Python3：urllib模块的使用

urllib.request.urlopen(url, data=None, [timeout, ]*, cafile=None, capath=None, cadefault=False, context=None)
    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
response = request.urlopen(r‘http://python.org/‘)
page = response.read()
page = page.decode(‘utf-8‘)
urlopen返回对象提供方法：

read() , readline() ,readlines() , fileno() , close() ：对HTTPResponse类型数据进行操作

info()：返回HTTPMessage对象，表示远程服务器返回的头信息
getcode()：返回Http状态码。如果是http请求，200请求成功完成;404网址未找到
geturl()：返回请求的url

url = r‘http://www.lagou.com/zhaopin/Python/?labelWords=label‘
headers = {
     ‘User-Agent‘: r‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) ‘
                   r‘Chrome/45.0.2454.85 Safari/537.36 115Browser/6.0.3‘,
     ‘Referer‘: r‘http://www.lagou.com/zhaopin/Python/?labelWords=label‘,
     ‘Connection‘: ‘keep-alive‘
}
req = request.Request(url, headers=headers)
page = request.urlopen(req).read()
page = page.decode(‘utf-8‘)

urllib.request.urlopen(url, data=None, [timeout, ]*, cafile=None, capath=None, cadefault=False, context=None)
urlopen()的data参数默认为None，当data参数不为空的时候，urlopen()提交方式为Post。

from urllib import request, parse
url = r‘http://www.lagou.com/jobs/positionAjax.json?‘
headers = {
     ‘User-Agent‘: r‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) ‘
                   r‘Chrome/45.0.2454.85 Safari/537.36 115Browser/6.0.3‘,
     ‘Referer‘: r‘http://www.lagou.com/zhaopin/Python/?labelWords=label‘,
     ‘Connection‘: ‘keep-alive‘
}
data = {
     ‘first‘: ‘true‘,
     ‘pn‘: 1,
     ‘kd‘: ‘Python‘
}
data = parse.urlencode(data).encode(‘utf-8‘)
req = request.Request(url, headers=headers, data=data)
page = request.urlopen(req).read()
page = page.decode(‘utf-8‘)

data = {
     ‘first‘: ‘true‘,
     ‘pn‘: 1,
     ‘kd‘: ‘Python‘
}
data = parse.urlencode(data).encode(‘utf-8‘)
经过urlencode（）转换后的data数据为?first=true?pn=1?kd=Python，最后提交的url为:
http://www.lagou.com/jobs/positionAjax.json?first=true?pn=1?kd=Python
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
当然，也可以把data的数据封装在urlopen（）参数中:
page = request.urlopen(req, data=data).read()

从json中取出的数据类型和数据如下：
 {‘install‘: {‘install_date‘: ‘2018/09/26‘, ‘install_result‘: ‘success‘}}
经过转码：company_data = parse.urlencode(data).encode(‘utf-8‘)
变成这样：b‘install=%7B%27install_date%27%3A+%272018%2F09%2F26%27%2C+%27install_result%27%3A+%27success%27%7D‘
服务器端接收数据：
data = request.POST.get("company_data")
数据类型、数据分别如下：
 {"install": {"install_result": "success", "install_date": "2018/09/26"}}

客户端：
import json
with open(‘1.json‘, ‘r‘) as f:
    data = json.load(f)

data = {"company_data": json.dumps(data)}

# urlopen（）的data参数默认为None，当data参数不为空的时候，urlopen（）提交方式为Post
from urllib import request, parse
url = r‘http://192.168.165.4:8000/show/report/‘
company_data = parse.urlencode(data).encode(‘utf-8‘)
req = request.Request(url, data=company_data)
print(company_data)
page = request.urlopen(req).read()
page = page.decode(‘utf-8‘)

服务器端：
@csrf_exempt
def receive_data(request):
    data = request.POST.get("company_data")
    if data:
        try:
            data = json.loads(data)
            print("企业数据", type(data), data)
            return HttpResponse(data)
        except ValueError as e:
            print(str(e))
    else:
        return HttpResponse("no data")

data = {
     ‘first‘: ‘true‘,
     ‘pn‘: 1,
     ‘kd‘: ‘Python‘
}
proxy = request.ProxyHandler({‘http‘: ‘5.22.195.215:80‘})  # 设置proxy
opener = request.build_opener(proxy)  # 挂载opener
request.install_opener(opener)  # 安装opener
data = parse.urlencode(data).encode(‘utf-8‘)
page = opener.open(url, data).read()
page = page.decode(‘utf-8‘)