Urllib小結

Urllib
一、基礎用法
import urllib.request

response = urllib.request.urlopen('http://www.baidu.com')
print(response.read().decode('utf-8'))
# 輸出百度的網頁內容

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())
# 添加文件內容

二、響應
1.響應類型
import urllib.request

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

2.request
import urllib.request

request = urllib.request.Request('https://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'))
# 添加文件頭信息

三、Handler
1.代理
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())

2.cookies
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)
存儲cookie-->使用cookiejar
使用cookie-->build_opener不能直接用cookie（opener）

3.寫入文件
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)


四、異常處理
from urllib import request, error

try:
    response = request.urlopen('http://cuiqingcai.com/index.htm')
except error.HTTPError as e:
    print(  e.headers,e.code,e.reason, sep='\n')
except error.URLError as e:
    print(e.reason)
else:
    print('Request Successfully')
#  e.headers,e.code,e.reason, sep='\n'
# 文件頭信息、返回響應碼、異常原因。以換行符分割

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')

五、URL解析
1.urlparse
from urllib.parse import urlparse

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

2.urlunparse
from urllib.parse import urlunparse

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

3.urlencode
from urllib.parse import urlencode

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