def convertList(page):
'''
Convert a list of NRHP entries. Both headers and items will be converted.
'''
wikipedia.output(u'Working on %s' % page.title())
text = page.get()
try:
newtext = convertHeaders(page, text)
newtext = convertItems(page, newtext)
except TypeError or AttributeError:
wikipedia.output(u'One of the regexes failed at %s, skipping this page' % (page.title,))
traceback.print_exc(file=sys.stdout)
time.sleep(10)
return u'Failed'
if not text==newtext:
wikipedia.showDiff(text, newtext)
comment = u'Converting list to use [[Template:NRHP header]] and [[Template:NRHP row]]'
#choice = wikipedia.inputChoice(u'Do you want to accept these changes?', ['Yes', 'No'], ['y', 'n'], 'n')
choice = 'y'
if choice == 'y':
#DEBUG
page.put(newtext, comment)
return u'Success'
#wikipedia.output(newtext)
return u'Unchanged'
def revert(self, item):
predata = {
"action": "query",
"titles": item["title"],
"prop": "revisions",
"rvprop": "ids|timestamp|user|content",
"rvlimit": "2",
"rvstart": item["timestamp"],
}
data = query.GetData(predata, self.site)
if "error" in data:
raise RuntimeError(data["error"])
pages = data["query"].get("pages", ())
if not pages:
return False
page = pages.itervalues().next()
if len(page.get("revisions", ())) != 2:
return False
rev = page["revisions"][1]
comment = u"Reverted to revision %s by %s on %s" % (rev["revid"], rev["user"], rev["timestamp"])
if self.comment:
comment += ": " + self.comment
page = pywikibot.Page(self.site, item["title"])
pywikibot.output(
u"\n\n>>> \03{lightpurple}%s\03{default} <<<" % page.title(asLink=True, forceInterwiki=True, textlink=True)
)
old = page.get()
new = rev["*"]
pywikibot.showDiff(old, new)
page.put(new, comment)
return comment
def process_article(page):
EditMsg = "Robot: Substituting {{[[Template:RS500|RS500]]}} and common fixes"
wikipedia.setAction(EditMsg)
try:
wikitext = page.get()
except wikipedia.NoPage:
return
except wikipedia.IsRedirectPage:
return
# Fix Casing (Reduces the number of possible expressions)
# Common fixes
# wikitext = commonfixes.fix(wikitext)
# State point. Count any changes as needing an update if they're after this line
state0 = wikitext
# Add |Iran=yes
wikitext = re.compile(r'\{\{\s*rs500(.*?)\}\}',
re.IGNORECASE).sub(r'{{subst:RS500\1}}', wikitext)
wikipedia.showDiff(page.get(), wikitext)
if (wikitext != state0):
try:
wikipedia.output(u'WRITE: Adding %s bytes.' %
str(len(wikitext) - len(page.get())))
# print 'Waiting 2.5 seconds'
# time.sleep(2.5)
page.put(wikitext)
except TypeError:
print 'Skipping TypeError'
return
def tagNowcommons(self, imagepage, filename):
'''
Tagged the imag which has been moved to Commons for deletion.
'''
if pywikibot.Page(pywikibot.getSite('commons', 'commons'), u'File:' + filename).exists():
#Get a fresh copy, force to get the page so we dont run into edit conflicts
imtxt=imagepage.get(force=True)
#Remove the move to commons templates
if imagepage.site().language() in moveToCommonsTemplate:
for moveTemplate in moveToCommonsTemplate[imagepage.site().language()]:
imtxt = re.sub(u'(?i)\{\{' + moveTemplate + u'[^\}]*\}\}', u'', imtxt)
#add {{NowCommons}}
if imagepage.site().language() in nowCommonsTemplate:
addTemplate = nowCommonsTemplate[imagepage.site().language()] % filename
else:
addTemplate = nowCommonsTemplate['_default'] % filename
if imagepage.site().language() in nowCommonsMessage:
commentText = nowCommonsMessage[imagepage.site().language()]
else:
commentText = nowCommonsMessage['_default']
pywikibot.showDiff(imagepage.get(), imtxt + addTemplate)
imagepage.put(imtxt + addTemplate, comment = commentText)
def update_template_coordinates():
for page in iterate_lists():
old_text = page.get()
new_text = old_text
for data in iterate_monuments_on_page(page):
old_text = new_text
try:
db_data = template_data_to_db_data(data)
if not has_location(db_data):
#szelesseg, hosszusag = get_old_coordinates_for_monument(db_data['azonosito'])
hosszusag, szelesseg = get_old_coordinates_for_monument(db_data['azonosito']) # FIXME forditva vannak a DB-ben?
