urllib库解析

Posted 2021-03-01 dengschoo

tags:

篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了urllib库解析相关的知识，希望对你有一定的参考价值。

Urllib库详解

什么是Urllib：

Python内置的HTTP请求库

urllib.request 请求模块
urllib.error 异常处理模块
urllib.parse url 解析模块

urlopen

urllib.request.urlopen(url, data=None, [timeout, ]*, cafile=None, capath=None, cadefault=False, context=None)

url 传入url
data 用于POST提交数据
timeout 设置最大响应接受时间

import urllib.request

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

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())

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‘)

响应

响应类型

import urllib.request

response = urllib.request.urlopen(‘https://www.python.org‘)
print(type(response))

状态码、响应头

import urllib.request

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

import urllib.request

response = urllib.request.urlopen(‘https://www.python.org‘)
print(response.read().decode(‘utf-8‘))

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‘))

输出：
{
  "args": {}, 
  "data": "", 
  "files": {}, 
  "form": {
    "name": "Germey"
  }, 
  "headers": {
    "Accept-Encoding": "identity", 
    "Connect-Time": "1", 
    "Connection": "close", 
    "Content-Length": "11", 
    "Content-Type": "application/x-www-form-urlencoded", 
    "Host": "httpbin.org", 
    "Total-Route-Time": "0", 
    "User-Agent": "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)", 
    "Via": "1.1 vegur", 
    "X-Request-Id": "f96e736e-0b8a-4ab4-9dcc-a970fcd2fbbf"
  }, 
  "json": null, 
  "origin": "219.238.82.169", 
  "url": "http://httpbin.org/post"
}

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‘))

输出：
{
  "args": {}, 
  "data": "", 
  "files": {}, 
  "form": {
    "name": "Germey"
  }, 
  "headers": {
    "Accept-Encoding": "identity", 
    "Connect-Time": "0", 
    "Connection": "close", 
    "Content-Length": "11", 
    "Content-Type": "application/x-www-form-urlencoded", 
    "Host": "httpbin.org", 
    "Total-Route-Time": "0", 
    "User-Agent": "Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)", 
    "Via": "1.1 vegur", 
    "X-Request-Id": "a624bcaa-3581-4b93-84b0-037940338e71"
  }, 
  "json": null, 
  "origin": "219.238.82.169", 
  "url": "http://httpbin.org/post"
}

Handler

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())

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)

输出：
BAIDUID=E77BF84491E332F6F8F1D451AD0063D3:FG=1
BIDUPSID=E77BF84491E332F6F8F1D451AD0063D3
H_PS_PSSID=1466_21127_22075
PSTM=1490198051
BDSVRTM=0
BD_HOME=0

把cookie保存到文件中

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)

从cookie保存文件中读取cookie信息

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‘))

异常处理

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=‘
‘)
except error.URLError as e:
    print(e.reason)
else:
    print(‘Request Successfully‘)

输出：
Not Found
404
Server: nginx/1.10.1
Date: Wed, 22 Mar 2017 15:59:55 GMT
Content-Type: text/html; charset=UTF-8
Transfer-Encoding: chunked
Connection: close
Vary: Cookie
Expires: Wed, 11 Jan 1984 05:00:00 GMT
Cache-Control: no-cache, must-revalidate, max-age=0
Link: <http://cuiqingcai.com/wp-json/>; rel="https://api.w.org/"

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‘)

<class ‘socket.timeout‘>
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)

输出：
<class ‘urllib.parse.ParseResult‘> ParseResult(scheme=‘http‘, netloc=‘www.baidu.com‘, path=‘/index.html‘, params=‘user‘, query=‘id=5‘, fragment=‘comment‘)

from urllib.parse import urlparse

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

输出：
ParseResult(scheme=‘https‘, netloc=‘‘, path=‘www.baidu.com/index.html‘, params=‘user‘, query=‘id=5‘, fragment=‘comment‘)

from urllib.parse import urlparse

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

输出：
ParseResult(scheme=‘http‘, netloc=‘www.baidu.com‘, path=‘/index.html‘, params=‘user‘, query=‘id=5#comment‘, fragment=‘‘)

from urllib.parse import urlparse

result = urlparse(‘http://www.baidu.com/index.html#comment‘, allow_fragments=False)
print(result)

输出：
ParseResult(scheme=‘http‘, netloc=‘www.baidu.com‘, path=‘/index.html#comment‘, params=‘‘, query=‘‘, fragment=‘‘)

urlunparse

from urllib.parse import urlunparse

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

输出：
http://www.baidu.com/index.html;user?a=6#comment

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‘))

输出：
http://www.baidu.com/FAQ.html
https://cuiqingcai.com/FAQ.html
https://cuiqingcai.com/FAQ.html
https://cuiqingcai.com/FAQ.html?question=2
https://cuiqingcai.com/index.php
http://www.baidu.com?category=2#comment
www.baidu.com?category=2#comment
www.baidu.com?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)

输出：
http://www.baidu.com?name=germey&age=22

以上是关于urllib库解析的主要内容，如果未能解决你的问题，请参考以下文章

Urllib库基本使用详解（爬虫，urlopen，request，代理ip的使用，cookie解析，异常处理，URL深入解析）

python爬虫 urllib库基本使用

urllib库:解析链接

Python-urllib库parse模块解析链接常用方法

爬虫：Urllib库详解

python爬虫---从零开始Urllib库