python爬虫——urllib库

1.urllib

urlopen

urlopen.reques.urlopen(url,date=None,[timeout,]*,cafile=None,capath=None,cadefault=False,context=None)

#只有url参数的情况
import urllib.request
response = urllib.request.urlopen('http://www.baidu.com')
print(response.read().decode('utf-8'))

#有url和data两个参数的情况
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)#post提交
print(response.read())

#超时设置
import urllib.request
response = urllib.request.urlopen('http://httpbin.org/get',timeout=1)#get提交
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")

2.响应

2.1响应类型

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

2.2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'))

3.Request

使用request可以更加方便的指定的请求方式，并附加参数和数据。

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

附加headers

from urllib import request,parse
url = 'http://httpbin.org/post'
dict = {
    'name':'Germey'
}
data = bytes(parse.urlencode(dict),encoding='utf-8')
req = request.Request(url = url,data=data,method='POST')
req.add_header('Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36')
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='utf-8')
req = request.Request(url = url,data=data,method='POST')
req.add_header('User-Agent','Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/66.0.3359.139 Safari/537.36')
response = request.urlopen(req)
print(response.read().decode('utf-8'))

4.Handler

4.1代理

import urllib.request
proxy_hanlder = urllib.request.ProxyHandler({
    'http':'http://127.0.0.1:9743',
    'https':'https://127.0.0.1:9743'
})
opener = urllib.request.build_opener(proxy_hanlder)
response = opener.open('http://www.baidu.com')
print(response.read(0)

4.2Cookie

获取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)

以火狐方式保存

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)

以LWPCookieJar方式保存cookie

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)

以LWPCookieJar方式读取cookie

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

5.异常处理

#返回状态码是404
from urllib import request,error
try:
    response = request.urlopen('http://www.hahaha.com/hahaha.html')
except error.URLError as e:
    print(e.reason)

多种异常：

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

超时异常：

import socket 
import urllib.request
import urllib.error
try:
    response = urllib.request.urlopen('httpa://www.baidu.com',timeout = 0.1)
except urllib.error.URLError as e:
    print(type(e.reason))
    if isinstance(e.reason,socket.timeout):
        print('TIME OUT')

6.RUL解析

6.1urlparse

将传入的url分割，将参数和域名分割开。

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)

带参数

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

from urllib.parse import urlparse
result = urlparse('http://www.baidu.com/index.html;user?id=5#comment',scheme = 'https')#指定协议，原协议存在，scheme不生效
print(type(result),result)

from urllib.parse import urlparse
result = urlparse('www.baidu.com/index.html;user?id=5#comment',allow_fragments = False)#锚点链接，设为false，会将fragement拼接到query
print(type(result),result)

from urllib.parse import urlparse
result = urlparse('www.baidu.com/index.html#comment',allow_fragments = False)#query不存在，会将fragement拼接到path上
print(type(result),result)

6.2urlunparse

将单数拼接成完整的url

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

6.3urljoin

将两个url拼接成一个url。

from urllib.parse import urljoin
print(urljoin('http://www.baidu.com','FAQ.html'))
print(urljoin('http://www.baidu.com','https:hahaha.com/FAQ.html'))
print(urljoin('www.baidu.com','?category=2#comment'))

6.4urlencode

将字典转为get请求参数

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