快捷導(dǎo)航

python3實(shí)現(xiàn)抓取網(wǎng)頁(yè)資源的 N 種方法

更新時(shí)間：2017年05月02日 14:21:54 作者：方倍工作室

這兩天學(xué)習(xí)了python3實(shí)現(xiàn)抓取網(wǎng)頁(yè)資源的方法，發(fā)現(xiàn)了很多種方法，所以，今天添加一點(diǎn)小筆記。

1、最簡(jiǎn)單

import urllib.request
response = urllib.request.urlopen('http://python.org/')
html = response.read()

2、使用 Request

import urllib.request
 
req = urllib.request.Request('http://python.org/')
response = urllib.request.urlopen(req)
the_page = response.read()

3、發(fā)送數(shù)據(jù)

#! /usr/bin/env python3
 
import urllib.parse
import urllib.request
 
url = 'http://localhost/login.php'
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
values = {
     'act' : 'login',
     'login[email]' : 'yzhang@i9i8.com',
     'login[password]' : '123456'
     }
 
data = urllib.parse.urlencode(values)
req = urllib.request.Request(url, data)
req.add_header('Referer', 'http://www.python.org/')
response = urllib.request.urlopen(req)
the_page = response.read()
 
print(the_page.decode("utf8"))

4、發(fā)送數(shù)據(jù)和header

#! /usr/bin/env python3
 
import urllib.parse
import urllib.request
 
url = 'http://localhost/login.php'
user_agent = 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)'
values = {
     'act' : 'login',
     'login[email]' : 'yzhang@i9i8.com',
     'login[password]' : '123456'
     }
headers = { 'User-Agent' : user_agent }
 
data = urllib.parse.urlencode(values)
req = urllib.request.Request(url, data, headers)
response = urllib.request.urlopen(req)
the_page = response.read()
 
print(the_page.decode("utf8"))

5、http 錯(cuò)誤

#! /usr/bin/env python3
 
import urllib.request
 
req = urllib.request.Request('http://www.python.org/fish.html')
try:
  urllib.request.urlopen(req)
except urllib.error.HTTPError as e:
  print(e.code)
  print(e.read().decode("utf8"))

6、異常處理1

#! /usr/bin/env python3
 
from urllib.request import Request, urlopen
from urllib.error import URLError, HTTPError
req = Request("http://twitter.com/")
try:
  response = urlopen(req)
except HTTPError as e:
  print('The server couldn\'t fulfill the request.')
  print('Error code: ', e.code)
except URLError as e:
  print('We failed to reach a server.')
  print('Reason: ', e.reason)
else:
  print("good!")
  print(response.read().decode("utf8"))

7、異常處理2

#! /usr/bin/env python3
 
from urllib.request import Request, urlopen
from urllib.error import URLError
req = Request("http://twitter.com/")
try:
  response = urlopen(req)
except URLError as e:
  if hasattr(e, 'reason'):
    print('We failed to reach a server.')
    print('Reason: ', e.reason)
  elif hasattr(e, 'code'):
    print('The server couldn\'t fulfill the request.')
    print('Error code: ', e.code)
else:
  print("good!")
  print(response.read().decode("utf8"))

8、HTTP 認(rèn)證

#! /usr/bin/env python3
 
import urllib.request
 
# create a password manager
password_mgr = urllib.request.HTTPPasswordMgrWithDefaultRealm()
 
# Add the username and password.
# If we knew the realm, we could use it instead of None.
top_level_url = "https://cms.tetx.com/"
password_mgr.add_password(None, top_level_url, 'yzhang', 'cccddd')
 
handler = urllib.request.HTTPBasicAuthHandler(password_mgr)
 
# create "opener" (OpenerDirector instance)
opener = urllib.request.build_opener(handler)
 
# use the opener to fetch a URL
a_url = "https://cms.tetx.com/"
x = opener.open(a_url)
print(x.read())
 
# Install the opener.
# Now all calls to urllib.request.urlopen use our opener.
urllib.request.install_opener(opener)
 
a = urllib.request.urlopen(a_url).read().decode('utf8')
print(a)

9、使用代理

#! /usr/bin/env python3
 
import urllib.request
 
proxy_support = urllib.request.ProxyHandler({'sock5': 'localhost:1080'})
opener = urllib.request.build_opener(proxy_support)
urllib.request.install_opener(opener)

 
a = urllib.request.urlopen("http://g.cn").read().decode("utf8")
print(a)

10、超時(shí)

#! /usr/bin/env python3
 
import socket
import urllib.request
 
# timeout in seconds
timeout = 2
socket.setdefaulttimeout(timeout)
 
# this call to urllib.request.urlopen now uses the default timeout
# we have set in the socket module
req = urllib.request.Request('http://twitter.com/')
a = urllib.request.urlopen(req).read()
print(a)

以上就是本文的全部?jī)?nèi)容，希望對(duì)大家的學(xué)習(xí)有所幫助，也希望大家多多支持腳本之家。

您可能感興趣的文章: