def getLinks(wtext):
#adapted from linkedPages() http://svn.wikimedia.org/svnroot/pywikipedia/trunk/pywikipedia/wikipedia.py
links = []
wtext = wikipedia.removeLanguageLinks(wtext, site)
wtext = wikipedia.removeCategoryLinks(wtext, site)
# remove HTML comments, pre, nowiki, and includeonly sections
# from text before processing
wtext = wikipedia.removeDisabledParts(wtext)
# resolve {{ns:-1}} or {{ns:Help}}
wtext = site.resolvemagicwords(wtext)
for match in Rlink.finditer(wtext):
title = match.group('title')
title = title.replace("_", " ").strip(" ")
if title.startswith("#"): # this is an internal section link
continue
if not site.isInterwikiLink(title):
if title.startswith("#"): # [[#intrasection]] same article
continue
title = title.split('#')[
0] # removing sections [[other article#section|blabla]]
title = '%s%s' % (title[:1].upper(), title[1:]) #first up
title = title.strip()
if title.startswith(":") or title.startswith(
"File:") or title.startswith("Image:") or title.startswith(
"Category:"): # files, cats, etc
continue
if title and title not in links:
links.append(title)
return links
def buildDescription(flinfoDescription=u'',
flickrreview=False,
reviewer=u'',
override=u'',
addCategory=u'',
removeCategories=False):
''' Build the final description for the image. The description is based on
the info from flickrinfo and improved.
'''
description = flinfoDescription
if removeCategories:
description = pywikibot.removeCategoryLinks(
description, pywikibot.getSite('commons', 'commons'))
if override:
description = description.replace(u'{{cc-by-sa-2.0}}\n', u'')
description = description.replace(u'{{cc-by-2.0}}\n', u'')
description = description.replace(u'{{flickrreview}}\n', u'')
description = description.replace(
u'{{copyvio|Flickr, licensed as "All Rights Reserved" which is not a free license --~~~~}}\n',
u'')
description = description.replace(u'=={{int:license}}==',
u'=={{int:license}}==\n' + override)
elif flickrreview:
if reviewer:
description = description.replace(
u'{{flickrreview}}', u'{{flickrreview|' + reviewer +
'|{{subst:CURRENTYEAR}}-{{subst:CURRENTMONTH}}-{{subst:CURRENTDAY2}}}}'
)
if addCategory:
description = description.replace(u'{{subst:unc}}\n', u'')
description = description + u'\n[[Category:' + addCategory + ']]\n'
description = description.replace(u'\r\n', u'\n')
return description
def buildDescription(flinfoDescription=u'', flickrreview=False, reviewer=u'',
override=u'', addCategory=u'', removeCategories=False, photoInfo=None):
''' Build the final description for the image. The description is based on
the info from flickrinfo and improved.
'''
description = flinfoDescription
description = description.replace(u'|Description=', u'|Description={{' + ripper_config['lang'] + '|1=');
description = description.replace(u'\n|Source=', u'}}\n{{' + ripper_config['monument_template'] + '|' + getMonumentId(photoInfo) + '}}\n|Source=');
if removeCategories:
description = pywikibot.removeCategoryLinks(description,
pywikibot.getSite(
'commons', 'commons'))
if override:
description = description.replace(u'{{cc-by-sa-2.0}}\n', u'')
description = description.replace(u'{{cc-by-2.0}}\n', u'')
description = description.replace(u'{{flickrreview}}\n', u'')
description = description.replace(
u'{{copyvio|Flickr, licensed as "All Rights Reserved" which is not a free license --~~~~}}\n',
u'')
description = description.replace(u'=={{int:license}}==',
u'=={{int:license}}==\n' + override)
elif flickrreview:
if reviewer:
description = description.replace(u'{{flickrreview}}',
u'{{flickrreview|' + reviewer +
'|{{subst:CURRENTYEAR}}-{{subst:CURRENTMONTH}}-{{subst:CURRENTDAY2}}}}')
description = description + u'\n{{Wiki Loves Monuments 2011|' + ripper_config['country'] + '}}'
description = description + u'\n' + ripper_config['categories'] + '\n'
description = description.replace(u'{{subst:unc}}\n', u'')
if addCategory:
description = description + u'\n[[Category:' + addCategory + ']]\n'
description = description.replace(u'\r\n', u'\n')
return description
def cleanUpCategories(description =''):
'''
Filter the categories in the description using the functions in imagerecat
'''
#Get the list of current categories
categoryPages = wikipedia.getCategoryLinks(description, wikipedia.getSite())
#Make it a list of strings (not page objects)
categories = []
for cat in categoryPages:
categories.append(cat.titleWithoutNamespace())
#Strip the categories of the current description
description = wikipedia.removeCategoryLinks(description, wikipedia.getSite())
#Filter the list of categories
categories = imagerecat.applyAllFilters(categories)
#If we have a category, remove the uncat template
if not (categories==''):
description = description.replace(u'{{subst:unc}}', u'')
#Add the categories to the description again
description = description + u'\n'
for category in categories:
#print u'Category : ' + category
description = description + u'[[Category:' + category + u']]\n'
return description
def cleanUpCategories(description=''):
'''
Filter the categories in the description using the functions in imagerecat
'''
#Get the list of current categories
categoryPages = wikipedia.getCategoryLinks(description,
wikipedia.getSite())
#Make it a list of strings (not page objects)
categories = []
for cat in categoryPages:
categories.append(cat.titleWithoutNamespace())
#Strip the categories of the current description
description = wikipedia.removeCategoryLinks(description,
wikipedia.getSite())
#Filter the list of categories
categories = imagerecat.applyAllFilters(categories)
#If we have a category, remove the uncat template
if not (categories == ''):
description = description.replace(u'{{subst:unc}}', u'')
#Add the categories to the description again
description = description + u'\n'
for category in categories:
#print u'Category : ' + category
description = description + u'[[Category:' + category + u']]\n'
return description
def replaceCategory (image = None, parents = [], newcat = u''):
'''
Remove all parent categories and add newcat
'''
result = 0
newcats = []
if not newcat == u'':
currentCats = imagerecat.getCurrentCats(image)
workingCategories = currentCats
workingCategories.append(newcat)
# Adding parents if the category filter is lagging.
# The bot often works on new categories. In these cases the filter does know the parent categories
workingCategories = workingCategories + parents
for cat in imagerecat.applyAllFilters(workingCategories):
#Now remove those parents again
if cat not in parents:
newcats.append(cat)
if not(set(currentCats)==set(newcats)):
newtext = wikipedia.removeCategoryLinks(image.get(), image.site()) + u'\n'
for category in newcats:
newtext = newtext + u'[[Category:' + category + u']]\n'
comment = u'Moving image to (a subcategory of) [[Category:' + newcat + u']] and trying to filter categories'
wikipedia.output(image.title())
wikipedia.showDiff(image.get(), newtext)
image.put(newtext, comment)
result = 1
return result
def buildDescription(flinfoDescription=u'', flickrreview=False, reviewer=u'',
override=u'', addCategory=u'', removeCategories=False):
''' Build the final description for the image. The description is based on
the info from flickrinfo and improved.
