urllib包
-
urllib.request 发送http请求
-
urllib.error 处理请求过程中,出现的异常。
-
urllib.parse 解析url
-
urllib.robotparser 解析robots.txt 文件
urllib当中使用最多的模块,涉及请求,响应,浏览器模拟,代理,cookie等功能。
request.urlopen(url, data=None, timeout=10)
#url: 需要打开的网址
#data:Post提交的数据
#timeout:设置网站的访问超时时间
from urllib import request
import ssl
# 解决某些环境下报<urlopen error [SSL: CERTIFICATE_VERIFY_FAILED] certificate verify failed
ssl._create_default_https_context = ssl._create_unverified_context
url = 'https://www.jianshu.com'
#返回<http.client.HTTPResponse object at 0x0000000002E34550>
response = request.urlopen(url, data=None, timeout=10)
#直接用urllib.request模块的urlopen()获取页面,page的数据格式为bytes类型,需要decode()解码,转换成str类型。
page = response.read().decode('utf-8')
需要添加headers头信息,urlopen不支持,需要使用Request
PC
import urllib.request
url = 'https://www.jianshu.com'
# 增加header
headers = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.96 Safari/537.36'
}
request = urllib.request.Request(url,headers=headers)
response = urllib.request.urlopen(request)
#在urllib里面 判断是get请求还是post请求,就是判断是否提交了data参数
print(request.get_method())
>> 输出结果
GET
req = request.Request('http://www.douban.com/')
req.add_header('User-Agent', 'Mozilla/6.0 (iPhone; CPU iPhone OS 8_0 like Mac OS X) '
'AppleWebKit/536.26 (KHTML, like Gecko) Version/8.0 Mobile/10A5376e Safari/8536.25')
with request.urlopen(req) as f:
print('Status:', f.status, f.reason)
for k, v in f.getheaders():
print('%s: %s' % (k, v))
print('Data:', f.read().decode('utf-8'))
客户端用于记录用户身份,维持登录信息
import http.cookiejar, urllib.request
# 1 创建CookieJar对象
cookie = http.cookiejar.CookieJar()
# 使用HTTPCookieProcessor创建cookie处理器,
handler = urllib.request.HTTPCookieProcessor(cookie)
# 构建opener对象
opener = urllib.request.build_opener(handler)
# 将opener安装为全局
urllib.request.install_opener(opener)
data = urllib.request.urlopen(url)
# 2 保存cookie为文本
import http.cookiejar, urllib.request
filename = "cookie.txt"
# 保存类型有很多种
## 类型1
cookie = http.cookiejar.MozillaCookieJar(filename)
## 类型2
cookie = http.cookiejar.LWPCookieJar(filename)
# 使用相应的方法读取
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)
……
4.设置代理
当需要抓取的网站设置了访问限制,这时就需要用到代理来抓取数据。
import urllib.request
url = 'http://httpbin.org/ip'
proxy = {'http':'39.134.108.89:8080','https':'39.134.108.89:8080'}
proxies = urllib.request.ProxyHandler(proxy) # 创建代理处理器
opener = urllib.request.build_opener(proxies,urllib.request.HTTPHandler) # 创建特定的opener对象
urllib.request.install_opener(opener) # 安装全局的opener 把urlopen也变成特定的opener
data = urllib.request.urlopen(url)
print(data.read().decode())
import urllib.error
import urllib.request
requset = urllib.request.Request('http://www.usahfkjashfj.com/')
try:
urllib.request.urlopen(requset).read()
except urllib.error.URLError as e:
print(e.reason)
else:
print('success')
>> print结果
[Errno 11004] getaddrinfo failed
HTTPError是URLError的子类,在你利用URLopen方法发出一个请求时,服务器上都会对应一个应答对象response,其中他包含一个数字“状态码”,
例如response是一个重定向,需定位到别的地址获取文档,urllib将对此进行处理。其他不能处理的,URLopen会产生一个HTTPError,对应相应的状态码,
HTTP状态码表示HTTP协议所返回的响应的状态。
from urllib import request, error
try:
response = request.urlopen('http://cuiqingcai.com/index.htm')
except error.URLError as e:
print(e.reason)
# 先捕获子类错误
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')
>> print结果
Not Found
------------- Not Found 404 Server: nginx/1.10.3 (Ubuntu) Date: Thu, 08 Feb 2018 14:45:39 GMT Content-Type: text/html; charset=UTF-8 Transfer-Encoding: chunked Connection: close Vary: Cookie Expires: Wed, 11 Jan 1984 05:00:00 GMT
print(parse.urljoin('https://www.jianshu.com/xyz','FAQ.html'))
print(parse.urljoin('http://www.baidu.com/about.html','http://www.baidu.com/FAQ.html'))
>>结果
https://www.jianshu.com/FAQ.html
http://www.baidu.com/FAQ.html
urllib.parse.urlencode 字典转字符串
from urllib import request, parse
url = r'https://www.jianshu.com/collections/20f7f4031550/mark_viewed.json'
headers = {
'User-Agent': r'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.132 Safari/537.36',
'Referer': r'https://www.jianshu.com/c/20f7f4031550?utm_medium=index-collections&utm_source=desktop',
'Connection': 'keep-alive'
}
data = {
'uuid': '5a9a30b5-3259-4fa0-ab1f-be647dbeb08a',
}
#Post的数据必须是bytes或者iterable of bytes,不能是str,因此需要进行encode()编码
data = parse.urlencode(data).encode('utf-8')
print(data)
req = request.Request(url, headers=headers, data=data)
page = request.urlopen(req).read()
page = page.decode('utf-8')
print(page)
>>结果
b'uuid=5a9a30b5-3259-4fa0-ab1f-be647dbeb08a'
{"message":"success"}
http://so.biquge.la/cse/search?s=7138806708853866527&q=%CD%EA%C3%C0%CA%C0%BD%E7
from urllib import parse
x = parse.quote('山西', encoding='gb18030')# encoding='GBK
print(x) #%C9%BD%CE%F7
city = parse.unquote('%E5%B1%B1%E8%A5%BF',) # encoding='utf-8'
print(city) # 山西
urllib3包
Urllib3是一个功能强大,条理清晰,用于HTTP客户端的Python库,许多Python的原生系统已经开始使用urllib3。Urllib3提供了很多python标准库里所没有的重要特性:
1.线程安全 2.连接池 3.客户端SSL/TLS验证 4.文件分部编码上传 5.协助处理重复请求和HTTP重定位 6.支持压缩编码 7.支持HTTP和SOCKS代理
安装:
Urllib3 能通过pip来安装:
$pip install urllib3
你也可以在github上下载最新的源码,解压之后进行安装:
$git clone git://github.com/shazow/urllib3.git
$python setup.py install
urllib3的使用:
request GET请求
import urllib3
import requests
# 忽略警告:InsecureRequestWarning: Unverified HTTPS request is being made. Adding certificate verification is strongly advised.
