爬虫--Urllib库详解

1、什么是Urllib?

2、相比Python2的变化

3、用法讲解

(1)urlopen

urlllb.request.urlopen(url,data=None[timeout,],cahle=None,capath=None,cadefault=False,context=None)
#第一个参数为url网址，第二个参数为额外的数据，第三个参数为超时的设置，剩下的参数暂时用不到
######### GET 类型的请求 #############
import urllib.request
response =urllib.request.urlopen("http://ww.baidu.com")
print(response.read().decode("utf-8")
<!DOCTYPE html>
<!--STATUS OK-->

·······················

······················

·····················

<script>
if(navigator.cookieEnabled){
document.cookie="NOJS=;expires=Sat, 01 Jan 2000 00:00:00 GMT";
}
</script>

</body>
</html>
打印的结果为：
######### POST 类型的请求 #############
import urllib.request
import urllib.parse

data=bytes(urllib.parse.urlencode({'word':'hello'}),encoding='utf8')
response=urllib.request.urlopen("http://httpbin.org/post",data=data) # http://httpbin.org/post  HTTP测试的网址
print(response.read())
b'{\n  "args": {}, \n  "data": "", \n  "files": {}, \n  "form": {\n    "word": "hello"\n  }, \n  "headers": {\n    "Accept-Encoding": "identity", \n    "Connection": "close", \n    "Content-Length": "10", \n    "Content-Type": "application/x-www-form-urlencoded", \n    "Host": "httpbin.org", \n    "User-Agent": "Python-urllib/3.5"\n  }, \n  "json": null, \n  "origin": "221.208.253.76", \n  "url": "http://httpbin.org/post"\n}\n'
打印的结果为：
import urllib.request
############### 超时的设置 ###############
response=urllib.request.urlopen("http://httpbin.org/get",timeout=1) # 设置一个超时的时间，在规定的时间没有响应，则抛出异常
print(response.read()) 
b'{\n "args": {}, \n "headers": {\n "Accept-Encoding": "identity", \n "Connection": "close", \n "Host": "httpbin.org", \n "User-Agent": "Python-urllib/3.5"\n }, \n "origin": "221.208.253.76", \n "url": "http://httpbin.org/get"\n}\n'
打印的结果为：
import urllib.request
import urllib.error
import socket

############### 超时的设置,超出响应时间 ###############

try:
    response = urllib.request.urlopen('htp://httpbin.org/get', timeout=0.1)
except urllib.error.URLError as e:
    if isinstance(e.reason,socket.timeout):
        print("Time out")
 Time out
打印的结果为：

 (2)响应

 响应类型

import urllib.request
response=urllib.request.urlopen('https://www.python.org')
print(type(response))
<class 'http.client.HTTPResponse'>
打印的结果为：

状态码、响应头

import urllib.request
response =urllib.request.urlopen('https://www.python.org')
print(response.status) # 获取状态码
print(response.getheaders) # 获取响应头
print(response.getheader('Server'))
200
<bound method HTTPResponse.getheaders of <http.client.HTTPResponse object at 0x0000000002D04EB8>>
nginx
打印的结果为：

(3)request

import urllib.request
request=urllib.request.Request("https://python.org")
response=urllib.request.urlopen(request)
print(response.read().decode("utf-8"))
<!doctype html>
<!--[if lt IE 7]> <html class="no-js ie6 lt-ie7 lt-ie8 lt-ie9"> <![endif]-->
<!--[if IE 7]> <html class="no-js ie7 lt-ie8 lt-ie9"> <![endif]-->
<!--[if IE 8]> <html class="no-js ie8 lt-ie9"> <![endif]-->
<!--[if gt IE 8]><!--><html class="no-js" lang="en" dir="ltr"> <!--<![endif]-->

<head>

·················

····················

</body>
</html>
打印的结果为：
from urllib import request,parse
url='http://httpbin.org/post'

############ POST 请求 ###############
headers={
    "User-Agent":"Mozilla/4.0(compatible;MSIE 5.5;Windows NT)",
    "Host":'httpbin.org'
    }
dict={
    'name':"Germey"
    }
data =bytes(parse.urlencode(dict),encoding="utf-8")
req =request.Request(url=url,data=data,headers=headers,method='POST')
response=request.urlopen(req)
print(response.read().decode('utf-8'))
{
"args": {}, 
"data": "", 
"files": {}, 
"form": {
"name": "Germey"
}, 
"headers": {
"Accept-Encoding": "identity", 
"Connection": "close", 
"Content-Length": "11", 
"Content-Type": "application/x-www-form-urlencoded", 
"Host": "httpbin.org", 
"User-Agent": "Mozilla/4.0(compatible;MSIE 5.5;Windows NT)"
}, 
"json": null, 
"origin": "221.208.253.76", 
"url": "http://httpbin.org/post"
}
打印的结果为：
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;MSIE5.5;Windows NT)')
response = request.urlopen(req)
print(response.read().decode('utf-8'))
{
"args": {}, 
"data": "", 
"files": {}, 
"form": {
"name": "Germey"
}, 
"headers": {
"Accept-Encoding": "identity", 
"Connection": "close", 
"Content-Length": "11", 
"Content-Type": "application/x-www-form-urlencoded", 
"Host": "httpbin.org", 
"User-Agent": "Mozilla/4.0(compatible;MSIE5.5;Windows NT)"
}, 
"json": null, 
"origin": "221.208.253.76", 
"url": "http://httpbin.org/post"
}
打印的结果为：

