本文整理汇总了Python中wikipedia.replaceExcept函数的典型用法代码示例。如果您正苦于以下问题：Python replaceExcept函数的具体用法？Python replaceExcept怎么用？Python replaceExcept使用的例子？那么恭喜您, 这里精选的函数代码示例或许可以为您提供帮助。
在下文中一共展示了replaceExcept函数的15个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: fixSyntaxSave
def fixSyntaxSave(self, text):
exceptions = ['nowiki', 'comment', 'math', 'pre', 'source',
'startspace']
# link to the wiki working on
## TODO: disable this for difflinks and titled links
## http://de.wikipedia.org/w/index.php?title=Wikipedia%3aVandalismusmeldung&diff=103109563&oldid=103109271
## text = pywikibot.replaceExcept(text,
## r'\[https?://%s\.%s\.org/wiki/(?P<link>\S+)\s+(?P<title>.+?)\s?\]'
## % (self.site.lang, self.site.family.name),
## r'[[\g<link>|\g<title>]]', exceptions)
# external link in double brackets
text = pywikibot.replaceExcept(
text,
r'\[\[(?P<url>https?://[^\]]+?)\]\]',
r'[\g<url>]', exceptions)
# external link starting with double bracket
text = pywikibot.replaceExcept(text,
r'\[\[(?P<url>https?://.+?)\]',
r'[\g<url>]', exceptions)
# external link and description separated by a dash, with
# whitespace in front of the dash, so that it is clear that
# the dash is not a legitimate part of the URL.
text = pywikibot.replaceExcept(
text,
r'\[(?P<url>https?://[^\|\] \r\n]+?) +\| *(?P<label>[^\|\]]+?)\]',
r'[\g<url> \g<label>]', exceptions)
# dash in external link, where the correct end of the URL can
# be detected from the file extension. It is very unlikely that
# this will cause mistakes.
text = pywikibot.replaceExcept(
text,
r'\[(?P<url>https?://[^\|\] ]+?(\.pdf|\.html|\.htm|\.php|\.asp|\.aspx|\.jsp)) *\| *(?P<label>[^\|\]]+?)\]',
r'[\g<url> \g<label>]', exceptions)
return text示例2: removeUselessSpaces
def removeUselessSpaces(self, text):
multipleSpacesR = re.compile(' +')
spaceAtLineEndR = re.compile(' $')
exceptions = ['comment', 'math', 'nowiki', 'pre', 'startspace', 'table',
'template']
text = pywikibot.replaceExcept(text, multipleSpacesR, ' ', exceptions)
text = pywikibot.replaceExcept(text, spaceAtLineEndR, '', exceptions)
return text示例3: commonsfiledesc
def commonsfiledesc(self, text):
# section headers to {{int:}} versions
exceptions = ["comment", "includeonly", "math", "noinclude", "nowiki", "pre", "source", "ref", "timeline"]
text = pywikibot.replaceExcept(
text, r"([\r\n]|^)\=\= *Summary *\=\=", r"\1== {{int:filedesc}} ==", exceptions, True
)
text = pywikibot.replaceExcept(
text,
r"([\r\n])\=\= *\[\[Commons:Copyright tags\|Licensing\]\]: *\=\=",
r"\1== {{int:license}} ==",
exceptions,
True,
)
text = pywikibot.replaceExcept(
text,
r"([\r\n])\=\= *(Licensing|License information|{{int:license-header}}) *\=\=",
r"\1== {{int:license}} ==",
exceptions,
True,
)
# frequent field values to {{int:}} versions
text = pywikibot.replaceExcept(
text,
r"([\r\n]\|[Ss]ource *\= *)(?:[Oo]wn work by uploader|[Oo]wn work|[Ee]igene [Aa]rbeit) *([\r\n])",
r"\1{{own}}\2",
exceptions,
True,
)
text = pywikibot.replaceExcept(
text, r"(\| *Permission *\=) *(?:[Ss]ee below|[Ss]iehe unten) *([\r\n])", r"\1\2", exceptions, True