requests.packages.urllib3.disable_warnings()
# 一个PoolManager实例来生成请求, 由该实例对象处理与线程池的连接以及线程安全的所有细节
http = urllib3.PoolManager()
# 通过request()方法创建一个请求:
r = http.request('GET', 'http://cuiqingcai.com/')
print(r.status) # 200
# 获得html源码,utf-8解码
print(r.data.decode())
request GET请求(添加数据)
header = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36'
}
r = http.request('GET',
'https://www.baidu.com/s?',
fields={'wd': 'hello'},
headers=header)
print(r.status) # 200
print(r.data.decode())
post请求
#你还可以通过request()方法向请求(request)中添加一些其他信息,如:
header = {
'User-Agent': 'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/63.0.3239.108 Safari/537.36'
}
r = http.request('POST',
'http://httpbin.org/post',
fields={'hello':'world'},
headers=header)
print(r.data.decode())
# 对于POST和PUT请求(request),需要手动对传入数据进行编码,然后加在URL之后:
encode_arg = urllib.parse.urlencode({'arg': '我的'})
print(encode_arg.encode())
r = http.request('POST',
'http://httpbin.org/post?'+encode_arg,
headers=header)
# unicode解码
print(r.data.decode('unicode_escape'))
发送json数据
#JSON:在发起请求时,可以通过定义body 参数并定义headers的Content-Type参数来发送一个已经过编译的JSON数据:
import json
data={'attribute':'value'}
encode_data= json.dumps(data).encode()
r = http.request('POST',
'http://httpbin.org/post',
body=encode_data,
headers={'Content-Type':'application/json'}
)
print(r.data.decode('unicode_escape'))
上传文件
#使用multipart/form-data编码方式上传文件,可以使用和传入Form data数据一样的方法进行,并将文件定义为一个元组的形式 (file_name,file_data):
with open('1.txt','r+',encoding='UTF-8') as f:
file_read = f.read()
r = http.request('POST',
'http://httpbin.org/post',
fields={'filefield':('1.txt', file_read, 'text/plain')
})
print(r.data.decode('unicode_escape'))
#二进制文件
with open('websocket.jpg','rb') as f2:
binary_read = f2.read()
r = http.request('POST',
'http://httpbin.org/post',
body=binary_read,
headers={'Content-Type': 'image/jpeg'})
#
# print(json.loads(r.data.decode('utf-8'))['data'] )
print(r.data.decode('utf-8'))
使用Timeout
#使用timeout,可以控制请求的运行时间。在一些简单的应用中,可以将timeout参数设置为一个浮点数:
r = http.request('POST',
'http://httpbin.org/post',timeout=3.0)
print(r.data.decode('utf-8'))
#让所有的request都遵循一个timeout,可以将timeout参数定义在PoolManager中:
http = urllib3.PoolManager(timeout=3.0)
对重试和重定向进行控制
#通过设置retries参数对重试进行控制。Urllib3默认进行3次请求重试,并进行3次方向改变。
r = http.request('GET',
'http://httpbin.org/ip',retries=5)#请求重试的次数为5
print(r.data.decode('utf-8'))
##关闭请求重试(retrying request)及重定向(redirect)只要将retries定义为False即可:
r = http.request('GET',
'http://httpbin.org/redirect/1',retries=False,redirect=False)
print('d1',r.data.decode('utf-8'))
#关闭重定向(redirect)但保持重试(retrying request),将redirect参数定义为False即可
r = http.request('GET',
'http://httpbin.org/redirect/1',redirect=False)
def
request_encode_url(
self
, method, url, fields
=
None
, headers
=
None
,
*
*
urlopen_kw):
if
headers
is
None
:
headers
=
self
.headers
extra_kw
=
{
'headers'
: headers}
extra_kw.update(urlopen_kw)
if
fields:
url
+
=
'?'
+
urlencode(fields)
return
self
.urlopen(method, url,
*
*
extra_kw)