爬虫（二）：Urllib库详解

什么是Urllib：

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

　　　　GET请求方式

    POST请求方式

    超时timeout,异常处理

    响应类型(响应码,响应头...)

    POST请求添加Headers

    代理方法

    cookie添加 读取

    ---------- parse 包下 -----------

    urlparse 解析网址

    urlunparse 拼接网址

    urlencode GET参数化(比较有用)

 

python3：

urlopen

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

#############################
import urllib.request

# GET方式（不加data）
response = urllib.request.urlopen('http://www.baidu.com') # 请求数据
print(response.read().decode('utf-8')) # 转换为字符串编码，read()得到的是byte格式的
#############################
import urllib.parse
import urllib.request

# POST方式（加data）
data = bytes(urllib.parse.urlencode({'word': 'hello'}), encoding='utf8')
response = urllib.request.urlopen('http://httpbin.org/post', data=data)  # http://httpbin.org/post 用来做HTTP测试的网址
print(response.read())
#############################
import urllib.request

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

响应

# 响应类型
import urllib.request

response = urllib.request.urlopen('https://www.python.org')
print(type(response)) #<class 'http.client.HTTPResponse'>

#############################
# 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')) # 响应的服务
#############################
import urllib.request
#获取响应内容
response = urllib.request.urlopen('https://www.python.org')
print(response.read().decode('utf-8')) # read() 获取bytes类型

Request

# 加入headers，发送一个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'))

Handler

# 添加代理
import urllib.request

proxy_handler = urllib.request.ProxyHandler({ # 代理设置
    'http': 'http://127.0.0.1:9743',
    'https': 'https://127.0.0.1:9742'
})
opener = urllib.request.build_opener(proxy_handler)
response = opener.open('http://httpbin.org/get')
print(response.read())

Cookie

import http.cookiejar, urllib.request

# 获取cookies
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)
#############################

# 将cookie保存为txt文件
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)

#############################
# 读取cookie文件
import http.cookiejar, urllib.request
# 用哪种格式存cookies，就用哪种方法读取
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

# 异常处理1
from urllib import request, error
try:
    response = request.urlopen('http://cuiqingcai.com/index.htm')
except error.URLError as e:
    print(e.reason)

#############################
# 异常处理2
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')
#############################
# 异常处理3
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')

URL解析

# 一个参数
from urllib.parse import urlparse
result = urlparse('http://www.baidu.com/index.html;user?id=5#comment')
print(type(result), result)

##########################
# 指定协议, 如果没有取https, 有就用url带的
from urllib.parse import urlparse
result = urlparse('http://www.baidu.com/index.html;user?id=5#comment', scheme='https') # 指定协议类型
print(result)

##########################
# allow_fragments=False 一般不会用,把锚链接部分移动到参数(没有参数在往前移动#XXXX)
from urllib.parse import urlparse
result = urlparse('http://www.baidu.com/index.html#comment', allow_fragments=False)
print(result)

urlunparse

from urllib.parse import urlunparse
# 拼接网站
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

from urllib.parse import urljoin
# 拼接
print(urljoin('http://www.baidu.com', 'Faq.html'))
# 以第二个位基准
print(urljoin('http://www.baidu.com', 'https://www.baidu.com/aaa'))
# 拼接
print(urljoin('http://www.baidu.com', '?a=1'))

urlencode

# 参数化get参数
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