pywikibot.output(
"adding coordinates: \03{lightyellow}%s\03{default} - %s -> (\03{lightyellow}%s\03{default}, \03{lightyellow}%s\03{default})"
% (db_data['azonosito'], page.title(), szelesseg, hosszusag)
)
new_text = fill_coordinates_on_page(old_text, db_data['azonosito'], szelesseg, hosszusag)
pywikibot.showDiff(old_text, new_text)
except NoCoordinateForMonument:
pass
except pg8000.errors.ProgrammingError:
raise
except:
print db_data
raise
page.put(new_text, comment = u'Koordináták beszúrása', botflag=False)
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)
def updateInterwiki (self, wikipediaPage = None, commonsPage = None):
'''
Update the interwiki's at commons from a wikipedia page. The bot just
replaces the interwiki links at the commons page with the interwiki's from
the wikipedia page. This should probably be more intelligent. We could use
add all the interwiki's and remove duplicates. Or only remove language links
if multiple language links to the same language exist.
This function is disabled for the moment untill i figure out what the best
way is to update the interwiki's.
'''
interwikis = {}
comment= u''
interwikilist = wikipediaPage.interwiki()
interwikilist.append(wikipediaPage)
for interwikiPage in interwikilist:
interwikis[interwikiPage.site()]=interwikiPage
oldtext = commonsPage.get()
# The commonssite object doesnt work with interwiki's
newtext = pywikibot.replaceLanguageLinks(oldtext, interwikis,
pywikibot.getSite(u'nl'))
comment = u'Updating interwiki\'s from [[' + \
wikipediaPage.site().language() + \
u':' + wikipediaPage.title() + u']]'
if newtext != oldtext:
#This doesnt seem to work. Newtext has some trailing whitespace
pywikibot.showDiff(oldtext, newtext)
commonsPage.put(newtext=newtext, comment=comment)
def process_article(page):
EditMsg = "Robot: Substituting {{[[Template:RS500|RS500]]}} and common fixes"
wikipedia.setAction(EditMsg)
try:
wikitext = page.get()
except wikipedia.NoPage:
return
except wikipedia.IsRedirectPage:
return
# Fix Casing (Reduces the number of possible expressions)
# Common fixes
# wikitext = commonfixes.fix(wikitext)
# State point. Count any changes as needing an update if they're after this line
state0 = wikitext
# Add |Iran=yes
wikitext = re.compile(r'\{\{\s*rs500(.*?)\}\}', re.IGNORECASE).sub(r'{{subst:RS500\1}}', wikitext)
wikipedia.showDiff(page.get(), wikitext)
if (wikitext != state0):
try:
wikipedia.output(u'WRITE: Adding %s bytes.' % str(len(wikitext)-len(page.get())))
# print 'Waiting 2.5 seconds'
# time.sleep(2.5)
page.put(wikitext)
except TypeError:
print 'Skipping TypeError'
return
def revert(self, item):
predata = {
'action': 'query',
'titles': item['title'],
'prop': 'revisions',
'rvprop': 'ids|timestamp|user|content',
'rvlimit': '2',
'rvstart': item['timestamp'],
}
data = query.GetData(predata, self.site)
if 'error' in data:
raise RuntimeError(data['error'])
pages = data['query'].get('pages', ())
if not pages: return False
page = pages.itervalues().next()
if len(page.get('revisions', ())) != 2: return False
rev = page['revisions'][1]
comment = u'Reverted to revision %s by %s on %s' % (rev['revid'],
rev['user'], rev['timestamp'])
if self.comment: comment += ': ' + self.comment
page = pywikibot.Page(self.site, item['title'])
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% page.aslink(True, True))
old = page.get()
new = rev['*']
pywikibot.showDiff(old, new)
page.put(new, comment)
return comment
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 save(self, text, page, comment, minorEdit=True, botflag=True):
# only save if something was changed
if text != page.get():
# Show the title of the page we're working on.
# Highlight the title in purple.
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" %
page.title())
# show what was changed
pywikibot.showDiff(page.get(), text)
pywikibot.output(u'Comment: %s' % comment)
try:
# Save the page
page.put(text,
comment=comment,
minorEdit=minorEdit,
botflag=botflag)
return True
except pywikibot.LockedPage:
pywikibot.output(u"Page %s is locked; skipping." %
page.title(asLink=True))
except pywikibot.EditConflict:
pywikibot.output(u'Skipping %s because of edit conflict' %
(page.title()))
except pywikibot.SpamfilterError, error:
pywikibot.output(
u'Cannot change %s because of spam blacklist entry %s' %
(page.title(), error.url))
def tagNowcommons(self, imagepage, filename):
'''
Tagged the imag which has been moved to Commons for deletion.