'''
description = flinfoDescription
if removeCategories:
description = pywikibot.removeCategoryLinks(description,
pywikibot.getSite(
'commons', 'commons'))
if override:
description = description.replace(u'{{cc-by-sa-2.0}}\n', u'')
description = description.replace(u'{{cc-by-2.0}}\n', u'')
description = description.replace(u'{{flickrreview}}\n', u'')
description = description.replace(
u'{{copyvio|Flickr, licensed as "All Rights Reserved" which is not a free license --~~~~}}\n',
u'')
description = description.replace(u'=={{int:license}}==',
u'=={{int:license}}==\n' + override)
elif flickrreview:
if reviewer:
description = description.replace(u'{{flickrreview}}',
u'{{flickrreview|' + reviewer +
'|{{subst:CURRENTYEAR}}-{{subst:CURRENTMONTH}}-{{subst:CURRENTDAY2}}}}')
if addCategory:
description = description.replace(u'{{subst:unc}}\n', u'')
description = description + u'\n[[Category:' + addCategory + ']]\n'
description = description.replace(u'\r\n', u'\n')
return description
def putAfterTemplate(page, template, toadd, loose=True):
'''
Try to put text after template.
If the template is not found return False if loose is set to False
If loose is set to True: Remove interwiki's, categories, add template, restore categories, restore interwiki's.
Based on cc-by-sa-3.0 code by Dschwen
'''
oldtext = page.get()
newtext = u''
templatePosition = oldtext.find(u'{{%s' % (template, ))
if templatePosition >= 0:
previousChar = u''
currentChar = u''
templatePosition += 2
curly = 1
square = 0
while templatePosition < len(oldtext):
currentChar = oldtext[templatePosition]
if currentChar == u'[' and previousChar == u'[':
square += 1
previousChar = u''
if currentChar == u']' and previousChar == u']':
square -= 1
previousChar = u''
if currentChar == u'{' and previousChar == u'{':
curly += 1
previousChar = u''
if currentChar == u'}' and previousChar == u'}':
curly -= 1
previousChar = u''
previousChar = currentChar
templatePosition += 1
if curly == 0 and square <= 0:
# Found end of template
break
newtext = oldtext[:templatePosition] + u'\n' + toadd + oldtext[
templatePosition:]
else:
if loose:
newtext = oldtext
cats = wikipedia.getCategoryLinks(newtext)
ll = wikipedia.getLanguageLinks(newtext)
nextext = wikipedia.removeLanguageLinks(newtext)
newtext = wikipedia.removeCategoryLinks(newtext)
newtext = newtext + u'\n' + toadd
newtext = wikipedia.replaceCategoryLinks(newtext, cats)
newtext = wikipedia.replaceLanguageLinks(newtext, ll)
return newtext
def putAfterTemplate (page, template, toadd, loose=True):
'''
Try to put text after template.
If the template is not found return False if loose is set to False
If loose is set to True: Remove interwiki's, categories, add template, restore categories, restore interwiki's.
Based on cc-by-sa-3.0 code by Dschwen
'''
oldtext = page.get()
newtext = u''
templatePosition = oldtext.find(u'{{%s' % (template,))
if templatePosition >= 0:
previousChar = u''
currentChar = u''
templatePosition += 2
curly = 1
square = 0
while templatePosition < len(oldtext):
currentChar = oldtext[templatePosition]
if currentChar == u'[' and previousChar == u'[' :
square += 1
previousChar = u''
if currentChar == u']' and previousChar == u']' :
square -= 1
previousChar = u''
if currentChar == u'{' and previousChar == u'{' :
curly += 1
previousChar = u''
if currentChar == u'}' and previousChar == u'}' :
curly -= 1
previousChar = u''
previousChar = currentChar
templatePosition +=1
if curly == 0 and square <= 0 :
# Found end of template
break
newtext = oldtext[:templatePosition] + u'\n' + toadd + oldtext[templatePosition:]
else:
if loose:
newtext = oldtext
cats = wikipedia.getCategoryLinks(newtext)
ll = wikipedia.getLanguageLinks(newtext)
nextext = wikipedia.removeLanguageLinks (newtext)
newtext = wikipedia.removeCategoryLinks(newtext)
newtext = newtext + u'\n' + toadd
newtext = wikipedia.replaceCategoryLinks(newtext, cats)
newtext = wikipedia.replaceLanguageLinks(newtext, ll)
return newtext
def saveImagePage(imagepage, newcats, usage, galleries, onlyFilter):
''' Remove the old categories and add the new categories to the image. '''
newtext = pywikibot.removeCategoryLinks(imagepage.get(), imagepage.site())
if not(onlyFilter):
newtext = removeTemplates(newtext)
newtext = newtext + getCheckCategoriesTemplate(usage, galleries,
len(newcats))
newtext = newtext + u'\n'
for category in newcats:
newtext = newtext + u'[[Category:' + category + u']]\n'
if(onlyFilter):
comment = u'Filtering categories'
else:
comment = u'Image is categorized by a bot using data from [[Commons:Tools#CommonSense|CommonSense]]'
pywikibot.showDiff(imagepage.get(), newtext)
imagepage.put(newtext, comment)
return
def categorizeImage(page, id, cursor, cursor2):
# get metadata
metadata = getMetadata(id, cursor)
# get current text
oldtext = page.get()
# get current categories
currentCategories =[]
for cat in page.categories():
currentCategories.append(cat.titleWithoutNamespace().strip().replace(u' ', u'_'))
# remove templates
cleanDescription = wikipedia.removeCategoryLinks(imagerecat.removeTemplates(page.get()), wikipedia.getSite())
# get new categories
categories = getCategories(metadata, cursor, cursor2, currentCategories)
if categories and not set(currentCategories)==set(categories):
description = cleanDescription + u'\n\n' + categories
comment = u'Trying to find better categories for this [[Commons:Batch uploading/Geograph|Geograph]] image'
wikipedia.output(description)
wikipedia.showDiff(oldtext, description)
page.put(description, comment)
def buildDescription(flinfoDescription=u'', flickrreview=False, reviewer=u'', addCategory=u'', removeCategories=False, rijksmonumentid=1):
'''
Build the final description for the image. The description is based on the info from flickrinfo and improved.
'''
description = flinfoDescription
description = description.replace(u'\n|Source=[http://www.flickr.com/', u'\n{{Rijksmonument|%s}}\n|Source=[http://www.flickr.com/' % (rijksmonumentid,))
if removeCategories:
description = wikipedia.removeCategoryLinks(description, wikipedia.getSite('commons', 'commons'))
if flickrreview:
if reviewer:
description = description.replace(u'{{flickrreview}}', u'{{flickrreview|' + reviewer + '|{{subst:CURRENTYEAR}}-{{subst:CURRENTMONTH}}-{{subst:CURRENTDAY2}}}}')
if addCategory:
description = description.replace(u'{{subst:unc}}\n', u'')
description = description + u'\n[[Category:' + addCategory + ']]\n'
description = description.replace(u'\r\n', u'\n')
return description
def buildDescription(flinfoDescription=u'', flickrreview=False, reviewer=u'', addCategory=u'', removeCategories=False, rijksmonumentid=1):
'''
Build the final description for the image. The description is based on the info from flickrinfo and improved.
