Urllib库基本使用

Urllib库基本使用

1 模块

• urllib.request—————— 请求模块
• urllib.error ——————— 异常处理模块
• urllib.parse——————— url解析模块
• urllib.robotparser———— robots.txt解析模块

2 urlopen

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

2.1 Get请求

import urllib.request

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

2.2 Post请求

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().decode('utf-8'))

2.3 超时设置

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')

- response.read()类型是byte
- response.read().decode(‘utf-8’) 类型是 str

3 响应的属性/方法

print(response.status)
print(response.getheaders())
print(response.getheader('Server'))
response.read()                     #类型是byte
response.read().decode('utf-8')     #类型是str

4 Request

4.1 Get请求

import urllib.request

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

4.2 Post请求

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'))

4.3 添加请求头

import urllib.request

headers = {
    'User-Agent': 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)',
    'Host': 'httpbin.org'
}
request = urllib.request.Request('http://www.httpbin.org/get',headers=headers)
# request.add_header('User-Agent', 'Mozilla/4.0 (compatible; MSIE 5.5; Windows NT)')
response = urllib.request.urlopen(request)
print(response.read().decode('utf-8'))

5 代理IP

import urllib.request

proxy_handler = urllib.request.ProxyHandler({
    'http': 'https://182.34.20.72:808',
    'https': 'http://182.34.20.72:808'
})
opener = urllib.request.build_opener(proxy_handler)
response = opener.open('http://httpbin.org/get')
print(response.read().decode('utf-8'))

6 Cookie

6.1 获取Cookie

import http.cookiejar
import 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)

6.2 保存Cookie

import http.cookiejar
import urllib.request

cookie = http.cookiejar.MozillaCookieJar("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)

6.3 读取Cookie

import http.cookiejar, urllib.request

cookie = http.cookiejar.MozillaCookieJar()
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'))

7 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)

8 urlparse

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

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

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

ParseResult(scheme=’https’, netloc=”, path=’www.baidu.com/index.html’, params=’user’, query=’id=5’, fragment=’comment’)
result = urllib.parse.urlparse(‘http://www.baidu.com/index.html;user?id=5#comment‘, scheme=’https’)

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

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

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

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

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

9 urlunparse

from urllib.parse import urlunparse

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

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

10 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'))

- 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

11 urlencode

例1

from urllib.parse import urlencode

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

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

例2

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().decode('utf-8'))