python的urllib.parse用法及说明

url:urllib.parse.urlparse(url, scheme='', allow_fragments=True)
url:urllib.parse.urlparse(url, scheme='', allow_fragments=True)

from urllib import request, parse2 #解析url
print(parse.urlparse('https://movie.douban.com/'))
print(parse.urlparse('https://movie.douban.com/', scheme='http'))
print(parse.urlparse('movie.douban.com/', scheme='http'))
# 下面是结果
ParseResult(scheme='https', netloc='movie.douban.com', path='/', params='', query='', fragment='')
ParseResult(scheme='https', netloc='movie.douban.com', path='/', params='', query='', fragment='')
ParseResult(scheme='http', netloc='', path='movie.douban.com/', params='', query='', fragment='')

from urllib import parse
# 将列表元素拼接成url
url = ['http', 'www', 'baidu', 'com', 'dfdf', 'eddffa'] # 这里至少需要6个元素
print(parse.urlunparse(url))
# 下面是结果6http://www/baidu;com?dfdf#eddffa

# 连接两个参数的url, 将第二个参数中缺的部分用第一个参数的补齐,如果第二个有完整的路径，则以第二个为主
print(parse.urljoin('https://movie.douban.com/', 'index'))
print(parse.urljoin('https://movie.douban.com/', 'https://accounts.douban.com/login'))
# 下面是结果
https://movie.douban.com/index6     https://accounts.douban.com/login

>>> from urllib import urlencode
>>> data = {
...     'a': 'test',
...     'name': '魔兽'
... }
>>> print urlencode(data)
a=test&name=%C4%A7%CA%DE
如果只想对一个字符串进行urlencode转换，怎么办？urllib提供另外一个函数：quote()
>>> from urllib import quote
>>> quote('魔兽')
'%C4%A7%CA%DE'

>>> from urllib import unquote
>>> unquote('%C4%A7%CA%DE')
'\xc4\xa7\xca\xde'
>>> print unquote('%C4%A7%CA%DE')
魔兽

# 导入parse模块
from urllib import parse
#调用parse模块的urlencode()进行编码
query_string = {'wd':'爬虫'}
result = parse.urlencode(query_string)
# format函数格式化字符串，进行url拼接
url = 'http://www.baidu.com/s?{}'.format(result)
print(url)

from urllib import parse
url = "http://www.baidu.com/s?wd={}"
words = input('请输入内容')
#quote()只能对字符串进行编码
query_string = parse.quote(words)
url = url.format(query_string)
print(url)

from urllib import parse
string = '%E7%88%AC%E8%99%AB'
result = parse.unquote(string)
print(result)

 query1= 'http://www.baidu.com/s?'
 query2='wd=%E7%88%AC%E8%99%AB'
 url = query1 + query2

  query2='wd=%E7%88%AC%E8%99%AB'
  url = 'http://www.baidu.com/s?%s'% query2

# 导入parse模块
from urllib import parse
#调用parse模块的urlencode()进行编码
query_string = {'wd':'爬虫'}
result = parse.urlencode(query_string)
# format函数格式化字符串，进行url拼接
url = 'http://www.baidu.com/s?{}'.format(result)
print(url)