'''
if pywikibot.Page(pywikibot.getSite('commons', 'commons'), u'File:' + filename).exists():
#Get a fresh copy, force to get the page so we dont run into edit conflicts
imtxt=imagepage.get(force=True)
#Remove the move to commons templates
if imagepage.site().language() in moveToCommonsTemplate:
for moveTemplate in moveToCommonsTemplate[imagepage.site().language()]:
imtxt = re.sub(u'(?i)\{\{' + moveTemplate + u'[^\}]*\}\}', u'', imtxt)
#add {{NowCommons}}
if imagepage.site().language() in nowCommonsTemplate:
addTemplate = nowCommonsTemplate[imagepage.site().language()] % filename
else:
addTemplate = nowCommonsTemplate['_default'] % filename
if imagepage.site().language() in nowCommonsMessage:
commentText = nowCommonsMessage[imagepage.site().language()]
else:
commentText = nowCommonsMessage['_default']
pywikibot.showDiff(imagepage.get(), imtxt + addTemplate)
imagepage.put(imtxt + addTemplate, comment = commentText)
def fes(pagina):
pag = wikipedia.Page(wikipedia.getSite('ca'), pagina) # creem un objecte page on poder treballar
noutext = text = pag.get() # obtenuim el text
noutext = re.sub(u"\| ?pàgines ?= p\.?", "|pàgines=", text)
wikipedia.showDiff(text, noutext)
if raw_input(u"Vols penjar la pàgina [y/n]?") == "y":
pag.put(noutext, comment=u"Robot fent canvis per la {{tl|ref-llibre}}")
def treat(self, page):
# Show the title of the page we're working on.
# Highlight the title in purple.
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" %
page.title())
try:
oldText = page.get()
text = oldText
curpos = 0
while curpos < len(text):
match = self.linkR.search(text, pos=curpos)
if not match:
break
# Make sure that next time around we will not find this same
# hit.
curpos = match.start() + 1
text, jumpToBeginning = self.handleNextLink(text, match)
if jumpToBeginning:
curpos = 0
if oldText == text:
pywikibot.output(u'No changes necessary.')
else:
pywikibot.showDiff(oldText, text)
page.put(text, self.comment)
except pywikibot.NoPage:
pywikibot.output(u"Page %s does not exist?!" %
page.title(asLink=True))
except pywikibot.IsRedirectPage:
pywikibot.output(u"Page %s is a redirect; skipping." %
page.title(asLink=True))
except pywikibot.LockedPage:
pywikibot.output(u"Page %s is locked?!" % page.title(asLink=True))
def tagNowcommons(self, imagepage, filename):
"""
Tagged the imag which has been moved to Commons for deletion.
"""
if pywikibot.Page(pywikibot.getSite("commons", "commons"), u"File:" + filename).exists():
# Get a fresh copy, force to get the page so we dont run into edit conflicts
imtxt = imagepage.get(force=True)
# Remove the move to commons templates
if imagepage.site().language() in moveToCommonsTemplate:
for moveTemplate in moveToCommonsTemplate[imagepage.site().language()]:
imtxt = re.sub(u"(?i)\{\{" + moveTemplate + u"[^\}]*\}\}", u"", imtxt)
# add {{NowCommons}}
if imagepage.site().language() in nowCommonsTemplate:
addTemplate = nowCommonsTemplate[imagepage.site().language()] % filename
else:
addTemplate = nowCommonsTemplate["_default"] % filename
if imagepage.site().language() in nowCommonsMessage:
commentText = nowCommonsMessage[imagepage.site().language()]
else:
commentText = nowCommonsMessage["_default"]
pywikibot.showDiff(imagepage.get(), imtxt + addTemplate)
imagepage.put(imtxt + addTemplate, comment=commentText)
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)
def tagUncategorized(templateTitle):
site = wikipedia.getSite()
language = site.language()
family = site.family.name
page = wikipedia.Page(wikipedia.getSite(), u'Template:%s' % (templateTitle,))
if not page.exists() or page.isRedirectPage():
return False
text = page.get()
oldtext = text
text = text + u'<noinclude>\n\n%s\n</noinclude>' % (uncategorizedTemplate.get(family).get(language), )
wikipedia.showDiff(oldtext, text)
try:
wikipedia.output(page.title())
page.put(text, editComment.get(family).get(language), maxTries=1)
except wikipedia.LockedPage:
return
except wikipedia.MaxTriesExceededError:
return
except wikipedia.EditConflict:
return
def addCoords(sourceWiki, lang, article, lat, lon, region, type, dim):
'''
Add the coordinates to article.