(4)Handler

 代理

import urllib.request
proxy_handler = urllib.request.ProxyHandler({
    'http':'http://127.0.0.1:9743',   # 代理http
    'https':'https://127.0.0.1:9743'  # 代理https
    })
opener =urllib.request.build_opener(proxy_handler)
response=opener.open("http://www.baidu.com")
print(response.read())
因为我没有代理，所以打印出来的结果为：

urllib.error.URLError: <urlopen error [WinError 10061] 由于目标计算机积极拒绝，无法连接。>
打印的结果为：

Cookie

import http.cookiejar,urllib.request
cookie=http.cookiejar.CookieJar()  # 获取Cookie信息
handler=urllib.request.HTTPCookieProcessor(cookie) # 把Cookie信息放入到 handler中
opener=urllib.request.build_opener(handler) # 建立opener
response=opener.open("http://www.baidu.com")
for item in cookie:
    print(item.name+"=”+item.value)
BAIDUID=DDCB4C216AE8EE90C7D95E7AF8FA577F:FG=1
BIDUPSID=DDCB4C216AE8EE90C7D95E7AF8FA577F
H_PS_PSSID=1452_21078_26350_27111
PSTM=1536830732
BDSVRTM=0
BD_HOME=0
delPer=0
打印的结果为：
########### 把Cookie 保存成文件 ##########
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)
在工程目录下多了一个cookie.txt文件

该文件的内容为：

# Netscape HTTP Cookie File
# http://curl.haxx.se/rfc/cookie_spec.html
# This is a generated file!  Do not edit.

.baidu.com TRUE   /  FALSE  3684314677 BAIDUID    CB67C520D33E28D7204C570EB7DFA28F:FG=1
.baidu.com TRUE   /  FALSE  3684314677 BIDUPSID   CB67C520D33E28D7204C570EB7DFA28F
.baidu.com TRUE   /  FALSE     H_PS_PSSID 1434_21113_26350_20930
.baidu.com TRUE   /  FALSE  3684314677 PSTM   1536831034
www.baidu.com  FALSE  /  FALSE     BDSVRTM    0
www.baidu.com  FALSE  /  FALSE     BD_HOME    0
www.baidu.com  FALSE  /  FALSE  2482910974 delPer 0
打印的结果为：
########### 另一种 Cookie 的保存案例 ##########
import http.cookiejar,urllib.request
filename = "cookies.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)

代码运行结果与上面相同！

(5)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)

 

Not Found
打印的结果为：
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")

 

Not Found
404
Server: nginx/1.10.3 (Ubuntu)
Date: Thu, 13 Sep 2018 11:08:18 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: <https://cuiqingcai.com/wp-json/>; rel="https://api.w.org/"
打印的结果为：
import socket
import urllib.request
import urllib.error
try:
    response = urllib.request.urlopen("https://www.baidu.com",timeout=0.000000001)
except urllib.error.URLError as e:
    print(type(e.reason))
    if isinstance(e.reason,socket.timeout):
        print("TimeOut")

 

<class 'socket.timeout'>
TimeOut
执行后的结果为：

 (6)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=5i#comment")
print(type(result),result)
<class 'urllib.parse.ParseResult'> ParseResult(scheme='http', netloc='www.baidu.com', path='/index.html', params='user', query='id=5i', fragment='comment')
打印的结果为：
######## 无协议类型 ###########
from urllib.parse import urlparse
result =urlparse("www.baidu.com/index.html;user?id=5i#comment,scheme=/https")
print(result)

 

ParseResult(scheme='', netloc='', path='www.baidu.com/index.html', params='user', query='id=5i', fragment='comment,scheme=/https')
打印后的结果为：
######## 默认的协议类型 ###########
from urllib.parse import urlparse
result=urlparse("http://www.baidu.com/index.html;user?id=5i#comment,scheme=/https")
print(result)

 

ParseResult(scheme='http', netloc='www.baidu.com', path='/index.html', params='user', query='id=5i', fragment='comment,scheme=/https')
打印后的结果为：
from urllib.parse import urlparse
result =urlparse("http://www.baidu.com/index.html;user?id=5i#comment",allow_fragments=False)
print(result)

 

ParseResult(scheme='http', netloc='www.baidu.com', path='/index.html', params='user', query='id=5i#comment', fragment='')
打印后的结果为：
from urllib.parse import urlparse
result =urlparse("http://www.baidu.com/index.htmlf#comment",allow_fragments=False)
print(result)
ParseResult(scheme='http', netloc='www.baidu.com', path='/index.htmlf#comment', params='', query='', fragment='')
打印后的结果为：

urlunparse

from urllib.parse import urlunparse
data =["http","www.baidu.cogn","index.html","user",'a=6','comment']
print(urlunparse(data))
http://www.baidu.cogn/index.html;user?a=6#comment
执行后的结果

 urljoin(url拼接，前面若在为补充，后面若在为基准)

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/infex.php'))
print(urljoin('http://www.baidu.com','?category=2#commen:'))
print(urljoin('www.baidu.com','?category=2t#comment'))
print(urljoin('www.baidu.comi#comment','?category=2'))
http://www.baidu.com/FAQ.htmr
https://cuiqingcai.com/FAQ.html
https://cuiqingcai.com/FAQ.html
https://cuiqingcai.com/FAQ.html?question=2
https://cuiqingcai.com/infex.php
http://www.baidu.com?category=2#commen:
www.baidu.com?category=2t#comment
www.baidu.comi?category=2
打印的结果为：

urlencode(把字典对象转化为GET请求参数)

from urllib.parse import urlencode
params={
    'name':'germey',
    'agel':'22'
    }
base_url='http://www.baidu.com?'
url=base_url+urlencode(params)
print(url)
http://www.baidu.com?name=germey&agel=22
打印的结果为：

 

posted @ 2018-09-13 19:50  追风的小蚂蚁  阅读(543)  评论(0)  编辑  收藏  举报