urllib的各种方法

import urllib.request

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‘: ‘zhaofan‘
}
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‘))   #decode可以将结果格式化显示

import urllib.request

proxy_handler = urllib.request.ProxyHandler({
    ‘http‘: ‘http://127.0.0.1:9743‘,   # 访问哪个网站格式http，https选用其中对应的一哥
    ‘https‘: ‘https://127.0.0.1:9743‘
})
opener = urllib.request.build_opener(proxy_handler)
response = opener.open(‘http://httpbin.org/get‘)
print(response.read())

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‘))

from urllib import request,error

try:
    response = request.urlopen("http://pythonsite.com/1111.html")
except error.URLError as e:
    print(e.reason)

from urllib import request,error
try:
    response = request.urlopen("http://pythonsite.com/1111.html")
except error.HTTPError as e:
    print(e.reason, "error.HTTPError")
    print(e.code, "error.HTTPError")
    print(e.headers, "error.HTTPError")
except error.URLError as e:
    print(e.reason,"error.URLError")

else:
    print("reqeust successfully")

import socket

from urllib import error,request

try:
    response = request.urlopen("http://www.pythonsite.com/",timeout=0.001)  # 时间太短了
except error.URLError as e:
    print(type(e.reason))
    if isinstance(e.reason,socket.timeout):
        print("time out")

from urllib.parse import urlparse

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

from urllib.parse import urlunparse

data = [‘http‘,‘www.baidu.com‘,‘index.html‘,‘user‘,‘a=123‘,‘commit‘]
print(urlunparse(data))  #输出http://www.baidu.com/index.html;user?a=123#commit

from urllib.parse import urljoin

# print(urljoin(‘http://www.baidu.com‘, ‘FAQ.html‘))
print(urljoin(‘http://www.baidu.com‘, ‘https://pythonsite.com/FAQ.html‘))
print(urljoin(‘http://www.baidu.com/about.html‘, ‘https://pythonsite.com/FAQ.html‘))
print(urljoin(‘http://www.baidu.com/about.html‘, ‘https://pythonsite.com/FAQ.html?question=2‘))
print(urljoin(‘http://www.baidu.com?wd=abc‘, ‘https://pythonsite.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‘))

from urllib.parse import urlencode

params = {
    "name":"zhaofan",
    "age":23,
}
base_url = "http://www.baidu.com?"

url = base_url+urlencode(params)
print(url)   # 输出结果为http://www.baidu.com?name=zhaofan&age=23