python urllib模块里面一些函数
2011-04-14 13:26
495 查看
urllib里面的一些函数,发现挺有用,特记在这里.备以后使用.
# splittype('type:opaquestring') --> 'type', 'opaquestring'
# splithost('//host[:port]/path') --> 'host[:port]', '/path'
# splituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'
# splitpasswd('user:passwd') -> 'user', 'passwd'
# splitport('host:port') --> 'host', 'port'
# splitquery('/path?query') --> '/path', 'query'
# splittag('/path#tag') --> '/path', 'tag'
# splitattr('/path;attr1=value1;attr2=value2;...') ->
# '/path', ['attr1=value1', 'attr2=value2', ...]
# splitvalue('attr=value') --> 'attr', 'value'
def splittype(url):
"""splittype('type:opaquestring') --> 'type', 'opaquestring'."""
global _typeprog
if _typeprog is None:
import re
_typeprog = re.compile('^([^/:]+):')
match = _typeprog.match(url)
if match:
scheme = match.group(1)
return scheme.lower(), url[len(scheme) + 1:]
return None, url
_hostprog = None
def splithost(url):
"""splithost('//host[:port]/path') --> 'host[:port]', '/path'."""
global _hostprog
if _hostprog is None:
import re
_hostprog = re.compile('^//([^/?]*)(.*)$')
match = _hostprog.match(url)
if match: return match.group(1, 2)
return None, url
_userprog = None
def splituser(host):
"""splituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'."""
global _userprog
if _userprog is None:
import re
_userprog = re.compile('^(.*)@(.*)$')
match = _userprog.match(host)
if match: return map(unquote, match.group(1, 2))
return None, host
_passwdprog = None
def splitpasswd(user):
"""splitpasswd('user:passwd') -> 'user', 'passwd'."""
global _passwdprog
if _passwdprog is None:
import re
_passwdprog = re.compile('^([^:]*):(.*)$',re.S)
match = _passwdprog.match(user)
if match: return match.group(1, 2)
return user, None
# splittag('/path#tag') --> '/path', 'tag'
_portprog = None
def splitport(host):
"""splitport('host:port') --> 'host', 'port'."""
global _portprog
if _portprog is None:
import re
_portprog = re.compile('^(.*):([0-9]+)$')
match = _portprog.match(host)
if match: return match.group(1, 2)
return host, None
_nportprog = None
def splitnport(host, defport=-1):
"""Split host and port, returning numeric port.
Return given default port if no ':' found; defaults to -1.
Return numerical port if a valid number are found after ':'.
Return None if ':' but not a valid number."""
global _nportprog
if _nportprog is None:
import re
_nportprog = re.compile('^(.*):(.*)$')
match = _nportprog.match(host)
if match:
host, port = match.group(1, 2)
try:
if not port: raise ValueError, "no digits"
nport = int(port)
except ValueError:
nport = None
return host, nport
return host, defport
_queryprog = None
def splitquery(url):
"""splitquery('/path?query') --> '/path', 'query'."""
global _queryprog
if _queryprog is None:
import re
_queryprog = re.compile('^(.*)\?([^?]*)$')
match = _queryprog.match(url)
if match: return match.group(1, 2)
return url, None
_tagprog = None
def splittag(url):
"""splittag('/path#tag') --> '/path', 'tag'."""
global _tagprog
if _tagprog is None:
import re
_tagprog = re.compile('^(.*)#([^#]*)$')
match = _tagprog.match(url)
if match: return match.group(1, 2)
return url, None
def splitattr(url):
"""splitattr('/path;attr1=value1;attr2=value2;...') ->
'/path', ['attr1=value1', 'attr2=value2', ...]."""
words = url.split(';')
return words[0], words[1:]
_valueprog = None
def splitvalue(attr):
"""splitvalue('attr=value') --> 'attr', 'value'."""
global _valueprog
if _valueprog is None:
import re
_valueprog = re.compile('^([^=]*)=(.*)$')
match = _valueprog.match(attr)
if match: return match.group(1, 2)
return attr, None
# splittype('type:opaquestring') --> 'type', 'opaquestring'
# splithost('//host[:port]/path') --> 'host[:port]', '/path'
# splituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'
# splitpasswd('user:passwd') -> 'user', 'passwd'
# splitport('host:port') --> 'host', 'port'
# splitquery('/path?query') --> '/path', 'query'
# splittag('/path#tag') --> '/path', 'tag'
# splitattr('/path;attr1=value1;attr2=value2;...') ->
# '/path', ['attr1=value1', 'attr2=value2', ...]
# splitvalue('attr=value') --> 'attr', 'value'
def splittype(url):
"""splittype('type:opaquestring') --> 'type', 'opaquestring'."""