'''
if (article and lang and type):
coordTemplate = 'Coordinate'
site = wikipedia.getSite(lang, 'wikipedia')
page = wikipedia.Page(site, article)
try:
text = page.get()
except wikipedia.NoPage: # First except, prevent empty pages
logging.warning('Page empty: %s', article)
return False
except wikipedia.IsRedirectPage: # second except, prevent redirect
logging.warning('Page is redirect: %s', article)
wikipedia.output(u'%s is a redirect!' % article)
return False
except wikipedia.Error: # third exception, take the problem and print
logging.warning('Some error: %s', article)
wikipedia.output(u"Some error, skipping..")
return False
if coordTemplate in page.templates():
logging.info('Already has Coordinate template: %s', article)
return False
if 'Linn' in page.templates():
logging.info('Linn template without coords: %s', article)
return False
newtext = text
replCount = 1
coordText = u'{{Coordinate |NS=%s |EW=%s |type=%s |region=%s' % (lat, lon, type, region)
if (dim):
coordText += u' |dim=%s' % ( int(dim),)
coordText += '}}'
localCatName = wikipedia.getSite().namespace(WP_CATEGORY_NS)
catStart = r'\[\[(' + localCatName + '|Category):'
catStartPlain = u'[[' + localCatName + ':'
replacementText = u''
replacementText = coordText + '\n\n' + catStartPlain
# insert coordinate template before categories
newtext = re.sub(catStart, replacementText, newtext, replCount, flags=re.IGNORECASE)
if text != newtext:
logging.info('Adding coords to: %s', article)
comment = u'lisan artikli koordinaadid %s.wikist' % (sourceWiki)
wikipedia.showDiff(text, newtext)
modPage = wikipedia.input(u'Modify page: %s ([y]/n) ?' % (article) )
if (modPage.lower == 'y' or modPage == ''):
page.put(newtext, comment)
return True
else:
logging.info('Nothing to change: %s', article)
return False
else:
return False
def workon(page):
mysite = pywikibot.getSite()
try:
text = page.get()
except pywikibot.IsRedirectPage:
pywikibot.output(u'%s is a redirect page. Skipping' %
page.title(asLink=True))
return
except pywikibot.NoPage:
pywikibot.output(u'%s does not exist. Skipping' %
page.title(asLink=True))
return
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" %
page.title())
links = page.linkedPages()
if len(links) > 0:
pywikibot.getall(mysite, links)
else:
pywikibot.output('Nothing left to do.')
return
for page2 in links:
try:
target = page2.getRedirectTarget()
except (pywikibot.Error, pywikibot.SectionError):
continue
text = treat(text, page2, target)
if text != page.get():
comment = pywikibot.translate(mysite, msg)
pywikibot.showDiff(page.get(), text)
try:
page.put(text, comment)
except (pywikibot.Error):
pywikibot.output('Error: unable to put %s' %
page.title(asLink=True))
def save(self, text, page, comment, minorEdit=False, botflag=False):
# only save if something was changed
if text != page.get():
# Show the title of the page we're working on.
# Highlight the title in purple.
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% page.title())
# show what was changed
pywikibot.showDiff(page.get(), text)
pywikibot.output(u'Comment: %s' %comment)
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No'], ['y', 'N'], 'N')
if choice == 'y':
try:
# Save the page
page.put(text, comment=comment,
minorEdit=minorEdit, botflag=botflag)
except pywikibot.LockedPage:
pywikibot.output(u"Page %s is locked; skipping."
