# 注意一下 是import urllib.request 还是 form urllib import request
0. urlopen()
语法：urllib.request.urlopen(url, data=None, [timeout, ]*, cafile=None, capath=None, cadefault=False, context=None)
*添加的data参数需要使用bytes()方法将参数转换为字节流（区别于str的一种类型 是一种比特流 010010010）编码的格式的内容，即bytes类型。
*response.read()是bytes类型的数据，需要decode（解码）一下。
import urllib.parse import urllib.request import urllib.error url = ‘http://httpbin.org/post‘ data = bytes(urllib.parse.urlencode({‘word‘: ‘hello‘}), encoding=‘utf8‘) try: response = urllib.request.urlopen(url, data=data,timeout=1) except urllib.error.URLError as e: if isinstance(e.reason, socket.timeout): print(‘TIME OUT‘) else: print(response.read().decode("utf-8"))
输出结果：
{
"args": {},
"data": "",
"files": {},
"form": {
"word": "hello"
},
"headers": {
"Accept-Encoding": "identity",
"Content-Length": "10",
"Content-Type": "application/x-www-form-urlencoded",
"Host": "httpbin.org",
"User-Agent": "Python-urllib/3.6"
},
"json": null,
"origin": "101.206.170.234, 101.206.170.234",
"url": "https://httpbin.org/post"
}
import urllib.request response = urllib.request.urlopen(‘https://www.python.org‘) print(response.status) print(response.getheaders()) print(response.getheader(‘Server‘))
输出结果：
200 [(‘Server‘, ‘nginx‘), (‘Content-Type‘, ‘text/html; charset=utf-8‘), (‘X-Frame-Options‘, ‘DENY‘), (‘Via‘, ‘1.1 vegur‘), (‘Via‘, ‘1.1 varnish‘), (‘Content-Length‘, ‘48410‘), (‘Accept-Ranges‘, ‘bytes‘), (‘Date‘, ‘Tue, 09 Apr 2019 02:32:34 GMT‘), (‘Via‘, ‘1.1 varnish‘), (‘Age‘, ‘722‘), (‘Connection‘, ‘close‘), (‘X-Served-By‘, ‘cache-iad2126-IAD, cache-hnd18751-HND‘), (‘X-Cache‘, ‘MISS, HIT‘), (‘X-Cache-Hits‘, ‘0, 1223‘), (‘X-Timer‘, ‘S1554777154.210361,VS0,VE0‘), (‘Vary‘, ‘Cookie‘), (‘Strict-Transport-Security‘, ‘max-age=63072000; includeSubDomains‘)] nginx
使用urllib库的urlopen()方法有很大的局限性，比如不能设置响应头的信息等。所以需要引入request()方法。
1. Request()
import urllib.request response = urllib.request.urlopen(‘https://www.python.org‘) print(response.read().decode(‘utf-8‘)) ###################################### import urllib.request req = urllib.request.Request(‘https://python.org‘) response = urllib.request.urlopen(req) print(response.read().decode(‘utf-8‘))
下面主要讲解下使用Request()方法来实现get请求和post请求,并设置参数。
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‘))
亦可使用add_header()方法来添加报头，实现浏览器的模拟，添加data属性亦可如下书写：
补充：还可以使用bulid_opener()修改报头，不过多阐述，够用了就好。
from urllib import request, parse url = ‘http://httpbin.org/post‘ dict = { ‘name‘: ‘Germey‘ } data = parse.urlencode(dict).encode(‘utf-8‘) 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‘))
from urllib import request,parse url = ‘http://www.baidu.com/s?wd=‘ key = ‘路飞‘ key_code = request.quote(key) url_all = url + key_code """ #第二种写法 url = ‘http://www.baidu.com/s‘ key = ‘路飞‘ wd = parse.urlencode({‘wd‘:key}) url_all = url + ‘?‘ + wd """ req = request.Request(url_all) response = request.urlopen(req) print(response.read().decode(‘utf-8‘))
在这里，对编码decode、reqest模块里的quote()方法、parse模块的urlencode()方法 等就有疑问了，，对此，做一些说明：
>>> str0 = ‘我爱你‘
>>> str1 = str0.encode(‘gb2312‘)
>>> str1
b‘\xce\xd2\xb0\xae\xc4\xe3‘
>>> str2 = str0.encode(‘gbk‘)
>>> str2
b‘\xce\xd2\xb0\xae\xc4\xe3‘
>>> str3 = str0.encode(‘utf-8‘)
>>> str3
b‘\xe6\x88\x91\xe7\x88\xb1\xe4\xbd\xa0‘
>>> str00 = str1.decode(‘gb2312‘)
>>> str00
‘我爱你‘
>>> str11 = str1.decode(‘utf-8‘) #报错，因为str1是gb2312编码的
Traceback (most recent call last):
File "<pyshell#9>", line 1, in <module>
str11 = str1.decode(‘utf-8‘)
UnicodeDecodeError: ‘utf-8‘ codec can‘t decode byte 0xce in position 0: invalid continuation byte
* encoding指定编码格式
在这里，又有疑问了？read()、readline()、readlines()的区别：
0.爬虫 urlib库讲解 urlopen()与Request()
原文：https://www.cnblogs.com/DC0307/p/10675878.html