'''
description = flinfoDescription
description = description.replace(u'\n|Source=[http://www.flickr.com/', u'\n{{Rijksmonument|%s}}\n|Source=[http://www.flickr.com/' % (rijksmonumentid,))
if removeCategories:
description = wikipedia.removeCategoryLinks(description, wikipedia.getSite('commons', 'commons'))
if flickrreview:
if reviewer:
description = description.replace(u'{{flickrreview}}', u'{{flickrreview|' + reviewer + '|{{subst:CURRENTYEAR}}-{{subst:CURRENTMONTH}}-{{subst:CURRENTDAY2}}}}')
if addCategory:
description = description.replace(u'{{subst:unc}}\n', u'')
description = description + u'\n[[Category:' + addCategory + ']]\n'
description = description.replace(u'\r\n', u'\n')
return description
def getNewFieldsFromFreetext(self, imagepage):
'''
Try to extract fields from free text for the new information template.
'''
text = imagepage.get()
#text = re.sub(u'== Summary ==', u'', text, re.IGNORECASE)
#text = re.sub(u'== Licensing ==', u'', text, re.IGNORECASE)
#text = re.sub(u'\{\{(self|self2)\|[^\}]+\}\}', u'', text, re.IGNORECASE)
for toRemove in sourceGarbage[imagepage.site().language()]:
text = re.sub(toRemove, u'', text, flags=re.IGNORECASE)
for (regex, repl) in licenseTemplates[imagepage.site().language()]:
text = re.sub(regex, u'', text, flags=re.IGNORECASE)
text = pywikibot.removeCategoryLinks(text, imagepage.site()).strip()
description = self.convertLinks(text.strip(), imagepage.site())
date = self.getUploadDate(imagepage)
source = self.getSource(imagepage)
author = self.getAuthorText(imagepage)
return (description, date, source, author)
def categorizeImage(page, id, cursor, cursor2):
# get metadata
metadata = getMetadata(id, cursor)
# get current text
oldtext = page.get()
# get current categories
currentCategories = []
for cat in page.categories():
currentCategories.append(cat.titleWithoutNamespace().strip().replace(
u' ', u'_'))
# remove templates
cleanDescription = wikipedia.removeCategoryLinks(
imagerecat.removeTemplates(page.get()), wikipedia.getSite())
# get new categories
categories = getCategories(metadata, cursor, cursor2, currentCategories)
if categories and not set(currentCategories) == set(categories):
description = cleanDescription + u'\n\n' + categories
comment = u'Trying to find better categories for this [[Commons:Batch uploading/Geograph|Geograph]] image'
wikipedia.output(description)
wikipedia.showDiff(oldtext, description)
page.put(description, comment)
def getNewFieldsFromFreetext(self, imagepage):
'''
Try to extract fields from free text for the new information template.
'''
text = imagepage.get()
#text = re.sub(u'== Summary ==', u'', text, re.IGNORECASE)
#text = re.sub(u'== Licensing ==', u'', text, re.IGNORECASE)
#text = re.sub(u'\{\{(self|self2)\|[^\}]+\}\}', u'', text, re.IGNORECASE)
for toRemove in sourceGarbage[imagepage.site().language()]:
text = re.sub(toRemove, u'', text, flags=re.IGNORECASE)
for (regex, repl) in licenseTemplates[imagepage.site().language()]:
text = re.sub(regex, u'', text, flags=re.IGNORECASE)
text = pywikibot.removeCategoryLinks(text, imagepage.site()).strip()
description = self.convertLinks(text.strip(), imagepage.site())
date = self.getUploadDate(imagepage)
source = self.getSource(imagepage)
author = self.getAuthorText(imagepage)
return (description, date, source, author)
def add_text(
page=None,
addText=None,
summary=None,
regexSkip=None,
regexSkipUrl=None,
always=False,
up=False,
putText=True,
oldTextGiven=None,
reorderEnabled=True,
create=False,
):
if not addText:
raise NoEnoughData("You have to specify what text you want to add!")
if not summary:
summary = i18n.twtranslate(pywikibot.getSite(), "add_text-adding", {"adding": addText[:200]})
# When a page is tagged as "really well written" it has a star in the
# interwiki links. This is a list of all the templates used (in regex
# format) to make the stars appear.
errorCount = 0
site = pywikibot.getSite()
pathWiki = site.family.nicepath(site.lang)
if putText:
pywikibot.output(u"Loading %s..." % page.title())
if oldTextGiven is None:
try:
text = page.get()
except pywikibot.NoPage:
if create:
pywikibot.output(u"%s doesn't exist, creating it!" % page.title())
text = u""
else:
pywikibot.output(u"%s doesn't exist, skip!" % page.title())
return (False, False, always)
except pywikibot.IsRedirectPage:
pywikibot.output(u"%s is a redirect, skip!" % page.title())
return (False, False, always)
else:
text = oldTextGiven
# Understand if the bot has to skip the page or not
# In this way you can use both -except and -excepturl
if regexSkipUrl is not None:
url = "%s%s" % (pathWiki, page.urlname())
result = re.findall(regexSkipUrl, site.getUrl(url))
if result != []:
pywikibot.output(
u"""Exception! regex (or word) used with -exceptUrl is in the page. Skip!
Match was: %s"""
% result
)
return (False, False, always)
if regexSkip is not None:
result = re.findall(regexSkip, text)
if result != []:
pywikibot.output(
u"""Exception! regex (or word) used with -except is in the page. Skip!
Match was: %s"""
% result
)
return (False, False, always)
# If not up, text put below
if not up:
newtext = text
# Translating the \\n into binary \n
addText = addText.replace("\\n", config.line_separator)
if reorderEnabled:
# Getting the categories
categoriesInside = pywikibot.getCategoryLinks(newtext, site)
# Deleting the categories
newtext = pywikibot.removeCategoryLinks(newtext, site)
# Getting the interwiki
interwikiInside = pywikibot.getLanguageLinks(newtext, site)
# Removing the interwiki
newtext = pywikibot.removeLanguageLinks(newtext, site)
# Adding the text
newtext += u"%s%s" % (config.line_separator, addText)
# Reputting the categories
newtext = pywikibot.replaceCategoryLinks(newtext, categoriesInside, site, True)
# Dealing the stars' issue
allstars = []
starstext = pywikibot.removeDisabledParts(text)
for star in starsList:
regex = re.compile("(\{\{(?:template:|)%s\|.*?\}\}[\s]*)" % star, re.I)
found = regex.findall(starstext)
if found != []:
newtext = regex.sub("", newtext)
allstars += found
if allstars != []:
newtext = newtext.strip() + config.line_separator * 2
allstars.sort()
for element in allstars:
newtext += "%s%s" % (element.strip(), config.LS)
# Adding the interwiki
newtext = pywikibot.replaceLanguageLinks(newtext, interwikiInside, site)
else:
newtext += u"%s%s" % (config.line_separator, addText)
else:
newtext = addText + config.line_separator + text
if putText and text != newtext:
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" % page.title())
pywikibot.showDiff(text, newtext)
# Let's put the changes.
while True:
# If someone load it as module, maybe it's not so useful to put the
# text in the page
if putText:
if not always:
choice = pywikibot.inputChoice(
u"Do you want to accept these changes?",
["Yes", "No", "All", "open in Browser"],
["y", "n", "a", "b"],
"n",
)
if choice == "a":
always = True
elif choice == "n":
return (False, False, always)
elif choice == "b":
webbrowser.open("http://%s%s" % (page.site.hostname(), page.site.nice_get_address(page.title())))
pywikibot.input("Press Enter when finished in browser.")