)
# added to transwikied pages
text = pywikibot.replaceExcept(text, r"__NOTOC__", "", exceptions, True)
# tracker element for js upload form
text = pywikibot.replaceExcept(text, r"<!-- *{{ImageUpload\|(?:full|basic)}} *-->", "", exceptions[1:], True)
text = pywikibot.replaceExcept(text, r"{{ImageUpload\|(?:basic|full)}}", "", exceptions, True)
# duplicated section headers
text = pywikibot.replaceExcept(
text,
r"([\r\n]|^)\=\= *{{int:filedesc}} *\=\=(?:[\r\n ]*)\=\= *{{int:filedesc}} *\=\=",
r"\1== {{int:filedesc}} ==",
exceptions,
True,
)
text = pywikibot.replaceExcept(
text,
r"([\r\n]|^)\=\= *{{int:license}} *\=\=(?:[\r\n ]*)\=\= *{{int:license}} *\=\=",
r"\1== {{int:license}} ==",
exceptions,
True,
)
return text示例4: fixArabicLetters
def fixArabicLetters(self, text):
if self.site.lang=='ckb' or self.site.lang=='fa':
exceptions = [
'gallery',
'hyperlink',
'interwiki',
# but changes letters inside wikilinks
#'link',
'math',
'pre',
'template',
'timeline',
'ref',
'source',
'startspace',
'inputbox',
]
# do not change inside file links
namespaces = list(self.site.namespace(6, all = True))
pattern = re.compile(u'\[\[(' + '|'.join(namespaces) + '):.+?\..+?\]\]',
re.UNICODE)
exceptions.append(pattern)
text = pywikibot.replaceExcept(text, u',', u'،', exceptions)
if self.site.lang=='ckb':
text = pywikibot.replaceExcept(text,
ur'ه([.،_<\]\s])',
ur'ە\1', exceptions)
text = pywikibot.replaceExcept(text, u'ه', u'ە', exceptions)
text = pywikibot.replaceExcept(text, u'ه', u'ھ', exceptions)
text = pywikibot.replaceExcept(text, u'ك', u'ک', exceptions)
text = pywikibot.replaceExcept(text, ur'[ىي]', u'ی', exceptions)
# replace persian digits
for i in range(0,10):
if self.site.lang=='ckb':
text = pywikibot.replaceExcept(text,
u'۰۱۲۳۴۵۶۷۸۹'[i],
u'٠١٢٣٤٥٦٧٨٩'[i], exceptions)
else:
text = pywikibot.replaceExcept(text,
u'٠١٢٣٤٥٦٧٨٩'[i],
u'۰۱۲۳۴۵۶۷۸۹'[i], exceptions)
# do not change digits in class, style and table params
pattern = re.compile(u'=".*?"', re.UNICODE)
exceptions.append(pattern)
# do not change digits inside html-tags
pattern = re.compile(u'<[/]*?[^</]+?[/]*?>', re.UNICODE)
exceptions.append(pattern)
exceptions.append('table') #exclude tables for now
for i in range(0,10):
if self.site.lang=='ckb':
text = pywikibot.replaceExcept(text, str(i),
u'٠١٢٣٤٥٦٧٨٩'[i], exceptions)
else:
text = pywikibot.replaceExcept(text, str(i),
u'۰۱۲۳۴۵۶۷۸۹'[i], exceptions)
return text示例5: removeUselessSpaces
def removeUselessSpaces(self, text):
result = []
multipleSpacesR = re.compile(" +")
spaceAtLineEndR = re.compile(" $")
exceptions = ["comment", "math", "nowiki", "pre", "startspace", "table", "template"]
text = pywikibot.replaceExcept(text, multipleSpacesR, " ", exceptions)
text = pywikibot.replaceExcept(text, spaceAtLineEndR, "", exceptions)
return text示例6: fixReferences
def fixReferences(self, text):
#http://en.wikipedia.org/wiki/User:AnomieBOT/source/tasks/OrphanReferenceFixer.pm
exceptions = ['nowiki', 'comment', 'math', 'pre', 'source', 'startspace']
