Python爬蟲系列-Urllib庫詳解

Urllib庫詳解

Python內置的Http請求庫:
* urllib.request 請求模塊
* urllib.error 異常處理模塊
* urllib.parse url解析模塊
* urllib.robotparser robots.txt解析模塊

相比在python2基礎上的變化

Python2

import urllib2
response = urllib2.urlopen('http://www.baidu.com')

Python3

import urllib.request
response = urllib.request.urlopen('http://www.baidu.com')

urlopen實現get方法

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

urlopen實現post方法

import urllib.parse
import urllib.request
data = bytes(urllib.parse.urlencode({'word':'hello'}),encoding='utf-8')
response = urllib.request.urlopen('http://httpbin.org/post',data=data)

urlopen實現超時設置

import urllib.request
response = urllib.request.urlopen('http://httpbin.org/get',timeout=1)
print(response.read())

將時間縮短，查看效果

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')

響應類型

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

<class 'http.client.HTTPResponse'>

狀態碼、響應頭

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

200
[('Server', 'nginx'), ('Content-Type', 'text/html; charset=utf-8'), ('X-Frame-Options', 'SAMEORIGIN'), ('x-xss-protection', '1; mode=block'), ('X-Clacks-Overhead', 'GNU Terry Pratchett'), ('Via', '1.1 varnish'), ('Content-Length', '50069'), ('Accept-Ranges', 'bytes'), ('Date', 'Mon, 26 Nov 2018 10:16:51 GMT'), ('Via', '1.1 varnish'), ('Age', '1872'), ('Connection', 'close'), ('X-Served-By', 'cache-iad2144-IAD, cache-tyo19943-TYO'), ('X-Cache', 'HIT, HIT'), ('X-Cache-Hits', '2, 4331'), ('X-Timer', 'S1543227412.955266,VS0,VE0'), ('Vary', 'Cookie'),
('Strict-Transport-Security', 'max-age=63072000; includeSubDomains')]
nginx

Request

from urllib import request,parse
url = 'http://httpbin.org/post'
headers = {
 'User-Agent':'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36',
 '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/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/70.0.3538.77 Safari/537.36"
},
"json": null,
"origin": "58.34.235.37",
"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'))

{
"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": "58.34.235.37",
"url": "http://httpbin.org/post"
}

Handler

代理

import urllib.request
proxy_handler = urllib.request.ProxyHandler({
    'http':'http://127.0.0.1:9319',
    'https':'https://127.0.0.1:9319'
})
opener = urllib.request.build_opener(proxy_handler)
response = opener.open('http://www.baidu.com')
print(response.read())

Cookie

獲取

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)

BAIDUID=DF51E1D71641196283719D090EEA14DA:FG=1
BIDUPSID=DF51E1D71641196283719D090EEA14DA
H_PS_PSSID=1433_21086_27508
PSTM=1543232201
delPer=0
BDSVRTM=0
BD_HOME=0

保存Cookie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)

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

.baidu.com TRUE / FALSE 3690716228 BAIDUID 3131EAE6351C0F474BF6E477B848A52B:FG=1
.baidu.com TRUE / FALSE 3690716228 BIDUPSID 3131EAE6351C0F474BF6E477B848A52B
.baidu.com TRUE / FALSE H_PS_PSSID 27775_1454_21088_20719
.baidu.com TRUE / FALSE 3690716228 PSTM 1543232581
.baidu.com TRUE / FALSE delPer 0
www.baidu.com FALSE / FALSE BDSVRTM 0
www.baidu.com FALSE / FALSE BD_HOME 0

import http.cookiejar,urllib.request
 filename = 'cookie2.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)

#LWP-Cookies-2.0
Set-Cookie3: BAIDUID="38C33C024449D6412F80B85996FAA2F8:FG=1"; path="/"; domain=".baidu.com"; path_spec; domain_dot; expires="2086-12-14 15:01:56Z"; version=0
Set-Cookie3: BIDUPSID=38C33C024449D6412F80B85996FAA2F8; path="/"; domain=".baidu.com"; path_spec; domain_dot; expires="2086-12-14 15:01:56Z"; version=0
Set-Cookie3: H_PS_PSSID=1462_21088_22157; path="/"; domain=".baidu.com"; path_spec; domain_dot; discard; version=0
Set-Cookie3: PSTM=1543232869; path="/"; domain=".baidu.com"; path_spec; domain_dot; expires="2086-12-14 15:01:56Z"; version=0
Set-Cookie3: delPer=0; path="/"; domain=".baidu.com"; path_spec; domain_dot; discard; version=0
Set-Cookie3: BDSVRTM=0; path="/"; domain="www.baidu.com"; path_spec; discard; version=0
Set-Cookie3: BD_HOME=0; path="/"; domain="www.baidu.com"; path_spec; discard; version=0

加載Cookie文件

import http.cookiejar,urllib.request
cookie = http.cookiejar.LWPCookieJar()
cookie.load('cookie2.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'))

異常處理

from urllib import request,error
 try:
     response = request.urlopen('http://cuiiqdkfsj.com/insdfi.htm')
 except error.URLError as e:
     print(e.reason)

[Errno -2] Name or service not known

from urllib import request,error
try:
     response = request.urlopen('http://www.baidu.com/dsjfi.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')

[Errno -2] Name or service not known

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

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')

指定協議

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

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

取消錨點連接,向前拼接

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

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

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

urljoin

urlencode

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