'''
@ urllib為python自帶的一個網絡庫
@ urlopen為urllib的一個方法,用于打開一個連接并抓取網頁,
 然后通過read()方法把值賦給read()
'''
import urllib

url = "http://www.lifevc.com"#多嘴兩句,為什么要選lifevc呢,主要是最近它很惹我.
html = urllib.urlopen(url)
content = html.read()
html.close()
#可以通過print打印出網頁內容
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;">

'''
@本程序用來下載百度貼吧圖片
@re 為正則說明庫
'''
import urllib
import re

# 獲取網頁html信息
url = "http://tieba.baidu.com/p/2336739808"
html = urllib.urlopen(url)
content = html.read()
html.close()

# 通過正則匹配圖片特征,并獲取圖片鏈接
img_tag = re.compile(r'class="BDE_Image" src="(.+?\.jpg)"')
img_links = re.findall(img_tag, content)

# 下載圖片 img_counter為圖片計數器(文件名)
img_counter = 0
for img_link in img_links:
  img_name = '%s.jpg' % img_counter
  urllib.urlretrieve(img_link, "http://Users//Sean//Downloads//tieba//%s" %img_name)
  img_counter += 1

'''
@本程序用來抓取blog.csdn.net網頁
'''
import urllib

url = "http://blog.csdn.net/FansUnion"
html = urllib.urlopen(url)
#getcode()方法為返回Http狀態(tài)碼
print html.getcode()
html.close()
#輸出

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
'''
@本程序用來抓取受限網頁(blog.csdn.net)
@User-Agent:客戶端瀏覽器版本
@Host:服務器地址
@Referer:跳轉地址
@GET:請求方法為GET
'''
import urllib2

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

#定制自定義Header,模擬瀏覽器向服務器提交請求
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)

#下載網頁html并打印
html = urllib2.urlopen(req)
content = html.read()
print content
html.close()

#input:
help(urllib2.Request)
#output(因篇幅關系,只取__init__方法)
__init__(self, url, data=None, headers={}, origin_req_host=None, unverifiable=False)
通過觀察,我們發(fā)現(xiàn)headers={},就是說可以以字典的方式提交header信息.那就動手試試咯!!

#只取自定義Header部分代碼
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)

'''
@本程序是用來動態(tài)提交Header信息
@random 動態(tài)庫,詳情請參考<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)',
  #因篇幅關系,此處省略N條
]

random_header = random.choice(headers)
# 可以通過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