if always or choice == "y":
try:
if always:
page.put(newtext, summary, minorEdit=page.namespace() != 3)
else:
page.put_async(newtext, summary, minorEdit=page.namespace() != 3)
except pywikibot.EditConflict:
pywikibot.output(u"Edit conflict! skip!")
return (False, False, always)
except pywikibot.ServerError:
errorCount += 1
if errorCount < config.maxretries:
pywikibot.output(u"Server Error! Wait..")
time.sleep(5)
continue
else:
raise pywikibot.ServerError(u"Fifth Server Error!")
except pywikibot.SpamfilterError as e:
pywikibot.output(u"Cannot change %s because of blacklist entry %s" % (page.title(), e.url))
return (False, False, always)
except pywikibot.PageNotSaved as error:
pywikibot.output(u"Error putting page: %s" % error.args)
return (False, False, always)
except pywikibot.LockedPage:
pywikibot.output(u"Skipping %s (locked page)" % page.title())
return (False, False, always)
else:
# Break only if the errors are one after the other...
errorCount = 0
return (True, True, always)
else:
return (text, newtext, always)
def add_text(page = None, addText = None, summary = None, regexSkip = None, regexSkipUrl = None,
always = False, up = False, putText = True, oldTextGiven = None):
if not addText:
raise NoEnoughData('You have to specify what text you want to add!')
if not summary:
summary = wikipedia.setAction(wikipedia.translate(wikipedia.getSite(), msg) % addText)
# When a page is tagged as "really well written" it has a star in the interwiki links.
# This is a list of all the templates used (in regex format) to make the stars appear.
starsList = ['link[ _]fa', 'link[ _]adq', 'enllaç[ _]ad',
'link[ _]ua', 'legătură[ _]af', 'destacado',
'ua', 'liên k[ _]t[ _]chọn[ _]lọc']
errorCount = 0
site = wikipedia.getSite()
# /wiki/ is not always the right path in non-wiki projects
pathWiki = site.family.nicepath(site.lang)
if putText:
wikipedia.output(u'Loading %s...' % page.title())
if oldTextGiven == None:
try:
text = page.get()
except wikipedia.NoPage:
wikipedia.output(u"%s doesn't exist, skip!" % page.title())
return (False, always) # continue
except wikipedia.IsRedirectPage:
wikipedia.output(u"%s is a redirect, skip!" % page.title())
return (False, always) # continue
else:
text = oldTextGiven
# Understand if the bot has to skip the page or not
# In this way you can use both -except and -excepturl
if regexSkipUrl != None:
url = '%s%s' % (pathWiki, page.urlname())
result = re.findall(regexSkipUrl, site.getUrl(url))
if result != []:
wikipedia.output(u'Exception! regex (or word) used with -exceptUrl is in the page. Skip!')
return (False, always) # continue
if regexSkip != None:
result = re.findall(regexSkip, text)
if result != []:
wikipedia.output(u'Exception! regex (or word) used with -except is in the page. Skip!')
return (False, always) # continue
# If not up, text put below
if not up:
newtext = text
# Getting the categories
categoriesInside = wikipedia.getCategoryLinks(newtext, site)
# Deleting the categories
newtext = wikipedia.removeCategoryLinks(newtext, site)
# Getting the interwiki
interwikiInside = wikipedia.getLanguageLinks(newtext, site)
# Removing the interwiki
newtext = wikipedia.removeLanguageLinks(newtext, site)
#nn got a message between the categories and the iw's and they want to keep it there, first remove it
if (site.language()==u'nn'):
newtext = newtext.replace(nn_iw_msg, '')
# Translating the \\n into binary \n
addText = addText.replace('\\n', '\n')
# Adding the text
newtext += u"\n%s" % addText
# Reputting the categories
newtext = wikipedia.replaceCategoryLinks(newtext, categoriesInside, site, True)
#Put the nn iw message back
if (site.language()==u'nn'):
newtext = newtext + u'\n' + nn_iw_msg
# Dealing the stars' issue
starsListInPage = list()
for star in starsList:
regex = re.compile('(\{\{(?:template:|)%s\|.*?\}\}\n)' % star, re.I)
risultato = regex.findall(newtext)
if risultato != []:
newtext = regex.sub('', newtext)
for element in risultato:
newtext += '\n%s' % element
# Adding the interwiki
newtext = wikipedia.replaceLanguageLinks(newtext, interwikiInside, site)
# If instead the text must be added above...
else:
newtext = addText + '\n' + text
if putText and text != newtext:
wikipedia.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" % page.title())
wikipedia.showDiff(text, newtext)
choice = ''
# Let's put the changes.
while 1:
# If someone load it as module, maybe it's not so useful to put the text in the page
if putText:
if not always:
choice = wikipedia.inputChoice(u'Do you want to accept these changes?', ['Yes', 'No', 'All'], ['y', 'N', 'a'], 'N')
if choice == 'a':
always = True
if choice == 'n':
return (False, always)
if choice == 'y' or always:
try:
if always:
page.put(newtext, summary)
else:
page.put_async(newtext, summary)
except wikipedia.EditConflict:
wikipedia.output(u'Edit conflict! skip!')
return (False, always)
except wikipedia.ServerError:
errorCount += 1
if errorCount < 5:
wikipedia.output(u'Server Error! Wait..')
time.sleep(3)
continue
else:
raise wikipedia.ServerError(u'Fifth Server Error!')
except wikipedia.SpamfilterError, e:
wikipedia.output(u'Cannot change %s because of blacklist entry %s' % (page.title(), e.url))
return (False, always)
except wikipedia.PageNotSaved, error:
wikipedia.output(u'Error putting page: %s' % error.args)
return (False, always)
except wikipedia.LockedPage:
wikipedia.output(u'Skipping %s (locked page)' % page.title())
return (False, always)
else:
# Break only if the errors are one after the other...
errorCount = 0
return (True, always)
def add_text(page = None, addText = None, summary = None, regexSkip = None,
regexSkipUrl = None, always = False, up = False, putText = True,
oldTextGiven = None, reorderEnabled = True, create=False):
if not addText:
raise NoEnoughData('You have to specify what text you want to add!')
