# urllib的parse模塊：實現(xiàn)url的解析氢哮、合并、編碼、解碼
from urllib import parse
# 實現(xiàn)url的識別和分段(協(xié)議蒜鸡、域玩焰、路徑 #錨點)
url = 'https://www.1217B.com/daxuesheng?name=zhangsan#123'
"""
url:要解析和拆分的url
scheme：設(shè)置協(xié)議荠呐，只有在沒有協(xié)議的情況下才會生效
allow_fragments=True:是否忽略錨點挥吵，默認(rèn)True不忽略

(scheme='https'（協(xié)議）, 
netloc='www.1217B.com'（域）, 
path='/daxuesheng'（路徑）, 
params=''（可選項）, # https://fe-api.zhaopin.com/c/i/sou?start=90&pageSize=90&cityId=489&workExperience=-1&education=-1&companyType=-1&employmentType=-1&jobWelfareTag=-1&kw=技術(shù)&kt=3&_v=0.92285166&x-zp-page-request-id=93cd5308082743a794c9d50e646f8e08-1545304784592-499104

query='name=zhangsan'（查詢參數(shù)）, 
fragment='123'（錨點）)
"""
# 拆分
url = 'https://fe-api.zhaopin.com/c/i/sou?&pageSize=90&cityId=489&workExperience=-1&education=-1&companyType=-1&employmentType=-1&jobWelfareTag=-1&kw=技術(shù)&kt=3&_v=0.92285166&x-zp-page-request-id=93cd5308082743a794c9d50e646f8e08-1545304784592-499104'
result = parse.urlparse(url)
str = 'start={}'.format()
print('a',result)
# 取出拆分后的某一個參數(shù)
print(result.scheme)

#url組合 ，data長度必須是6的可迭代對象
data = [sub_str for sub_str in result]
print('---',data)
full_url = parse.urlunparse(data)
print('urlunparse',full_url)

# url拼接祭椰，需要傳遞一個基類的url臭家，根據(jù)基類將某個不完整的url拼接完成
sub_url = '/p/123456'
# 基類url
base_url = 'https://www.1217B.com/daxuesheng?name=zhangsan#123'
full_url = parse.urljoin(base_url,sub_url)
print('urljoin:',full_url)

# 將字典類型的參數(shù)轉(zhuǎn)為url的編碼格式的字符串
parmars = {
    'name':'扎昂三',
    'class':'1712B'
}
result = parse.urlencode(parmars)
print('urlencode:',result)

# 反序列化，將url格式編碼的字符串轉(zhuǎn)化為字典類型
result = parse.parse_qs(result)
print('parse.parse.qs:',result)

# 可以將中文字符轉(zhuǎn)化為url編碼格式
kw = '某某某'
result = parse.quote(kw)
print('parse.quote',result)

# 將url編碼解碼
result = parse.unquote(result)
print('parse.unquote:',result)
# encode方淤、join：最常用的兩個方法