# it should be name = " or name=" NOT name ="
text = re.sub(r'(?i)<ref +name(= *| *=)"', r'<ref name="', text)
#remove empty <ref/>-tag
text = pywikibot.replaceExcept(text, r'(?i)(<ref\s*/>|<ref *>\s*</ref>)', r'', exceptions)
text = pywikibot.replaceExcept(text, r'(?i)<ref\s+([^>]+?)\s*>\s*</ref>', r'<ref \1/>', exceptions)
return text示例7: fixTypo
def fixTypo(self, text):
exceptions = ['nowiki', 'comment', 'math', 'pre', 'source', 'startspace', 'gallery', 'hyperlink', 'interwiki', 'link']
# change <number> ccm -> <number> cm³
text = pywikibot.replaceExcept(text, ur'(\d)\s* ccm', ur'\1 cm³', exceptions)
text = pywikibot.replaceExcept(text, ur'(\d)\s*ccm', ur'\1 cm³', exceptions)
# Solve wrong Nº sign with °C or °F
# additional exception requested on fr-wiki for this stuff
pattern = re.compile(u'«.*?»', re.UNICODE)
exceptions.append(pattern)
text = pywikibot.replaceExcept(text, ur'(\d)\s* [º°]([CF])', ur'\1 °\2', exceptions)
text = pywikibot.replaceExcept(text, ur'(\d)\s*[º°]([CF])', ur'\1 °\2', exceptions)
text = pywikibot.replaceExcept(text, ur'º([CF])', ur'°\1', exceptions)
return text示例8: fixArabicLetters
def fixArabicLetters(self, text):
exceptions = [
'gallery',
'hyperlink',
'interwiki',
# but changes letters inside wikilinks
#'link',
'math',
'pre',
'template',
'timeline',
'ref',
'source',
'startspace',
'inputbox',
]
# valid digits
digits = {
'ckb': u'٠١٢٣٤٥٦٧٨٩',
'fa': u'۰۱۲۳۴۵۶۷۸۹',
}
faChrs = u'ءاآأإئؤبپتثجچحخدذرزژسشصضطظعغفقکگلمنوهیةيك' + digits['fa']
new = digits.pop(self.site.lang)
# This only works if there are only two items in digits dict
old = digits[digits.keys()[0]]
# do not change inside file links
namespaces = list(self.site.namespace(6, all=True))
pattern = re.compile(
u'\[\[(' + '|'.join(namespaces) +
'):.+?\.\w+? *(\|((\[\[.*?\]\])|.)*)?\]\]',
re.UNICODE)
#not to let bot edits in latin content
exceptions.append(re.compile(u"[^%(fa)s] *?\"*? *?, *?[^%(fa)s]"
% {'fa': faChrs}))
exceptions.append(pattern)
text = pywikibot.replaceExcept(text, u',', u'،', exceptions)
if self.site.lang == 'ckb':
text = pywikibot.replaceExcept(text,
ur'ه([.،_<\]\s])',
ur'ە\1', exceptions)
text = pywikibot.replaceExcept(text, u'ه', u'ە', exceptions)
text = pywikibot.replaceExcept(text, u'ه', u'ھ', exceptions)
text = pywikibot.replaceExcept(text, u'ك', u'ک', exceptions)
text = pywikibot.replaceExcept(text, u'[ىي]', u'ی', exceptions)
return text
# replace persian/arabic digits
## deactivated due to bug #3539407
for i in xrange(0, 10):
text = pywikibot.replaceExcept(text, old[i], new[i], exceptions)
# do not change digits in class, style and table params
pattern = re.compile(u'\w+=(".+?"|\d+)', re.UNICODE)
exceptions.append(pattern)
# do not change digits inside html-tags
pattern = re.compile(u'<[/]*?[^</]+?[/]*?>', re.UNICODE)
exceptions.append(pattern)
exceptions.append('table') # exclude tables for now
# replace digits
for i in xrange(0, 10):
text = pywikibot.replaceExcept(text, str(i), new[i], exceptions)
return text示例9: commonsfiledesc