if not summary:
summary = i18n.twtranslate(pywikibot.getSite(), 'add_text-adding',
{'adding': addText[:200]})
# When a page is tagged as "really well written" it has a star in the
# interwiki links. This is a list of all the templates used (in regex
# format) to make the stars appear.
starsList = [
u'bueno',
u'bom interwiki',
u'cyswllt[ _]erthygl[ _]ddethol', u'dolen[ _]ed',
u'destacado', u'destaca[tu]',
u'enllaç[ _]ad',
u'enllaz[ _]ad',
u'leam[ _]vdc',
u'legătură[ _]a[bcf]',
u'liamm[ _]pub',
u'lien[ _]adq',
u'lien[ _]ba',
u'liên[ _]kết[ _]bài[ _]chất[ _]lượng[ _]tốt',
u'liên[ _]kết[ _]chọn[ _]lọc',
u'ligam[ _]adq',
u'ligoelstara',
u'ligoleginda',
u'link[ _][afgu]a', u'link[ _]adq', u'link[ _]f[lm]', u'link[ _]km',
u'link[ _]sm', u'linkfa',
u'na[ _]lotura',
u'nasc[ _]ar',
u'tengill[ _][úg]g',
u'ua',
u'yüm yg',
u'רא',
u'وصلة مقالة جيدة',
u'وصلة مقالة مختارة',
]
errorCount = 0
site = pywikibot.getSite()
# /wiki/ is not always the right path in non-wiki projects
pathWiki = site.family.nicepath(site.lang)
if putText:
pywikibot.output(u'Loading %s...' % page.title())
if oldTextGiven == None:
try:
text = page.get()
except pywikibot.NoPage:
if create:
pywikibot.output(u"%s doesn't exist, creating it!"
% page.title())
text = u''
else:
pywikibot.output(u"%s doesn't exist, skip!" % page.title())
return (False, False, always) # continue
except pywikibot.IsRedirectPage:
pywikibot.output(u"%s is a redirect, skip!" % page.title())
return (False, False, always) # continue
else:
text = oldTextGiven
# Understand if the bot has to skip the page or not
# In this way you can use both -except and -excepturl
if regexSkipUrl != None:
url = '%s%s' % (pathWiki, page.urlname())
result = re.findall(regexSkipUrl, site.getUrl(url))
if result != []:
pywikibot.output(
u'''Exception! regex (or word) used with -exceptUrl is in the page. Skipping!
Match was: %s''' % result)
return (False, False, always) # continue
if regexSkip != None:
result = re.findall(regexSkip, text)
if result != []:
pywikibot.output(
u'''Exception! regex (or word) used with -except is in the page. Skipping!
Match was: %s''' % result)
return (False, False, always) # continue
# If not up, text put below
if not up:
newtext = text
# Translating the \\n into binary \n
addText = addText.replace('\\n', '\n')
if (reorderEnabled):
# Getting the categories
categoriesInside = pywikibot.getCategoryLinks(newtext, site)
# Deleting the categories
newtext = pywikibot.removeCategoryLinks(newtext, site)
# Getting the interwiki
interwikiInside = pywikibot.getLanguageLinks(newtext, site)
# Removing the interwiki
newtext = pywikibot.removeLanguageLinks(newtext, site)
# nn got a message between the categories and the iw's
# and they want to keep it there, first remove it
hasCommentLine = False
if (site.language()==u'nn'):
regex = re.compile('(<!-- ?interwiki \(no(?:/nb)?, ?sv, ?da first; then other languages alphabetically by name\) ?-->)')
found = regex.findall(newtext)
if found:
hasCommentLine = True
newtext = regex.sub('', newtext)
# Adding the text
newtext += u"\n%s" % addText
# Reputting the categories
newtext = pywikibot.replaceCategoryLinks(newtext,
categoriesInside, site, True)
#Put the nn iw message back
if site.language()==u'nn' and (interwikiInside or hasCommentLine):
newtext = newtext + u'\r\n\r\n' + nn_iw_msg
# Dealing the stars' issue
allstars = []
starstext = pywikibot.removeDisabledParts(text)
for star in starsList:
regex = re.compile('(\{\{(?:template:|)%s\|.*?\}\}[\s]*)' % star,
re.I)
found = regex.findall(starstext)
if found != []:
newtext = regex.sub('', newtext)
allstars += found
if allstars != []:
newtext = newtext.strip()+'\r\n\r\n'
allstars.sort()
for element in allstars:
newtext += '%s\r\n' % element.strip()
# Adding the interwiki
newtext = pywikibot.replaceLanguageLinks(newtext, interwikiInside, site)
else:
# Adding the text
newtext += u"\n%s" % addText
# If instead the text must be added above...
else:
newtext = addText + '\n' + text
if putText and text != newtext:
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% page.title())
pywikibot.showDiff(text, newtext)
# Let's put the changes.
while True:
# If someone load it as module, maybe it's not so useful to put the
# text in the page
if putText:
if not always:
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'All', 'open in Browser'], ['y', 'N', 'a', 'b'], 'N')
if choice == 'a':
always = True
elif choice == 'n':
return (False, False, always)
elif choice == 'b':
webbrowser.open("http://%s%s" % (
page.site().hostname(),
page.site().nice_get_address(page.title())
))
pywikibot.input("Press Enter when finished in browser.")
if always or choice == 'y':
try:
if always:
page.put(newtext, summary)
else:
page.put_async(newtext, summary)
except pywikibot.EditConflict:
pywikibot.output(u'Edit conflict! skip!')
return (False, False, always)
except pywikibot.ServerError:
errorCount += 1
if errorCount < 5:
pywikibot.output(u'Server Error! Wait..')
time.sleep(5)
continue
else:
raise pywikibot.ServerError(u'Fifth Server Error!')
except pywikibot.SpamfilterError, e:
pywikibot.output(
u'Cannot change %s because of blacklist entry %s'
% (page.title(), e.url))
return (False, False, always)
except pywikibot.PageNotSaved, error:
pywikibot.output(u'Error putting page: %s' % error.args)
return (False, False, always)
except pywikibot.LockedPage:
pywikibot.output(u'Skipping %s (locked page)'
% page.title())
return (False, False, always)
else:
# Break only if the errors are one after the other...
errorCount = 0
return (True, True, always)
def add_text(page=None, addText=None, summary=None, regexSkip=None,
regexSkipUrl=None, always=False, up=False, putText=True,
oldTextGiven=None, reorderEnabled=True, create=False):
# When a page is tagged as "really well written" it has a star in the
# interwiki links. This is a list of all the templates used (in regex
# format) to make the stars appear.
starsList = [
u'bueno',
u'bom interwiki',
u'cyswllt[ _]erthygl[ _]ddethol', u'dolen[ _]ed',
u'destacado', u'destaca[tu]',
u'enllaç[ _]ad',
u'enllaz[ _]ad',
u'leam[ _]vdc',
u'legătură[ _]a[bcf]',
u'liamm[ _]pub',
u'lien[ _]adq',
u'lien[ _]ba',
u'liên[ _]kết[ _]bài[ _]chất[ _]lượng[ _]tốt',
u'liên[ _]kết[ _]chọn[ _]lọc',
u'ligam[ _]adq',
u'ligoelstara',
u'ligoleginda',
u'link[ _][afgu]a', u'link[ _]adq', u'link[ _]f[lm]', u'link[ _]km',
u'link[ _]sm', u'linkfa',
u'na[ _]lotura',
u'nasc[ _]ar',
u'tengill[ _][úg]g',
u'ua',
u'yüm yg',
u'רא',
u'وصلة مقالة جيدة',
u'وصلة مقالة مختارة',
]
errorCount = 0
site = pywikibot.getSite()
pathWiki = site.family.nicepath(site.lang)
site = pywikibot.getSite()
if oldTextGiven is None:
try:
text = page.get()
except pywikibot.NoPage:
if create:
pywikibot.output(u"%s doesn't exist, creating it!"