% page.title(asLink=True))
except pywikibot.EditConflict:
pywikibot.output(
u'Skipping %s because of edit conflict'
% (page.title()))
except pywikibot.SpamfilterError, error:
pywikibot.output(
u'Cannot change %s because of spam blacklist entry %s'
% (page.title(), error.url))
else:
return True
def addWeek(monday=None):
'''
Add another week to http://nl.wikipedia.org/wiki/Wikipedia:Te_verwijderen_categorie%C3%ABn
'''
page = wikipedia.Page(wikipedia.getSite(u'nl', u'wikipedia'),
u'Wikipedia:Te verwijderen categorieën')
pagetext = page.get()
#(year, week, Null) = monday.isocalendar()
year = monday.strftime('%Y')
week = monday.strftime('%W')
qmonday = monday + timedelta(weeks=3)
#(qyear, qweek, Null) = qmonday.isocalendar()
qyear = qmonday.strftime('%Y')
qweek = qmonday.strftime('%W')
#Add the current week template
pagetext = pagetext.replace(
u'<!-- HIERVOOR -->',
u'{{Wikipedia:Te verwijderen categorieën/Toegevoegd ' + str(year) +
u' week ' + str(week) + u'}}\n<!-- HIERVOOR -->')
#Remove the current week template from the queue
pagetext = pagetext.replace(
u'<!-- {{Wikipedia:Te verwijderen categorieën/Toegevoegd ' +
str(year) + u' week ' + str(week) + u'}} -->\n', u'')
#Add a new week template to the queue
pagetext = pagetext.replace(
u'<!-- EINDE QUEUE -->',
u'<!-- {{Wikipedia:Te verwijderen categorieën/Toegevoegd ' +
str(qyear) + u' week ' + str(qweek) + u'}} -->\n<!-- EINDE QUEUE -->')
wikipedia.showDiff(page.get(), pagetext)
page.put(
pagetext, u'{{Wikipedia:Te verwijderen categorieën/Toegevoegd ' +
str(year) + u' week ' + str(week) + u'}} erbij')
def treat(self, page):
# Show the title of the page we're working on.
# Highlight the title in purple.
wikipedia.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" % page.title())
try:
oldText = page.get()
# Inside image maps, don't touch selflinks, as they're used
# to create tooltip labels. See for example:
# http://de.wikipedia.org/w/index.php?title=Innenstadt_%28Bautzen%29&diff=next&oldid=35721641
if '<imagemap>' in oldText:
wikipedia.output(u'Skipping page %s because it contains an image map.' % page.aslink())
return
text = oldText
curpos = 0
while curpos < len(text):
match = self.linkR.search(text, pos = curpos)
if not match:
break
# Make sure that next time around we will not find this same hit.
curpos = match.start() + 1
text, jumpToBeginning = self.handleNextLink(page, text, match)
if jumpToBeginning:
curpos = 0
if oldText == text:
wikipedia.output(u'No changes necessary.')
else:
wikipedia.showDiff(oldText, text)
page.put_async(text)
except wikipedia.NoPage:
wikipedia.output(u"Page %s does not exist?!" % page.aslink())
except wikipedia.IsRedirectPage:
wikipedia.output(u"Page %s is a redirect; skipping." % page.aslink())
except wikipedia.LockedPage:
wikipedia.output(u"Page %s is locked?!" % page.aslink())
def processCategory(page):
'''
Process a single category
'''
templates = page.templatesWithParams()
fields = {}
for (template, params) in templates:
if template==u'Air Force header':
for param in params:
#Split at =
(field, sep, value) = param.partition(u'=')
if not value==u'':
fields[field]=value.strip()
# Process a gallery at the US Air Force site
if fields.get('id'):
if fields.get('subject'):
target = fields.get('subject')
else:
target = page.titleWithoutNamespace()
processGallery(fields.get('id'), target)
# Mark the category as done so we can skip it later on
oldtext = page.get()
newtext = re.sub(u'\{\{Air Force header', u'{{Air Force header\n|done=~~~~', oldtext)
comment = u'Transfered all images from http://www.af.mil/photos/mediagallery.asp?id=' + fields.get('id') + u' to [[Category:' + target + u']]'
wikipedia.showDiff(oldtext, newtext)
page.put(newtext, comment)
def appendtext(page, apptext):
global always
if page.isRedirectPage():
page = page.getRedirectTarget()
if not page.exists():
if page.isTalkPage():
text = u''
else:
raise pywikibot.NoPage(u"Page '%s' does not exist" % page.title())
else:
text = page.get()
# Here you can go editing. If you find you do not
# want to edit this page, just return
oldtext = text
text += apptext
if text != oldtext:
pywikibot.showDiff(oldtext, text)
if not always:
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?', ['Yes', 'No', 'All'],
['y', 'N', 'a'], 'N')
if choice == 'a':
always = True
if always or choice == 'y':
page.put(text, pywikibot.translate(pywikibot.getSite(), comment))
def workon(page):
mysite = pywikibot.getSite()
try:
text = page.get()
except pywikibot.IsRedirectPage:
pywikibot.output(u'%s is a redirect page. Skipping'
% page.title(asLink=True))
return
except pywikibot.NoPage:
pywikibot.output(u'%s does not exist. Skipping'
% page.title(asLink=True))
return
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% page.title())
links = page.linkedPages()
if len(links) > 0:
pywikibot.getall(mysite,links)
else:
pywikibot.output('Nothing left to do.')
