Hopiu/linkchecker
1
0
Fork 0
mirror of https://github.com/Hopiu/linkchecker.git synced 2026-04-29 10:34:42 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Updated ignored schemes.

Browse source
This commit is contained in:
Bastian Kleineidam 2012-09-22 16:18:37 +02:00
parent 1c59cb4d4c
commit 653b5f27dd
1 changed files with 88 additions and 21 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

109
linkcheck/checker/unknownurl.py
View file

@ -22,48 +22,115 @@ import re
from . import urlbase
from .const import WARN_IGNORE_URL
ignored_schemes = r"""^(
acap # application configuration access protocol
|afs # Andrew File System global file names
|chrome # Mozilla specific
# from http://www.iana.org/assignments/uri-schemes.html
ignored_schemes_permanent = r"""
aaas? # Diameter Protocol
|about # about
|acap # application configuration access protocol
|cap # Calendar Access Protocol
|cid # content identifier
|clsid # Microsoft specific
|crid # TV-Anytime Content Reference Identifier
|data # data
|dav # dav
|fax # fax
|feed # RSS or Atom feeds
|find # Mozilla specific
|dict # dictionary service protocol
|dns # Domain Name System
|geo # Geographic Locations
|go # go
|gopher # Gopher
|h323 # H.323
|iax # Inter-Asterisk eXchange Version 2
|icap # Internet Content Adaptation Protocol
|im # Instant Messaging
|imap # internet message access protocol
|ircs? # internet relay chat
|isbn # ISBN (int. book numbers)
|javascript # JavaScript
|info # Information Assets with Identifiers in Public Namespaces
|ipp # Internet Printing Protocol
|iris # Internet Registry Information Service
|iris\.(beep|xpcs?|lwz) #
|ldap # Lightweight Directory Access Protocol
|mailserver # Access to data available from mail servers
|mid # message identifier
|mms # multimedia stream
|modem # modem
|msrps? # Message Session Relay Protocol
|mtqp # Message Tracking Query Protocol
|mupdate # Mailbox Update (MUPDATE) Protocol
|nfs # network file system protocol
|nih? #
|opaquelocktoken # opaquelocktoken
|pop # Post Office Protocol v3
|prospero # Prospero Directory Service
|rsync # rsync protocol
|pres # Presence
|rtsp # real time streaming protocol
|rtspu # real time streaming protocol
|service # service location
|session #
|shttp # secure HTTP
|sip # session initiation protocol
|skype # Skype
|sieve # ManageSieve Protocol
|sips? # session initiation protocol
|sms # Short Message Service
|snmp # Simple Network Management Protocol
|soap\.beeps? #
|steam # Steam browser protocol
|tag #
|tel # telephone
|tftp # Trivial File Transfer Protocol
|thismessage #
|tip # Transaction Internet Protocol
|tn3270 # Interactive 3270 emulation sessions
|tv # TV Broadcasts
|urn # Uniform Resource Names
|vemmi # versatile multimedia interface
|wais # Wide Area Information Servers
|wss? # WebSocket connections
|xcon(-userid)? #
|xmlrpc\.beeps? #
|xmpp #
|z39\.50r # Z39.50 Retrieval
|z39\.50s # Z39.50 Session
):"""
"""
ignored_schemes_provisional = r"""
|afs # Andrew File System global file names
|callto #
|com-eventbrite-attendee #
|dlna-play(single|container) #
|dtn # DTNRG research and development
|dvb #
|hcp #
|icon #
|ipn #
|jms # Java Message Service
|mms # multimedia stream
|ms-help #
|msnim #
|oid #
|res #
|rsync # rsync protocol
|skype # Skype
|view-source #
"""
ignored_schemes_historical = r"""
|fax # fax
|mailserver # Access to data available from mail servers
|modem # modem
|prospero # Prospero Directory Service
|videotex #
|wais # Wide Area Information Servers
|z39\.50 # Z39.50 information access
"""
ignored_schemes_other = r"""
|chrome # Mozilla specific
|clsid # Microsoft specific
|feed # RSS or Atom feeds
|find # Mozilla specific
|isbn # ISBN (int. book numbers)
|ircs? # internet relay chat
|javascript # JavaScript
"""
ignored_schemes = "^(%s%s%s%s):" % (
ignored_schemes_permanent,
ignored_schemes_provisional,
ignored_schemes_historical,
ignored_schemes_other,
)
ignored_schemes_re = re.compile(ignored_schemes, re.VERBOSE)
is_unknown_url = ignored_schemes_re.search