% page.title())
text = u''
else:
pywikibot.output(u"%s doesn't exist, skip!" % page.title())
return (False, False, always)
except pywikibot.IsRedirectPage:
pywikibot.output(u"%s is a redirect, skip!" % page.title())
return (False, False, always)
else:
text = oldTextGiven
# If not up, text put below
if not up:
newtext = text
# Translating the \\n into binary \n
addText = addText.replace('\\n', '\n')
if (reorderEnabled):
# Getting the categories
categoriesInside = pywikibot.getCategoryLinks(newtext, site)
# Deleting the categories
newtext = pywikibot.removeCategoryLinks(newtext, site)
# Getting the interwiki
interwikiInside = pywikibot.getLanguageLinks(newtext, site)
# Removing the interwiki
newtext = pywikibot.removeLanguageLinks(newtext, site)
# Adding the text
newtext += u"\n%s" % addText
# Reputting the categories
newtext = pywikibot.replaceCategoryLinks(newtext,
categoriesInside, site,
True)
# Dealing the stars' issue
allstars = []
starstext = pywikibot.removeDisabledParts(text)
for star in starsList:
regex = re.compile('(\{\{(?:template:|)%s\|.*?\}\}[\s]*)'
% star, re.I)
found = regex.findall(starstext)
if found != []:
newtext = regex.sub('', newtext)
allstars += found
if allstars != []:
newtext = newtext.strip() + '\r\n\r\n'
allstars.sort()
for element in allstars:
newtext += '%s\r\n' % element.strip()
# Adding the interwiki
newtext = pywikibot.replaceLanguageLinks(newtext, interwikiInside,
site)
else:
newtext += u"\n%s" % addText
else:
newtext = addText + '\n' + text
if putText and text != newtext:
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% page.title())
#pywikibot.showDiff(text, newtext)
# Let's put the changes.
while True:
# If someone load it as module, maybe it's not so useful to put the
# text in the page
if putText:
if always or choice == 'y':
try:
pass
if always:
page.put(newtext, summary,
minorEdit=False)
else:
page.put_async(newtext, summary,
minorEdit=False)
except pywikibot.EditConflict:
pywikibot.output(u'Edit conflict! skip!')
return (False, False, always)
except pywikibot.ServerError:
errorCount += 1
if errorCount < 5:
pywikibot.output(u'Server Error! Wait..')
time.sleep(5)
continue
else:
raise pywikibot.ServerError(u'Fifth Server Error!')
except pywikibot.SpamfilterError, e:
pywikibot.output(
u'Cannot change %s because of blacklist entry %s'
% (page.title(), e.url))
return (False, False, always)
except pywikibot.PageNotSaved, error:
pywikibot.output(u'Error putting page: %s' % error.args)
return (False, False, always)
except pywikibot.LockedPage:
pywikibot.output(u'Skipping %s (locked page)'
% page.title())
return (False, False, always)
else:
# Break only if the errors are one after the other...
errorCount = 0
return (True, True, always)
def add_text(
page=None,
addText=None,
summary=None,
regexSkip=None,
regexSkipUrl=None,
always=False,
up=False,
putText=True,
oldTextGiven=None,
create=False,
):
if not addText:
raise NoEnoughData("You have to specify what text you want to add!")
if not summary:
summary = wikipedia.translate(wikipedia.getSite(), msg) % addText[:200]
# When a page is tagged as "really well written" it has a star in the
# interwiki links. This is a list of all the templates used (in regex
# format) to make the stars appear.
starsList = [
u"bueno",
u"cyswllt[ _]erthygl[ _]ddethol",
u"dolen[ _]ed",
u"destacado",
u"destaca[tu]",
u"enllaç[ _]ad",
u"enllaz[ _]ad",
u"leam[ _]vdc",
u"legătură[ _]a[bcf]",
u"liamm[ _]pub",
u"lien[ _]adq",
u"lien[ _]ba",
u"liên[ _]kết[ _]bài[ _]chất[ _]lượng[ _]tốt",
u"liên[ _]kết[ _]chọn[ _]lọc",
u"ligam[ _]adq",
u"ligoelstara",
u"ligoleginda",
u"link[ _][afgu]a",
u"link[ _]adq",
u"link[ _]f[lm]",
u"link[ _]km",
u"link[ _]sm",
u"linkfa",
u"na[ _]lotura",
u"nasc[ _]ar",
u"tengill[ _][úg]g",
u"ua",
u"yüm yg",
u"רא",
u"وصلة مقالة جيدة",
u"وصلة مقالة مختارة",
]
errorCount = 0
site = wikipedia.getSite()
# /wiki/ is not always the right path in non-wiki projects
pathWiki = site.family.nicepath(site.lang)
if putText:
wikipedia.output(u"Loading %s..." % page.title())
if oldTextGiven == None:
try:
text = page.get()
except wikipedia.NoPage:
if create:
wikipedia.output(u"%s doesn't exist, creating it!" % page.title())
text = u""
else:
wikipedia.output(u"%s doesn't exist, skip!" % page.title())
return (False, False, always) # continue
except wikipedia.IsRedirectPage:
wikipedia.output(u"%s is a redirect, skip!" % page.title())
return (False, False, always) # continue
else:
text = oldTextGiven
# Understand if the bot has to skip the page or not
# In this way you can use both -except and -excepturl
if regexSkipUrl != None:
url = "%s%s" % (pathWiki, page.urlname())
result = re.findall(regexSkipUrl, site.getUrl(url))
if result != []:
wikipedia.output(u"Exception! regex (or word) used with -exceptUrl is in the page. Skip!")
return (False, False, always) # continue
if regexSkip != None:
result = re.findall(regexSkip, text)
if result != []:
wikipedia.output(u"Exception! regex (or word) used with -except is in the page. Skip!")
