簡介

Python內建的HTTP請求庫

• urllib.request 請求模組
• urllib.error 異常處理模組
• urllib.parse url 解析模組
• urllib.robotparser robots.txt解析模組

urlopen

• 功能：給伺服器傳送request請求

urllib.request.urlopen

(url,data=None,[timeout,]*,cafile=None,capath=None,cadefault=False,contex=None)

• 引數
  • data post所帶引數
  • ca* ca證書有關

請求網頁原始碼（GET）

import urllib.request
response = urllib.request.urlopen('http://www.baidu.com')
print(response.read().decode('utf-8'))

請求網頁（POST）

import urllib.parse
import urllib.request
data = bytes(urllib.parse.urlencode({'word':'hello'}),encoding='utf8')
response = urllib.
 
request.urlopen('http://httpbin.org/post',data=data)
print(response.read())

http測試網：http://httpbin.org

超時設定

import urllib.request
response = urllib.request.urlopen('http://httpbin.org/get', timeout=1)
print(response.read())

異常處理

import socket
import urllib.request
import urllib.error

try
 
:
    response = urllib.request.urlopen('http://httpbin.org/get', timeout=0.1)
except urllib.error.URLError as e:
    if isinstance(e.reason,socket.timeout):
        print('TIME OUT')

響應

• 響應型別

  import urllib.request
  response = urllib.request.urlopen('http://www.python.org')
  print(type(response))
  

• 狀態碼、響應頭

  import urllib.request
  response = urllib.request.urlopen('http://www.python.org')
  print(response.status)
  print(response.getheaders())
  print(response.getheader('Server'))
  

Request

• 增加傳入方式

import urllib.request
request = urllib.request.Request('http://www.python.org')
response = urllib.request.urlopen(request)
print(response.read().decode('utf-8'))

from urllib import request, parse
url = 'http://httpbin.org/post'
headers = {
    'User-Agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)',
    'Host': 'httpbin.org'
}
dict = {
    'name': 'Germey'
}
data = bytes(parse.urlencode(dict), encoding='utf8')
req = request.Request(url=url, data=data, headers=headers, method='POST')
response = request.urlopen(req)
print(response.read().decode('utf-8'))

from urllib import request, parse
url = 'http://httpbin.org/post'
dict = {
    'name': 'Germey'
}
data = bytes(parse.urlencode(dict), encoding='utf8')
req = request.Request(url=url, data=data, method='POST')
req.add_header('User-Agent', 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)')
response = request.urlopen(req)
print(response.read().decode('utf-8'))

Handler

代理

• 偽裝IP地址

import urllib.request
proxy_handler = urllib.request.ProxyHandler({
    'http': 'http://127.0.0.1:9743',
    'https': 'https://127.0.0.1:9743'
})
opener = urllib.request.build_opener(proxy_handler)
response = opener.open('http://httpbin.org/get')
print(response.read())

Cookie

• 客戶端儲存使用者資訊，維持登入狀態

import http.cookiejar, urllib.request
cookie = http.cookiejar.CookieJar()
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
for item in cookie:
    print(item.name+"="+item.value)

import http.cookiejar, urllib.request
filename = "cookie.txt"
cookie = http.cookiejar.MozillaCookieJar(filename)
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
cookie.save(ignore_discard=True, ignore_expires=True)

import http.cookiejar, urllib.request
filename = 'cookie.txt'
cookie = http.cookiejar.LWPCookieJar(filename)
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
cookie.save(ignore_discard=True, ignore_expires=True)

import http.cookiejar, urllib.request
cookie = http.cookiejar.LWPCookieJar()
cookie.load('cookie.txt', ignore_discard=True, ignore_expires=True)
handler = urllib.request.HTTPCookieProcessor(cookie)
opener = urllib.request.build_opener(handler)
response = opener.open('http://www.baidu.com')
print(response.read().decode('utf-8'))

異常處理

from urllib import request, error
try:
    response = request.urlopen('http://cuiqingcai.com/index.htm')
except error.URLError as e:
    print(e.reason)

from urllib import request, error
try:
    response = request.urlopen('http://cuiqingcai.com/index.htm')
except error.HTTPError as e:
    print(e.reason, e.code, e.headers, sep='\n')
except error.URLError as e:
    print(e.reason)
else:
    print('Request Successfully')

import socket
import urllib.request
import urllib.error
try:
    response = urllib.request.urlopen('https://www.baidu.com', timeout=0.01)
except urllib.error.URLError as e:
    print(type(e.reason))
    if isinstance(e.reason, socket.timeout):
        print('TIME OUT')

URL解析

urlparse

urllib.parse.urlparse(urlstring, scheme='', allow_fragments=True)

from urllib.parse import urlparse
result = urlparse('http://www.baidu.com/index.html;user?id=5#comment')
print(type(result), result)

from urllib.parse import urlparse
result = urlparse('www.baidu.com/index.html;user?id=5#comment', scheme='https')
print(result)

from urllib.parse import urlparse
result = urlparse('http://www.baidu.com/index.html;user?id=5#comment', scheme='https')
print(result)

from urllib.parse import urlparse
result = urlparse('http://www.baidu.com/index.html;user?id=5#comment', allow_fragments=False)
print(result)

from urllib.parse import urlparse
result = urlparse('http://www.baidu.com/index.html#comment', allow_fragments=False)
print(result)

urlunparse

from urllib.parse import urlunparse
data = ['http', 'www.baidu.com', 'index.html', 'user', 'a=6', 'comment']
print(urlunparse(data))

urljoin

from urllib.parse import urljoin
print(urljoin('http://www.baidu.com', 'FAQ.html'))
print(urljoin('http://www.baidu.com', 'https://cuiqingcai.com/FAQ.html'))
print(urljoin('http://www.baidu.com/about.html', 'https://cuiqingcai.com/FAQ.html'))
print(urljoin('http://www.baidu.com/about.html', 'https://cuiqingcai.com/FAQ.html?question=2'))
print(urljoin('http://www.baidu.com?wd=abc', 'https://cuiqingcai.com/index.php'))
print(urljoin('http://www.baidu.com', '?category=2#comment'))
print(urljoin('www.baidu.com', '?category=2#comment'))
print(urljoin('www.baidu.com#comment', '?category=2'))

urlencode

from urllib.parse import urlencode
params = {
    'name': 'germey',
    'age': 22
}
base_url = 'http://www.baidu.com?'
url = base_url + urlencode(params)
print(url)

urllib庫官方說明文件