global _typeprog
if _typeprog is None:
import re
_typeprog = re.compile('^([^/:]+):')
match = _typeprog.match(url)
if match:
scheme = match.group(1)
return scheme.lower(), url[len(scheme) + 1:]
return None, url
_hostprog = None
def splithost(url):
"""splithost('//host[:port]/path') --> 'host[:port]', '/path'."""
global _hostprog
if _hostprog is None:
import re
_hostprog = re.compile('^//([^/?]*)(.*)$')
match = _hostprog.match(url)
if match: return match.group(1, 2)
return None, url
_userprog = None
def splituser(host):
"""splituser('user[:passwd]@host[:port]') --> 'user[:passwd]', 'host[:port]'."""
global _userprog
if _userprog is None:
import re
_userprog = re.compile('^(.*)@(.*)$')
match = _userprog.match(host)
if match: return map(unquote, match.group(1, 2))
return None, host
_passwdprog = None
def splitpasswd(user):
"""splitpasswd('user:passwd') -> 'user', 'passwd'."""
global _passwdprog
if _passwdprog is None:
import re
_passwdprog = re.compile('^([^:]*):(.*)$',re.S)
match = _passwdprog.match(user)
if match: return match.group(1, 2)
return user, None
# splittag('/path#tag') --> '/path', 'tag'
_portprog = None
def splitport(host):
"""splitport('host:port') --> 'host', 'port'."""
global _portprog
if _portprog is None:
import re
_portprog = re.compile('^(.*):([0-9]+)$')
match = _portprog.match(host)
if match: return match.group(1, 2)
return host, None
_nportprog = None
def splitnport(host, defport=-1):
"""Split host and port, returning numeric port.
Return given default port if no ':' found; defaults to -1.
Return numerical port if a valid number are found after ':'.
Return None if ':' but not a valid number."""
global _nportprog
if _nportprog is None:
import re
_nportprog = re.compile('^(.*):(.*)$')
match = _nportprog.match(host)
if match:
host, port = match.group(1, 2)
try:
if not port: raise ValueError, "no digits"
nport = int(port)
except ValueError:
nport = None
return host, nport
return host, defport
_queryprog = None
def splitquery(url):
"""splitquery('/path?query') --> '/path', 'query'."""
global _queryprog
if _queryprog is None:
import re
_queryprog = re.compile('^(.*)\?([^?]*)$')
match = _queryprog.match(url)
if match: return match.group(1, 2)
return url, None
_tagprog = None
def splittag(url):
"""splittag('/path#tag') --> '/path', 'tag'."""
global _tagprog
if _tagprog is None:
import re
_tagprog = re.compile('^(.*)#([^#]*)$')
match = _tagprog.match(url)
if match: return match.group(1, 2)
return url, None
def splitattr(url):
"""splitattr('/path;attr1=value1;attr2=value2;...') ->
'/path', ['attr1=value1', 'attr2=value2', ...]."""
words = url.split(';')
return words[0], words[1:]
_valueprog = None
def splitvalue(attr):
"""splitvalue('attr=value') --> 'attr', 'value'."""
global _valueprog
if _valueprog is None:
import re
_valueprog = re.compile('^([^=]*)=(.*)$')
match = _valueprog.match(attr)
if match: return match.group(1, 2)
return attr, None
相关文章推荐
- Python os 模块中一些重要函数和变量
- Python urllib模块与urlopen()函数解析疵
- Python urllib模块与urlopen()函数解析偎
- python pandas中的random模块一些函数的用法
- 转载 - Python里面关于 模块 和 包 和 __init__.py 的一些事
- python 模块、作用域及一些函数
- Python 3.6模块学习urllib的urllib.request.urlopen()函数学习
- python爬虫学习(一)通过urllib2模块获取html,设置用户代理
- python爬虫之urllib模块和requests模块学习
- Head_first_python 第二章共享你的代码 函数模块
- Python urllib模块学习
- 【python】整理一些实用的函数
- Python模块学习 --- urllib
- python常用函数库及模块巧妙用法汇总
- Python 一些特别函数 __getitem__ __getattr__
- Dive Into Python 学习记录1-函数/模块导入/字典/列表/元组/字符串分割、连接、格式化/映射list/
- python里面的join函数用法及简单示例
- 【转】关于python cookielib,urllib2,httplib 模块(HTTP状态码)
- python的urllib模块显示下载进度示例
- python中doctest自我测试(测试模块中的函数是否对)