return (False, False, always) # continue
# If not up, text put below
if not up:
newtext = text
# Getting the categories
categoriesInside = wikipedia.getCategoryLinks(newtext, site)
# Deleting the categories
newtext = wikipedia.removeCategoryLinks(newtext, site)
# Getting the interwiki
interwikiInside = wikipedia.getLanguageLinks(newtext, site)
# Removing the interwiki
newtext = wikipedia.removeLanguageLinks(newtext, site)
# nn got a message between the categories and the iw's and they want to keep it there, first remove it
if site.language() == u"nn":
newtext = newtext.replace(nn_iw_msg, "")
# Translating the \\n into binary \n
addText = addText.replace("\\n", "\n")
# Adding the text
newtext += u"\n%s" % addText
# Reputting the categories
newtext = wikipedia.replaceCategoryLinks(newtext, categoriesInside, site, True)
# Put the nn iw message back
if site.language() == u"nn":
newtext = newtext + u"\n" + nn_iw_msg
# Dealing the stars' issue
allstars = []
starstext = wikipedia.removeDisabledParts(text)
for star in starsList:
regex = re.compile("(\{\{(?:template:|)%s\|.*?\}\}[\s]*)" % star, re.I)
found = regex.findall(starstext)
if found != []:
newtext = regex.sub("", newtext)
allstars += found
if allstars != []:
newtext = newtext.strip() + "\r\n\r\n"
allstars.sort()
for element in allstars:
newtext += "%s\r\n" % element.strip()
# Adding the interwiki
newtext = wikipedia.replaceLanguageLinks(newtext, interwikiInside, site)
# If instead the text must be added above...
else:
newtext = addText + "\n" + text
if putText and text != newtext:
wikipedia.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" % page.title())
wikipedia.showDiff(text, newtext)
# Let's put the changes.
while True:
# If someone load it as module, maybe it's not so useful to put the
# text in the page
if putText:
if not always:
choice = wikipedia.inputChoice(
u"Do you want to accept these changes?", ["Yes", "No", "All"], ["y", "N", "a"], "N"
)
if choice == "a":
always = True
elif choice == "n":
return (False, False, always)
if always or choice == "y":
try:
if always:
page.put(newtext, summary)
else:
page.put_async(newtext, summary)
except wikipedia.EditConflict:
wikipedia.output(u"Edit conflict! skip!")
return (False, False, always)
except wikipedia.ServerError:
errorCount += 1
if errorCount < 5:
wikipedia.output(u"Server Error! Wait..")
time.sleep(5)
continue
else:
raise wikipedia.ServerError(u"Fifth Server Error!")
except wikipedia.SpamfilterError, e:
wikipedia.output(u"Cannot change %s because of blacklist entry %s" % (page.title(), e.url))
return (False, False, always)
except wikipedia.PageNotSaved, error:
wikipedia.output(u"Error putting page: %s" % error.args)
return (False, False, always)
except wikipedia.LockedPage:
wikipedia.output(u"Skipping %s (locked page)" % page.title())
return (False, False, always)
else:
# Break only if the errors are one after the other...
errorCount = 0
return (True, True, always)
def add_text(page=None,
addText=None,
summary=None,
regexSkip=None,
regexSkipUrl=None,
always=False,
up=False,
putText=True,
oldTextGiven=None,
reorderEnabled=True,
create=False):
if not addText:
raise NoEnoughData('You have to specify what text you want to add!')
if not summary:
summary = i18n.twtranslate(pywikibot.getSite(), 'add_text-adding',
{'adding': addText[:200]})
# When a page is tagged as "really well written" it has a star in the
# interwiki links. This is a list of all the templates used (in regex
# format) to make the stars appear.
starsList = [
u'bueno',
u'bom interwiki',
u'cyswllt[ _]erthygl[ _]ddethol',
u'dolen[ _]ed',
u'destacado',
u'destaca[tu]',
u'enllaç[ _]ad',
u'enllaz[ _]ad',
u'leam[ _]vdc',
u'legătură[ _]a[bcf]',
u'liamm[ _]pub',
u'lien[ _]adq',
u'lien[ _]ba',
u'liên[ _]kết[ _]bài[ _]chất[ _]lượng[ _]tốt',
u'liên[ _]kết[ _]chọn[ _]lọc',
u'ligam[ _]adq',
u'ligoelstara',
u'ligoleginda',
u'link[ _][afgu]a',
u'link[ _]adq',
u'link[ _]f[lm]',
u'link[ _]km',
u'link[ _]sm',
u'linkfa',
u'na[ _]lotura',
u'nasc[ _]ar',
u'tengill[ _][úg]g',
u'ua',
u'yüm yg',
u'רא',
u'وصلة مقالة جيدة',
u'وصلة مقالة مختارة',
]
errorCount = 0
site = pywikibot.getSite()
# /wiki/ is not always the right path in non-wiki projects
pathWiki = site.family.nicepath(site.lang)
if putText:
pywikibot.output(u'Loading %s...' % page.title())
if oldTextGiven == None:
try:
text = page.get()
except pywikibot.NoPage:
if create:
pywikibot.output(u"%s doesn't exist, creating it!" %
page.title())
text = u''
else:
pywikibot.output(u"%s doesn't exist, skip!" % page.title())
return (False, False, always) # continue
except pywikibot.IsRedirectPage:
pywikibot.output(u"%s is a redirect, skip!" % page.title())
return (False, False, always) # continue
else:
text = oldTextGiven
# Understand if the bot has to skip the page or not
# In this way you can use both -except and -excepturl
if regexSkipUrl != None:
url = '%s%s' % (pathWiki, page.urlname())
result = re.findall(regexSkipUrl, site.getUrl(url))
if result != []:
pywikibot.output(
u'''Exception! regex (or word) used with -exceptUrl is in the page. Skip!
Match was: %s''' % result)
return (False, False, always) # continue
if regexSkip != None:
result = re.findall(regexSkip, text)
if result != []:
pywikibot.output(
u'''Exception! regex (or word) used with -except is in the page. Skip!
Match was: %s''' % result)
return (False, False, always) # continue
# If not up, text put below
if not up:
newtext = text
# Translating the \\n into binary \n
addText = addText.replace('\\n', '\n')
if (reorderEnabled):
# Getting the categories
categoriesInside = pywikibot.getCategoryLinks(newtext, site)
# Deleting the categories
newtext = pywikibot.removeCategoryLinks(newtext, site)
# Getting the interwiki
interwikiInside = pywikibot.getLanguageLinks(newtext, site)
# Removing the interwiki
newtext = pywikibot.removeLanguageLinks(newtext, site)
# nn got a message between the categories and the iw's
# and they want to keep it there, first remove it
hasCommentLine = False
if (site.language() == u'nn'):
regex = re.compile(
'(<!-- ?interwiki \(no(?:/nb)?, ?sv, ?da first; then other languages alphabetically by name\) ?-->)'
)
found = regex.findall(newtext)
if found:
hasCommentLine = True
newtext = regex.sub('', newtext)
# Adding the text
newtext += u"\n%s" % addText
# Reputting the categories
newtext = pywikibot.replaceCategoryLinks(newtext, categoriesInside,
site, True)
#Put the nn iw message back
if site.language() == u'nn' and (interwikiInside
or hasCommentLine):
newtext = newtext + u'\r\n\r\n' + nn_iw_msg
# Dealing the stars' issue
allstars = []
starstext = pywikibot.removeDisabledParts(text)
for star in starsList:
regex = re.compile(
'(\{\{(?:template:|)%s\|.*?\}\}[\s]*)' % star, re.I)
found = regex.findall(starstext)
if found != []:
newtext = regex.sub('', newtext)
allstars += found
if allstars != []:
newtext = newtext.strip() + '\r\n\r\n'
allstars.sort()
for element in allstars:
newtext += '%s\r\n' % element.strip()
# Adding the interwiki
newtext = pywikibot.replaceLanguageLinks(newtext, interwikiInside,
site)
else:
