Urllib库
"""
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
urllib.robotparser robots.txt 解析模块
"""
import urllib2
response = urllib2.urlopen('http://www.baidu.com')
import urllib.request
resp = urllib.request.urlopen('http://www.baidu.com')
urllib的请求
import urllib.request
resp = urllib.request.urlopen('http://www.baidu.com')
print(resp.read().decode("utf-8"))
import urllib.parse
import urllib.request
data = bytes(urllib.parse.urlencode({"world":"hello"}),encoding="utf8")
response = urllib.request.urlopen("http://httpbin.org/get",data=data)
print(response.read())
import urllib.request
resp = urllib.request.urlopen('http://httpbin.org/get',timeout=1)
print(resp.read().decode("utf-8"))
import socket
import urllib.request
import urllib.error
try:
resp = 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")
urllib 响应
import urllib.request
resp = urllib.request.urlopen('http://httpbin.org/get',timeout=1)
print(resp.status)
print(resp.getheaders())
print(resp.getheader("server"))
print(response.read()decode("utf8"))
更为复杂的请求
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'))
设置代理
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())
cookie
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'))
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='\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')
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)
"""
<class 'urllib.parse.ParseResult'>
ParseResult(scheme='http', netloc='www.baidu.com', path='/index.html', params='user', query='id=5', fragment='comment')
协议类型 域名 地址
params='user'这个不常用到,
query='id=5'
fragment='comment'
#fragment: 片段ID
该部分与上面的?后面的表单信息本质的区别就是这部分内容不会被传递到服务器端。一般用于页面的锚。就是我们常见的网站右下脚一般有一个回到顶部的按钮,一般就是使用其实现的。
"""
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
"""
与 urlparse是反函数
urlparse是拆分,urlunparse则是拼接的
"""
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'))
"""
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)