def __init__(self,
generator,
acceptall=False,
limit=None,
ignorepdf=False):
"""
- generator : Page generator
- acceptall : boolean, is -always on ?
- limit : int, stop after n modified pages
- ignorepdf : boolean
"""
self.generator = generator
self.acceptall = acceptall
self.limit = limit
self.ignorepdf = ignorepdf
self.site = pywikibot.getSite()
# Check
manual = 'mw:Manual:Pywikibot/refLinks'
code = None
for alt in [self.site.code] + i18n._altlang(self.site.code):
if alt in localized_msg:
code = alt
break
if code:
manual += '/%s' % code
self.msg = i18n.twtranslate(self.site, 'reflinks-msg', locals())
self.stopPage = pywikibot.Page(
self.site, pywikibot.translate(self.site, stopPage))
local = pywikibot.translate(self.site, badtitles)
if local:
bad = '(' + globalbadtitles + '|' + local + ')'
else:
bad = globalbadtitles
self.titleBlackList = re.compile(bad, re.I | re.S | re.X)
self.norefbot = noreferences.NoReferencesBot(None)
self.deduplicator = DuplicateReferences()
try:
self.stopPageRevId = self.stopPage.latestRevision()
except pywikibot.NoPage:
pywikibot.output(u'The stop page %s does not exist' %
self.stopPage.title(asLink=True))
raise
# Regex to grasp content-type meta HTML tag in HTML source
self.META_CONTENT = re.compile(ur'(?i)<meta[^>]*content\-type[^>]*>')
# Extract the encoding from a charset property (from content-type !)
self.CHARSET = re.compile(ur'(?i)charset\s*=\s*(?P<enc>[^\'";>/]*)')
# Extract html title from page
self.TITLE = re.compile(ur'(?is)(?<=<title>).*?(?=</title>)')
# Matches content inside <script>/<style>/HTML comments
self.NON_HTML = re.compile(
ur'(?is)<script[^>]*>.*?</script>|<style[^>]*>.*?</style>|<!--.*?-->|<!\[CDATA\[.*?\]\]>'
)
# Authorized mime types for HTML pages
self.MIME = re.compile(
ur'application/(?:xhtml\+xml|xml)|text/(?:ht|x)ml')
def __init__(self, generator, **kwargs):
"""- generator : Page generator."""
self.availableOptions.update({
'ignorepdf': False, # boolean
'limit': None, # int, stop after n modified pages
'summary': None,
})
super(ReferencesRobot, self).__init__(**kwargs)
self.generator = generator
self.site = pywikibot.Site()
self._use_fake_user_agent = config.fake_user_agent_default.get(
'reflinks', False)
# Check
manual = 'mw:Manual:Pywikibot/refLinks'
code = None
for alt in [self.site.code] + i18n._altlang(self.site.code):
if alt in localized_msg:
code = alt
break
if code:
manual += '/{0}'.format(code)
if self.getOption('summary') is None:
self.msg = i18n.twtranslate(self.site, 'reflinks-msg', locals())
else:
self.msg = self.getOption('summary')
local = i18n.translate(self.site, badtitles)
if local:
bad = '(' + globalbadtitles + '|' + local + ')'
else:
bad = globalbadtitles
self.titleBlackList = re.compile(bad, re.I | re.S | re.X)
self.norefbot = noreferences.NoReferencesBot(None, verbose=False)
self.deduplicator = DuplicateReferences(self.site)
self.site_stop_page = i18n.translate(self.site, stop_page)
if self.site_stop_page:
self.stop_page = pywikibot.Page(self.site, self.site_stop_page)
if self.stop_page.exists():
self.stop_page_rev_id = self.stop_page.latest_revision_id
else:
pywikibot.warning('The stop page {0} does not exist'
.format(self.stop_page.title(as_link=True)))
# Regex to grasp content-type meta HTML tag in HTML source
self.META_CONTENT = re.compile(br'(?i)<meta[^>]*content\-type[^>]*>')