# Adding the text
newtext += u"\n%s" % addText
# If instead the text must be added above...
else:
newtext = addText + '\n' + text
if putText and text != newtext:
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" %
page.title())
pywikibot.showDiff(text, newtext)
# Let's put the changes.
while True:
# If someone load it as module, maybe it's not so useful to put the
# text in the page
if putText:
if not always:
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'All', 'open in Browser'],
['y', 'N', 'a', 'b'], 'N')
if choice == 'a':
always = True
elif choice == 'n':
return (False, False, always)
elif choice == 'b':
webbrowser.open(
"http://%s%s" %
(page.site().hostname(), page.site().nice_get_address(
page.title())))
pywikibot.input("Press Enter when finished in browser.")
if always or choice == 'y':
try:
if always:
page.put(newtext, summary)
else:
page.put_async(newtext, summary)
except pywikibot.EditConflict:
pywikibot.output(u'Edit conflict! skip!')
return (False, False, always)
except pywikibot.ServerError:
errorCount += 1
if errorCount < 5:
pywikibot.output(u'Server Error! Wait..')
time.sleep(5)
continue
else:
raise pywikibot.ServerError(u'Fifth Server Error!')
except pywikibot.SpamfilterError, e:
pywikibot.output(
u'Cannot change %s because of blacklist entry %s' %
(page.title(), e.url))
return (False, False, always)
except pywikibot.PageNotSaved, error:
pywikibot.output(u'Error putting page: %s' % error.args)
return (False, False, always)
except pywikibot.LockedPage:
pywikibot.output(u'Skipping %s (locked page)' %
page.title())
return (False, False, always)
else:
# Break only if the errors are one after the other...
errorCount = 0
return (True, True, always)
def add_text(page=None, addText=None, summary=None, regexSkip=None,
regexSkipUrl=None, always=False, up=False, putText=True,
oldTextGiven=None, reorderEnabled=True, create=False):
if not addText:
raise NoEnoughData('You have to specify what text you want to add!')
if not summary:
summary = i18n.twtranslate(pywikibot.getSite(), 'add_text-adding',
{'adding': addText[:200]})
# When a page is tagged as "really well written" it has a star in the
# interwiki links. This is a list of all the templates used (in regex
# format) to make the stars appear.
errorCount = 0
site = pywikibot.getSite()
pathWiki = site.family.nicepath(site.lang)
if putText:
pywikibot.output(u'Loading %s...' % page.title())
if oldTextGiven is None:
try:
text = page.get()
except pywikibot.NoPage:
if create:
pywikibot.output(u"%s doesn't exist, creating it!"
% page.title())
text = u''
else:
pywikibot.output(u"%s doesn't exist, skip!" % page.title())
return (False, False, always)
except pywikibot.IsRedirectPage:
pywikibot.output(u"%s is a redirect, skip!" % page.title())
return (False, False, always)
else:
text = oldTextGiven
# Understand if the bot has to skip the page or not
# In this way you can use both -except and -excepturl
if regexSkipUrl is not None:
url = '%s%s' % (pathWiki, page.urlname())
result = re.findall(regexSkipUrl, site.getUrl(url))
if result != []:
pywikibot.output(
u'''Exception! regex (or word) used with -exceptUrl is in the page. Skip!
Match was: %s''' % result)
return (False, False, always)
if regexSkip is not None:
result = re.findall(regexSkip, text)
if result != []:
pywikibot.output(
u'''Exception! regex (or word) used with -except is in the page. Skip!
Match was: %s''' % result)
return (False, False, always)
# If not up, text put below
if not up:
newtext = text
# Translating the \\n into binary \n
addText = addText.replace('\\n', config.line_separator)
if (reorderEnabled):
# Getting the categories
categoriesInside = pywikibot.getCategoryLinks(newtext, site)
# Deleting the categories
newtext = pywikibot.removeCategoryLinks(newtext, site)
# Getting the interwiki
interwikiInside = pywikibot.getLanguageLinks(newtext, site)
# Removing the interwiki
newtext = pywikibot.removeLanguageLinks(newtext, site)
# Adding the text
newtext += u"%s%s" % (config.line_separator, addText)
# Reputting the categories
newtext = pywikibot.replaceCategoryLinks(newtext,
categoriesInside, site,
True)
# Dealing the stars' issue
allstars = []
starstext = pywikibot.removeDisabledParts(text)
for star in starsList:
regex = re.compile('(\{\{(?:template:|)%s\|.*?\}\}[\s]*)'
% star, re.I)
found = regex.findall(starstext)
if found != []:
newtext = regex.sub('', newtext)
allstars += found
if allstars != []:
newtext = newtext.strip() + config.line_separator * 2
allstars.sort()
for element in allstars:
newtext += '%s%s' % (element.strip(), config.LS)
# Adding the interwiki
newtext = pywikibot.replaceLanguageLinks(newtext, interwikiInside,
site)
else:
newtext += u"%s%s" % (config.line_separator, addText)
else:
newtext = addText + config.line_separator + text
if putText and text != newtext:
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% page.title())
pywikibot.showDiff(text, newtext)
# Let's put the changes.
while True:
# If someone load it as module, maybe it's not so useful to put the
# text in the page
if putText:
if not always:
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'All', 'open in Browser'],
['y', 'n', 'a', 'b'], 'n')
if choice == 'a':
always = True
elif choice == 'n':
return (False, False, always)
elif choice == 'b':
webbrowser.open("http://%s%s" % (
page.site.hostname(),
page.site.nice_get_address(page.title())
))
pywikibot.input("Press Enter when finished in browser.")
if always or choice == 'y':
try:
if always:
page.put(newtext, summary,
minorEdit=page.namespace() != 3)
else:
page.put_async(newtext, summary,
minorEdit=page.namespace() != 3)
except pywikibot.EditConflict:
pywikibot.output(u'Edit conflict! skip!')
return (False, False, always)
except pywikibot.ServerError:
errorCount += 1
if errorCount < config.maxretries:
pywikibot.output(u'Server Error! Wait..')
time.sleep(5)
continue
else:
raise pywikibot.ServerError(u'Fifth Server Error!')
except pywikibot.SpamfilterError as e:
pywikibot.output(
u'Cannot change %s because of blacklist entry %s'
% (page.title(), e.url))
return (False, False, always)
except pywikibot.PageNotSaved as error:
pywikibot.output(u'Error putting page: %s' % error.args)
return (False, False, always)
except pywikibot.LockedPage:
pywikibot.output(u'Skipping %s (locked page)'
% page.title())
return (False, False, always)
else:
# Break only if the errors are one after the other...
errorCount = 0
return (True, True, always)
else:
return (text, newtext, always)