def commonsfiledesc(self, text):
# section headers to {{int:}} versions
exceptions = ['comment', 'includeonly', 'math', 'noinclude', 'nowiki',
'pre', 'source', 'ref', 'timeline']
text = pywikibot.replaceExcept(text,
r"([\r\n]|^)\=\= *Summary *\=\=",
r"\1== {{int:filedesc}} ==",
exceptions, True)
text = pywikibot.replaceExcept(
text,
r"([\r\n])\=\= *\[\[Commons:Copyright tags\|Licensing\]\]: *\=\=",
r"\1== {{int:license-header}} ==", exceptions, True)
text = pywikibot.replaceExcept(
text,
r"([\r\n])\=\= *(Licensing|License information|{{int:license}}) *\=\=",
r"\1== {{int:license-header}} ==", exceptions, True)
# frequent field values to {{int:}} versions
text = pywikibot.replaceExcept(
text,
r'([\r\n]\|[Ss]ource *\= *)(?:[Oo]wn work by uploader|[Oo]wn work|[Ee]igene [Aa]rbeit) *([\r\n])',
r'\1{{own}}\2', exceptions, True)
text = pywikibot.replaceExcept(
text,
r'(\| *Permission *\=) *(?:[Ss]ee below|[Ss]iehe unten) *([\r\n])',
r'\1\2', exceptions, True)
# added to transwikied pages
text = pywikibot.replaceExcept(text, r'__NOTOC__', '', exceptions, True)
# tracker element for js upload form
text = pywikibot.replaceExcept(
text,
r'<!-- *{{ImageUpload\|(?:full|basic)}} *-->',
'', exceptions[1:], True)
text = pywikibot.replaceExcept(text, r'{{ImageUpload\|(?:basic|full)}}',
'', exceptions, True)
# duplicated section headers
text = pywikibot.replaceExcept(
text,
r'([\r\n]|^)\=\= *{{int:filedesc}} *\=\=(?:[\r\n ]*)\=\= *{{int:filedesc}} *\=\=',
r'\1== {{int:filedesc}} ==', exceptions, True)
text = pywikibot.replaceExcept(
text,
r'([\r\n]|^)\=\= *{{int:license-header}} *\=\=(?:[\r\n ]*)\=\= *{{int:license-header}} *\=\=',
r'\1== {{int:license-header}} ==', exceptions, True)
return text示例10: fixSyntaxSave
def fixSyntaxSave(self, text):
exceptions = ['nowiki', 'comment', 'math', 'pre', 'source', 'startspace']
# external link in double brackets
text = pywikibot.replaceExcept(text, r'\[\[(?P<url>https?://[^\]]+?)\]\]', r'[\g<url>]', exceptions)
# external link starting with double bracket
text = pywikibot.replaceExcept(text, r'\[\[(?P<url>https?://.+?)\]', r'[\g<url>]', exceptions)
# external link and description separated by a dash, with
# whitespace in front of the dash, so that it is clear that
# the dash is not a legitimate part of the URL.
text = pywikibot.replaceExcept(text, r'\[(?P<url>https?://[^\|\] \r\n]+?) +\| *(?P<label>[^\|\]]+?)\]', r'[\g<url> \g<label>]', exceptions)
# dash in external link, where the correct end of the URL can
# be detected from the file extension. It is very unlikely that
# this will cause mistakes.
text = pywikibot.replaceExcept(text, r'\[(?P<url>https?://[^\|\] ]+?(\.pdf|\.html|\.htm|\.php|\.asp|\.aspx|\.jsp)) *\| *(?P<label>[^\|\]]+?)\]', r'[\g<url> \g<label>]', exceptions)
return text示例11: translateAndCapitalizeNamespaces
def translateAndCapitalizeNamespaces(self, text):
"""
Makes sure that localized namespace names are used.
"""
# arz uses english stylish codes
if self.site.sitename() == 'wikipedia:arz':