# Extract the encoding from a charset property (from content-type !)
self.CHARSET = re.compile(r'(?i)charset\s*=\s*(?P<enc>[^\'",;>/]*)')
# Extract html title from page
self.TITLE = re.compile(r'(?is)(?<=<title>).*?(?=</title>)')
# Matches content inside <script>/<style>/HTML comments
self.NON_HTML = re.compile(
br'(?is)<script[^>]*>.*?</script>|<style[^>]*>.*?</style>|'
br'<!--.*?-->|<!\[CDATA\[.*?\]\]>')
# Authorized mime types for HTML pages
self.MIME = re.compile(
r'application/(?:xhtml\+xml|xml)|text/(?:ht|x)ml')
def __init__(self, generator, **kwargs):
"""
- generator : Page generator
"""
self.availableOptions.update({
'ignorepdf': False, # boolean
'limit': None, # int, stop after n modified pages
'summary': None,
})
super(ReferencesRobot, self).__init__(**kwargs)
self.generator = generator
self.site = pywikibot.Site()
# Check
manual = 'mw:Manual:Pywikibot/refLinks'
code = None
for alt in [self.site.code] + i18n._altlang(self.site.code):
if alt in localized_msg:
code = alt
break
if code:
manual += '/%s' % code
if self.getOption('summary') is None:
self.msg = i18n.twtranslate(self.site, 'reflinks-msg', locals())
else:
self.msg = self.getOption('summary')
self.stopPage = pywikibot.Page(self.site,
pywikibot.translate(self.site, stopPage))
local = pywikibot.translate(self.site, badtitles)
if local:
bad = '(' + globalbadtitles + '|' + local + ')'
else:
bad = globalbadtitles
self.titleBlackList = re.compile(bad, re.I | re.S | re.X)
self.norefbot = noreferences.NoReferencesBot(None, verbose=False)
self.deduplicator = DuplicateReferences()
try:
self.stopPageRevId = self.stopPage.latestRevision()
except pywikibot.NoPage:
pywikibot.output(u'The stop page %s does not exist'
% self.stopPage.title(asLink=True))
raise
# Regex to grasp content-type meta HTML tag in HTML source
self.META_CONTENT = re.compile(r'(?i)<meta[^>]*content\-type[^>]*>')
# Extract the encoding from a charset property (from content-type !)
self.CHARSET = re.compile(r'(?i)charset\s*=\s*(?P<enc>[^\'";>/]*)')
# Extract html title from page
self.TITLE = re.compile(r'(?is)(?<=<title>).*?(?=</title>)')
# Matches content inside <script>/<style>/HTML comments
self.NON_HTML = re.compile(
r'(?is)<script[^>]*>.*?</script>|<style[^>]*>.*?</style>|<!--.*?-->|<!\[CDATA\[.*?\]\]>')
# Authorized mime types for HTML pages
self.MIME = re.compile(
r'application/(?:xhtml\+xml|xml)|text/(?:ht|x)ml')
def __init__(self, **kwargs):
"""Initializer."""
super().__init__(**kwargs)
self._use_fake_user_agent = config.fake_user_agent_default.get(
'reflinks', False)
# Check
manual = 'mw:Manual:Pywikibot/refLinks'
code = None
for alt in [self.site.code] + i18n._altlang(self.site.code):
if alt in localized_msg:
code = alt
break
if code:
manual += '/{}'.format(code)
if self.opt.summary:
self.msg = self.opt.summary
else:
self.msg = i18n.twtranslate(self.site, 'reflinks-msg', locals())
local = i18n.translate(self.site, badtitles)
if local:
bad = '({}|{})'.format(globalbadtitles, local)
else:
bad = globalbadtitles
self.titleBlackList = re.compile(bad, re.I | re.S | re.X)
self.norefbot = noreferences.NoReferencesBot(verbose=False)
self.deduplicator = DuplicateReferences(self.site)
self.site_stop_page = i18n.translate(self.site, stop_page)
if self.site_stop_page:
self.stop_page = pywikibot.Page(self.site, self.site_stop_page)
if self.stop_page.exists():
self.stop_page_rev_id = self.stop_page.latest_revision_id
else:
pywikibot.warning('The stop page {} does not exist'.format(
self.stop_page.title(as_link=True)))
# Regex to grasp content-type meta HTML tag in HTML source
self.META_CONTENT = re.compile(
br'(?i)<meta[^>]*(?:content\-type|charset)[^>]*>')
# Extract the encoding from a charset property (from content-type !)
self.CHARSET = re.compile(
r'(?i)charset\s*=\s*(?P<enc>(?P<q>[\'"]?)[^\'",;>/]*(?P=q))')
# Extract html title from page
self.TITLE = re.compile(r'(?is)(?<=<title>).*?(?=</title>)')
# Matches content inside <script>/<style>/HTML comments
self.NON_HTML = re.compile(
br'(?is)<script[^>]*>.*?</script>|<style[^>]*>.*?</style>|'
br'<!--.*?-->|<!\[CDATA\[.*?\]\]>')
# Authorized mime types for HTML pages
self.MIME = re.compile(
r'application/(?:xhtml\+xml|xml)|text/(?:ht|x)ml')
def __init__(self, generator, acceptall=False, limit=None, ignorepdf=False):
"""
- generator : Page generator
- acceptall : boolean, is -always on ?
- limit : int, stop after n modified pages
- ignorepdf : boolean
"""
self.generator = generator
self.acceptall = acceptall
self.limit = limit
self.ignorepdf = ignorepdf
self.site = pywikibot.getSite()
# Check
manual = "mw:Manual:Pywikibot/refLinks"
code = None
for alt in [self.site.code] + i18n._altlang(self.site.code):
if alt in localized_msg:
code = alt
break
if code:
manual += "/%s" % code
self.msg = i18n.twtranslate(self.site, "reflinks-msg", locals())
self.stopPage = pywikibot.Page(self.site, pywikibot.translate(self.site, stopPage))
local = pywikibot.translate(self.site, badtitles)
if local:
bad = "(" + globalbadtitles + "|" + local + ")"
else:
bad = globalbadtitles
self.titleBlackList = re.compile(bad, re.I | re.S | re.X)
self.norefbot = noreferences.NoReferencesBot(None)
self.deduplicator = DuplicateReferences()
try:
self.stopPageRevId = self.stopPage.latestRevision()
except pywikibot.NoPage:
pywikibot.output(u"The stop page %s does not exist" % self.stopPage.title(asLink=True))
raise
# Regex to grasp content-type meta HTML tag in HTML source
self.META_CONTENT = re.compile(ur"(?i)<meta[^>]*content\-type[^>]*>")