return
for page2 in links:
try:
target = page2.getRedirectTarget()
except (pywikibot.Error,pywikibot.SectionError):
continue
text = treat(text, page2, target)
if text != page.get():
comment = i18n.twtranslate(mysite, 'fixing_redirects-fixing')
pywikibot.showDiff(page.get() ,text)
try:
page.put(text, comment)
except (pywikibot.Error):
pywikibot.output('Error: unable to put %s'
% page.title(asLink=True))
def workon(page):
mysite = wikipedia.getSite()
try:
text = page.get()
except wikipedia.IsRedirectPage:
wikipedia.output(u'%s is a redirect page. Skipping' % page.aslink())
return
except wikipedia.NoPage:
wikipedia.output(u'%s does not exist. Skipping' % page.aslink())
return
wikipedia.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" % page.title())
links = page.linkedPages()
if len(links) > 0:
wikipedia.getall(mysite,links)
else:
wikipedia.output('Nothing left to do.')
return
for page2 in links:
try:
target = page2.getRedirectTarget()
except (wikipedia.Error,wikipedia.SectionError):
continue
text = treat(text, page2, target)
if text != page.get():
comment = wikipedia.translate(mysite, msg)
wikipedia.showDiff(page.get() ,text)
try:
page.put(text, comment)
except (wikipedia.Error):
wikipedia.output('Error: unable to put %s' % page.aslink())
def convertAllHTMLTables(self, text):
'''
Converts all HTML tables in text to wiki syntax.
Returns the converted text, the number of converted tables and the
number of warnings that occured.
'''
text = self.markActiveTables(text)
convertedTables = 0
warningSum = 0
warningMessages = u''
while True:
table, start, end = self.findTable(text)
if not table:
# no more HTML tables left
break
pywikibot.output(">> Table %i <<" % (convertedTables + 1))
# convert the current table
newTable, warningsThisTable, warnMsgsThisTable = self.convertTable(
table)
# show the changes for this table
if not self.quietMode:
pywikibot.showDiff(table.replace('##table##', 'table'),
newTable)
warningSum += warningsThisTable
for msg in warnMsgsThisTable:
warningMessages += 'In table %i: %s' % (convertedTables + 1,
msg)
text = text[:start] + newTable + text[end:]
convertedTables += 1
pywikibot.output(warningMessages)
return text, convertedTables, warningSum
def writeMainFreeUploads(subpages):
site = wikipedia.getSite(u'en', u'wikipedia')
page = wikipedia.Page(site, u'User:Multichill/Free_uploads')
oldtext = page.get()
text = u'__TOC__\n'
#text = text + u'== Links to day pages ==\n'
#text = text + u'{{Special:PrefixIndex/User:Multichill/Free uploads/20}}\n'
text = text + u'== This week ==\n'
i = 0
limit = 7
# From new to old
subpages.reverse()
for subpage in subpages:
date = subpage.replace(u'User:Multichill/Free uploads/', u'')
if i < limit:
text = text + u'===[[%s|%s]]===\n' % (subpage, date)
text = text + u'{{%s}}\n' % (subpage,)
elif i == limit:
text = text + u'== Older ==\n'
text = text + u'* [[%s|%s]]\n' % (subpage, date)
else:
text = text + u'* [[%s|%s]]\n' % (subpage, date)
i = i + 1
comment = u'Updating list, %d subpages contain images' % (len(subpages),)
wikipedia.showDiff(oldtext, text)
wikipedia.output(comment)
page.put(text, comment)
def save(self, text, page, comment=None, **kwargs):
# only save if something was changed
if text != page.get():
# Show the title of the page we're working on.
# Highlight the title in purple.
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% page.title())
# show what was changed
pywikibot.showDiff(page.get(), text)
pywikibot.output(u'Comment: %s' % comment)
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No'], ['y', 'N'], 'N')
if choice == 'y':
try:
# Save the page
page.put(text, comment=comment or self.comment, **kwargs)
except pywikibot.LockedPage:
pywikibot.output(u"Page %s is locked; skipping."