return text
family = self.site.family
# wiki links aren't parsed here.
exceptions = ['nowiki', 'comment', 'math', 'pre']
for nsNumber in family.namespaces:
if not family.isDefinedNSLanguage(nsNumber, self.site.lang):
# Skip undefined namespaces
continue
namespaces = list(self.site.namespace(nsNumber, all = True))
thisNs = namespaces.pop(0)
if nsNumber == 6 and family.name == 'wikipedia' and \
self.site.lang in ('en', 'fr'):
# do not change "Image" on en-wiki and fr-wiki
for image in [u'Image', u'image']:
if image in namespaces:
namespaces.remove(image)
# skip main (article) namespace
if thisNs and namespaces:
text = pywikibot.replaceExcept(text, r'\[\[\s*(' + '|'.join(namespaces) + ') *:(?P<nameAndLabel>.*?)\]\]', r'[[' + thisNs + ':\g<nameAndLabel>]]', exceptions)
return text示例12: removeDeprecatedTemplates
def removeDeprecatedTemplates(self, text):
if deprecatedTemplates.has_key(self.site.family.name) and deprecatedTemplates[self.site.family.name].has_key(self.site.lang):
for template in deprecatedTemplates[self.site.family.name][self.site.lang]:
if not self.site.nocapitalize:
template = '[' + template[0].upper() + template[0].lower() + ']' + template[1:]
text = wikipedia.replaceExcept(text, r'\{\{([mM][sS][gG]:)?' + template + '(?P<parameters>\|[^}]+|)}}', '', ['comment', 'math', 'nowiki', 'pre'])
return text示例13: sort_by_country_subcat
def sort_by_country_subcat(subcat, subject):
print subcat
subcat = subcat.replace("_", " ")
subject = subject.replace("_", " ")
if subcat.startswith(subject):
temp1 = subcat[len(subject) :].lstrip()
if temp1.startswith("from"):
temp2 = temp1[len("from") :].lstrip()
elif temp1.startswith("of"):
temp2 = temp1[len("of") :].lstrip()
elif temp1.startswith("in"):
temp2 = temp1[len("in") :].lstrip()
else:
temp2 = ""
if temp2:
if temp2.startswith("the"):
country = temp2[len("the") :].lstrip()
else:
country = temp2
page = wikipedia.Page(wikipedia.getSite(), "Category:" + subcat)
old = u"\[\[[cC]ategory:" + subject + u" by country[^\]]*\]\]"
new = u"[[Category:" + subject + u" by country|" + country + u"]]"
comment = u"Sorting [[:Category:" + subject + u" by country]]"
newtext = wikipedia.replaceExcept(page.get(), old, new, [])
wikipedia.showDiff(page.get(), newtext)
page.put(newtext, comment)示例14: sort_by_country_subcat
def sort_by_country_subcat(subcat, subject):
print subcat
subcat = subcat.replace('_', ' ')
subject = subject.replace('_', ' ')
if subcat.startswith(subject):
temp1 = subcat[len(subject):].lstrip()
if temp1.startswith('from'):
temp2 = temp1[len('from'):].lstrip()
elif temp1.startswith('of'):
temp2 = temp1[len('of'):].lstrip()
elif temp1.startswith('in'):
temp2 = temp1[len('in'):].lstrip()
else:
temp2 = ''
if temp2:
if temp2.startswith('the'):
country = temp2[len('the'):].lstrip()
else:
country = temp2
page = wikipedia.Page(wikipedia.getSite(), 'Category:' + subcat)
old = u'\[\[[cC]ategory:' + subject + u' by country[^\]]*\]\]'
new = u'[[Category:' + subject + u' by country|' + country + u']]'
comment = u'Sorting [[:Category:' + subject + u' by country]]'
newtext = wikipedia.replaceExcept(page.get(), old, new, [])
wikipedia.showDiff(page.get(), newtext)
page.put(newtext, comment)示例15: translateAndCapitalizeNamespaces
def translateAndCapitalizeNamespaces(self, text):
"""
Makes sure that localized namespace names are used.
"""
# arz uses english stylish codes
if self.site.sitename() == "wikipedia:arz":
return text
family = self.site.family
# wiki links aren't parsed here.
exceptions = ["nowiki", "comment", "math", "pre"]
for nsNumber in family.namespaces:
if not family.isDefinedNSLanguage(nsNumber, self.site.lang):
# Skip undefined namespaces
continue
namespaces = list(self.site.namespace(nsNumber, all=True))
thisNs = namespaces.pop(0)
if nsNumber == 6 and family.name == "wikipedia" and self.site.lang in ("en", "fr"):
# do not change "Image" on en-wiki and fr-wiki
for image in [u"Image", u"image"]:
if image in namespaces:
namespaces.remove(image)
# skip main (article) namespace
if thisNs and namespaces:
text = pywikibot.replaceExcept(
text,
r"\[\[\s*(" + "|".join(namespaces) + ") *:(?P<nameAndLabel>.*?)\]\]",
r"[[" + thisNs + ":\g<nameAndLabel>]]",
exceptions,
)
return text