# Extract the encoding from a charset property (from content-type !)
self.CHARSET = re.compile(ur'(?i)charset\s*=\s*(?P<enc>[^\'";>/]*)')
# Extract html title from page
self.TITLE = re.compile(ur"(?is)(?<=<title>).*?(?=</title>)")
# Matches content inside <script>/<style>/HTML comments
self.NON_HTML = re.compile(
ur"(?is)<script[^>]*>.*?</script>|<style[^>]*>.*?</style>|<!--.*?-->|<!\[CDATA\[.*?\]\]>"
)
# Authorized mime types for HTML pages
self.MIME = re.compile(ur"application/(?:xhtml\+xml|xml)|text/(?:ht|x)ml")
def __init__(self, generator, **kwargs):
"""- generator : Page generator."""
self.availableOptions.update({
'ignorepdf': False, # boolean
'repair': False, # boolean
'limit': None, # int, stop after n modified pages
'summary': None,
})
super(ReferencesRobot, self).__init__(**kwargs)
self.generator = generator
self.site = pywikibot.Site()
self._use_fake_user_agent = config.fake_user_agent_default.get(
'reflinks', False)
# Check
#manual = 'mw:Manual:Pywikibot/refLinks'
manual = 'Wikipedysta:MastiBot/refLinks'
code = None
for alt in [self.site.code] + i18n._altlang(self.site.code):
if alt in localized_msg:
code = alt
break
if code:
manual += '/%s' % code
if self.getOption('summary') is None:
self.msg = i18n.twtranslate(self.site, 'reflinks-msg', locals())
else:
self.msg = self.getOption('summary')
local = i18n.translate(self.site, badtitles)
if local:
bad = '(' + globalbadtitles + '|' + local + ')'
else:
bad = globalbadtitles
self.titleBlackList = re.compile(bad, re.I | re.S | re.X)
self.norefbot = noreferences.NoReferencesBot(None, verbose=False)
#self.deduplicator = DuplicateReferences()
self.site_stop_page = i18n.translate(self.site, stop_page)
if self.site_stop_page:
self.stop_page = pywikibot.Page(self.site, self.site_stop_page)
if self.stop_page.exists():
self.stop_page_rev_id = self.stop_page.latest_revision_id
else:
pywikibot.warning('The stop page %s does not exist' %
self.stop_page.title(asLink=True))
# Regex that match bare references
if self.getOption('repair'):
self.linksInRef = re.compile(
ur'(?i)<ref(?P<name>[^>]*)>\.?\[?(?P<url>http[s]?:(\/\/[^:\s\?]+?)(\??[^\s<]*?)[^\]\.])(\]|\]\.)?( [^<]*?<!-- Tytuł wygenerowany przez bota -->[ \t]*\])[ \t]*<\/ref>'
)
else:
self.linksInRef = re.compile(
ur'(?i)<ref(?P<name>[^>]*)>\.?\[?(?P<url>http[s]?:(\/\/[^:\s\?]+?)(\??[^\s<]*?)[^\]\.])(\]|\]\.)?[ \t]*<\/ref>'
)
# Regex to grasp content-type meta HTML tag in HTML source
self.META_CONTENT = re.compile(br'(?i)<meta[^>]*content\-type[^>]*>')
# Extract the encoding from a charset property (from content-type !)
self.CHARSET = re.compile(r'(?i)charset\s*=\s*(?P<enc>[^\'",;>/]*)')
# Extract html title from page
#self.TITLE = re.compile(r'(?is)(?<=<title>).*?(?=</title>)')
self.TITLE = re.compile(
r'(?is)(<title[^>]*?>)(?P<title>.*?)(?=</title>)')
# Matches content inside <script>/<style>/HTML comments
self.NON_HTML = re.compile(
br'(?is)<script[^>]*>.*?</script>|<style[^>]*>.*?</style>|'
br'<!--.*?-->|<!\[CDATA\[.*?\]\]>')
# Extract html language from page
self.LANG = re.compile(
r'(?i)(<html[^>]*?lang\s*?=\s*?|<meta\s*?HTTP-EQUIV\s*?=\s*?\"Content-Language\"\s*?CONTENT\s*?=\s*?|<meta property\s*?=\s*?\"og:locale\"\s*?content\s*?=\s*?)\"(?P<lang>.*?)[\_\-\"]'
)
# Authorized mime types for HTML pages
self.MIME = re.compile(
r'application/(?:xhtml\+xml|xml)|text/(?:ht|x)ml')
