def setPageInfo(self):
"""Sets basic page info, required for almost everything"""
followRedir = self.followRedir
params = {'action': 'query'}
if self.pageid:
params['pageids'] = self.pageid
else:
params['titles'] = self.title
if followRedir:
params['redirects'] = ''
req = api.APIRequest(self.site, params)
response = req.query()
self.pageid = response['query']['pages'].keys()[0]
if self.pageid > 0:
self.exists = True
if 'missing' in response['query']['pages'][str(self.pageid)]:
if not self.title:
# Pageids are never recycled, so a bad pageid with no title will never work
raise wiki.WikiError("Bad pageid given with no title")
self.exists = False
if 'invalid' in response['query']['pages'][str(self.pageid)]:
raise BadTitle(self.title)
if 'title' in response['query']['pages'][str(self.pageid)]:
self.title = response['query']['pages'][str(
self.pageid)]['title'].encode('utf-8')
self.namespace = int(response['query']['pages'][str(
self.pageid)]['ns'])
if self.namespace is not 0:
self.unprefixedtitle = self.title.split(':', 1)[1]
else:
self.unprefixedtitle = self.title
self.pageid = int(self.pageid)
if self.pageid < 0:
self.pageid = 0
return self
def __getHistoryInternal(self, direction, content, limit, rvcontinue):
if self.pageid == 0 and not self.title:
self.setPageInfo()
if not self.exists:
raise NoPage
if direction != 'newer' and direction != 'older':
raise wiki.WikiError("direction must be 'newer' or 'older'")
params = {
'action': 'query',
'prop': 'revisions',
'rvdir': direction,
'rvprop': 'ids|flags|timestamp|user|userid|size|sha1|comment',
'continue': '',
'rvlimit': limit
}
if self.pageid:
params['pageids'] = self.pageid
else:
params['titles'] = self.title
if content:
params['rvprop'] += '|content'
if rvcontinue:
params['continue'] = rvcontinue['continue']
params['rvcontinue'] = rvcontinue['rvcontinue']
req = api.APIRequest(self.site, params)
response = req.query(False)
id = response['query']['pages'].keys()[0]
if not self.pageid:
self.pageid = int(id)
revs = response['query']['pages'][id]['revisions']
rvc = None
if 'continue' in response:
rvc = response['continue']
return (revs, rvc)
def __init__(self,
site,
title=False,
check=True,
followRedir=True,
section=False,
sectionnumber=False,
pageid=False,
namespace=False):
"""
wiki - A wiki object
title - The page title, as a string or unicode object
check - Checks for existence, normalizes title, required for most things
followRedir - follow redirects (check must be true)
section - the section name
sectionnumber - the section number
pageid - pageid, can be in place of title
namespace - use to set the namespace prefix *if its not already in the title*
"""
# Initialize instance vars from function args
if not title and not pageid:
raise wiki.WikiError("No title or pageid given")
self.site = site
if pageid:
self.pageid = int(pageid)
else:
self.pageid = 0
self.followRedir = followRedir
self.title = title
self.unprefixedtitle = False # will be set later
self.urltitle = ''
self.wikitext = ''
self.templates = []
self.links = []
self.categories = []
self.exists = True # If we're not going to check, assume it does
self.protection = {}
self.namespace = namespace
# Things that need to be done before anything else
if self.title:
self.title = self.title.replace('_', ' ')
if self.namespace:
if namespace not in self.site.namespaces.keys():
raise BadNamespace(namespace)
if self.title:
self.unprefixedtitle = self.title
self.title = ':'.join(
(self.site.namespaces[self.namespace]['*'],
self.title.decode('utf8')))
if int(self.namespace) is 0 and self.title:
self.namespace = int(self.namespace)
self.unprefixedtitle = self.title
# Setting page info with API, should set:
# pageid, exists, title, unprefixedtitle, namespace
if check:
self.setPageInfo()
else:
if self.namespace is False and self.title:
self.namespace = namespaceDetect(self.title, self.site)
if self.namespace is not 0:
nsname = self.site.namespaces[self.namespace]['*']
self.unprefixedtitle = self.title.split(':', 1)[1]
self.title = ':'.join((nsname, self.unprefixedtitle))
else:
self.unprefixedtitle = self.title
if section or sectionnumber is not False:
self.setSection(section, sectionnumber)
else:
self.section = False
if title:
if not isinstance(self.title, unicode):
self.title = unicode(self.title, 'utf-8')
if not isinstance(self.unprefixedtitle, unicode):
self.unprefixedtitle = unicode(self.unprefixedtitle, 'utf-8')
self.urltitle = urllib.quote(self.title.encode('utf-8')).replace(
'%20', '_').replace('%2F', '/')
def __init__(self,
site,
title=False,
check=True,
followRedir=True,
section=False,
sectionnumber=False,
pageid=False):
"""
wiki - A wiki object
title - The page title, as a string or unicode object
check - Checks for existence, normalizes title, required for most things
followRedir - follow redirects (check must be true)
section - the section name
sectionnumber - the section number
pageid - pageid, can be in place of title
"""
if not title and not pageid:
raise wiki.WikiError("No title or pageid given")
self.site = site
if pageid:
self.pageid = int(pageid)
else:
self.pageid = 0
self.followRedir = followRedir
self.title = title
self.wikitext = ''
self.templates = []
self.links = []
self.exists = True # If we're not going to check, assume it does
self.protection = {}
if check:
self.setPageInfo()
else: # Guess at some stuff
self.namespace = False
if self.title:
self.title = self.title.replace('_', ' ')
bits = self.title.split(':', 1)
if len(bits) == 1 or bits[0] == '':
self.namespace = 0
else:
nsprefix = bits[0].lower(
) # wp:Foo and caTEGory:Foo are normalized by MediaWiki
for ns in self.site.namespaces:
if nsprefix == self.site.namespaces[ns]['*'].lower():
self.namespace = int(ns)
self.title = self.site.namespaces[ns][
'*'] + ':' + bits[1]
break
else:
if self.site.NSaliases:
for ns in self.site.NSaliases:
if nsprefix == ns.lower():
self.namespace = int(
self.site.NSaliases[ns])
self.title = self.site.namespaces[
self.namespace]['*'] + ':' + bits[1]
break
if not self.namespace:
self.namespace = 0
else:
self.namespace = 0
if section or sectionnumber is not False:
self.setSection(section, sectionnumber)
else:
self.section = False
if title and not isinstance(self.title, unicode):
self.title = unicode(self.title, 'utf-8')
self.urltitle = urllib.quote(self.title.encode('utf-8')).replace(
'%20', '_').replace('%2F', '/')
elif title:
self.urltitle = urllib.quote(self.title.encode('utf-8')).replace(
'%20', '_').replace('%2F', '/')
else:
self.urltitle = False