% page.title(asLink=True))
except pywikibot.EditConflict:
pywikibot.output(
u'Skipping %s because of edit conflict'
% (page.title()))
except pywikibot.SpamfilterError, error:
pywikibot.output(
u'Cannot change %s because of spam blacklist entry %s'
% (page.title(), error.url))
else:
return True
def put_page(self, page, new):
"""
Prints diffs between orginal and new (text), puts new text for page
"""
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% page.title())
pywikibot.showDiff(page.get(), new)
if not self.acceptall:
choice = pywikibot.inputChoice(u'Do you want to accept ' +
u'these changes?',
['Yes', 'No', 'All'],
['y', 'N', 'a'], 'N')
if choice == 'a':
self.acceptall = True
if choice == 'y':
page.put_async(new)
if self.acceptall:
try:
page.put(new)
except pywikibot.EditConflict:
pywikibot.output(u'Skipping %s because of edit conflict'
% (page.title(),))
except pywikibot.SpamfilterError, e:
pywikibot.output(
u'Cannot change %s because of blacklist entry %s'
% (page.title(), e.url))
except pywikibot.PageNotSaved, error:
pywikibot.output(u'Error putting page: %s' % (error.args,))
def process_article(page, tag):
EditMsg = "Robot: Tagging {{Film|%s}}" % tag
wikipedia.setAction(EditMsg)
try:
wikitext = page.get()
except wikipedia.NoPage:
page.put("{{Film|%s}}" % tag)
return
except wikipedia.IsRedirectPage:
return
if re.search(tag, wikitext, re.I):
print "Skipping " + str(page)
return
# Fix Casing (Reduces the number of possible expressions)
wikitext = re.compile(r'\{\{\s*(template:|)film',
re.IGNORECASE).sub(r'{{Film', wikitext)
state0 = wikitext
# Add tf parameter
wikitext = re.compile(r'\{\{\s*film(.*?)\}\}',
re.IGNORECASE).sub(r'{{Film\1|%s}}' % tag, wikitext)
wikipedia.showDiff(state0, wikitext)
if (wikitext != state0):
try:
print 'Going to edit %s' % str(page)
wikipedia.output(u'WRITE: Adding %s bytes.' %
str(len(wikitext) - len(state0)))
page.put(wikitext)
except KeyboardInterrupt:
sys.exit()
def process_article(page, tag):
EditMsg = "Robot: Tagging {{Film|%s}}" %tag
wikipedia.setAction(EditMsg)
try:
wikitext = page.get()
except wikipedia.NoPage:
page.put("{{Film|%s}}" %tag)
return
except wikipedia.IsRedirectPage:
return
if re.search(tag,wikitext,re.I):
print "Skipping " + str(page)
return
# Fix Casing (Reduces the number of possible expressions)
wikitext = re.compile(r'\{\{\s*(template:|)film', re.IGNORECASE).sub(r'{{Film', wikitext)
state0 = wikitext
# Add tf parameter
wikitext = re.compile(r'\{\{\s*film(.*?)\}\}', re.IGNORECASE).sub(r'{{Film\1|%s}}' %tag, wikitext)
wikipedia.showDiff(state0, wikitext)
if (wikitext != state0):
try:
print 'Going to edit %s' %str(page)
wikipedia.output(u'WRITE: Adding %s bytes.' % str(len(wikitext)-len(state0)))
page.put(wikitext)
except KeyboardInterrupt:
sys.exit()
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)
def addTopicCategory(page, conn, cursor):
wikipedia.output(u'Working on: %s' % page.title())
templates = page.templates()
if not u'Rijksmonument' in page.templates():
wikipedia.output(u'Rijksmonument template not found at: %s' % page.title())
return False
rijksmonumentid=-1
for (template, params) in page.templatesWithParams():
if template==u'Rijksmonument':
if len(params)==1:
try:
rijksmonumentid = int(params[0])
except ValueError:
wikipedia.output(u'Unable to extract a valid id')
break
if (rijksmonumentid < 0 or 600000 < rijksmonumentid ):
wikipedia.output(u'Invalid id')
return False
oorspr_functie = getOorspronkelijkeFunctie(rijksmonumentid, conn, cursor)
if not oorspr_functie:
wikipedia.output(u'No oorspr_functie found')
return False
oldtext = page.get()
newtext = oldtext + u'{{subst:Rijksmonument category|%s|subst=subst:}}' % (oorspr_functie,)
comment = u'Adding [[Template:Rijksmonument category|"%s" category]] based on Rijksmonument identifier' % (oorspr_functie,)
wikipedia.showDiff(oldtext, newtext)
page.put(newtext, comment)
def save(self, page, text):
if text != page.get():
