; InfoPath.1',
  'Mozilla/4.0 (compatible; GoogleToolbar 5.0.2124.2070; Windows 6.0; MSIE 8.0.6001.18241)',
  'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0)',
  'Mozilla/5.0 (compatible; MSIE 9.0; Windows NT 6.1; WOW64; Trident/5.0; Sleipnir/2.9.8)',
  #因篇幅关系,此处省略N条
]

random_header = random.choice(headers)
# 可以通过print random_header查看提交的header信息
req = urllib2.Request(url)
req.add_header("User-Agent", random_header)
req.add_header('Host', 'blog.csdn.net')
req.add_header('Referer', 'http://blog.csdn.net')
req.add_header('GET', url)
content = urllib2.urlopen(req).read()
print content