# Show the title of the page we're working on.
# Highlight the title in purple.
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<"
% page.title())
pywikibot.showDiff(page.get(), text)
if not self.always:
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'Always yes'], ['y', 'N', 'a'], 'N')
if choice == 'n':
return
elif choice == 'a':
self.always = True
if self.always:
try:
page.put(text, comment=self.comment)
except pywikibot.EditConflict:
pywikibot.output(u'Skipping %s because of edit conflict'
% (page.title(),))
except pywikibot.SpamfilterError, e:
pywikibot.output(
u'Cannot change %s because of blacklist entry %s'
% (page.title(), e.url))
except pywikibot.LockedPage:
pywikibot.output(u'Skipping %s (locked page)'
% (page.title(),))
def save(self, page, newText):
"""
Saves the page to the wiki, if the user accepts the changes made.
"""
pywikibot.showDiff(page.get(), newText)
if not self.always:
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'Always yes'], ['y', 'N', 'a'], 'Y')
if choice == 'n':
return
elif choice == 'a':
self.always = True
if self.always:
try:
page.put(newText)
except pywikibot.EditConflict:
pywikibot.output(u'Skipping %s because of edit conflict'
% (page.title(),))
except pywikibot.SpamfilterError, e:
pywikibot.output(
u'Cannot change %s because of blacklist entry %s'
% (page.title(), e.url))
except pywikibot.LockedPage:
pywikibot.output(u'Skipping %s (locked page)' % (page.title(),))
def convertList(page):
'''
Convert a list of NRHP entries. Both headers and items will be converted.
'''
wikipedia.output(u'Working on %s' % page.title())
text = page.get()
try:
newtext = convertHeaders(page, text)
newtext = convertItems(page, newtext)
except TypeError or AttributeError:
wikipedia.output(
u'One of the regexes failed at %s, skipping this page' %
(page.title, ))
traceback.print_exc(file=sys.stdout)
time.sleep(10)
return u'Failed'
if not text == newtext:
wikipedia.showDiff(text, newtext)
comment = u'Converting list to use [[Template:NRHP header]] and [[Template:NRHP row]]'
#choice = wikipedia.inputChoice(u'Do you want to accept these changes?', ['Yes', 'No'], ['y', 'n'], 'n')
choice = 'y'
if choice == 'y':
#DEBUG
page.put(newtext, comment)
return u'Success'
#wikipedia.output(newtext)
return u'Unchanged'
def processCategory(page):
'''
Process a single category
'''
templates = page.templatesWithParams()
fields = {}
for (template, params) in templates:
if template == u'Air Force header':
for param in params:
#Split at =
(field, sep, value) = param.partition(u'=')
if not value == u'':
fields[field] = value.strip()
# Process a gallery at the US Air Force site
if fields.get('id'):
if fields.get('subject'):
target = fields.get('subject')
else:
target = page.titleWithoutNamespace()
processGallery(fields.get('id'), target)
# Mark the category as done so we can skip it later on
oldtext = page.get()
newtext = re.sub(u'\{\{Air Force header',
u'{{Air Force header\n|done=~~~~', oldtext)
comment = u'Transfered all images from http://www.af.mil/photos/mediagallery.asp?id=' + fields.get(
'id') + u' to [[Category:' + target + u']]'
wikipedia.showDiff(oldtext, newtext)
page.put(newtext, comment)
def appendtext(page, apptext):
global always
if page.isRedirectPage():
page = page.getRedirectTarget()
if not page.exists():
if page.isTalkPage():
text = u''
else:
raise pywikibot.NoPage(u"Page '%s' does not exist" % page.title())
else:
text = page.get()
# Here you can go editing. If you find you do not
# want to edit this page, just return
oldtext = text
text += apptext
if text != oldtext:
pywikibot.showDiff(oldtext, text)
if not always:
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?', ['Yes', 'No', 'All'],
['y', 'N', 'a'], 'N')
if choice == 'a':
always = True
if always or choice == 'y':
page.put(text, pywikibot.translate(pywikibot.getSite(), comment))
def convertAllHTMLTables(self, text):
"""
Converts all HTML tables in text to wiki syntax.
Returns the converted text, the number of converted tables and the
number of warnings that occured.
"""
text = self.markActiveTables(text)
convertedTables = 0
warningSum = 0
warningMessages = u""
while True:
table, start, end = self.findTable(text)
if not table:
# no more HTML tables left
break
wikipedia.output(">> Table %i <<" % (convertedTables + 1))
# convert the current table
newTable, warningsThisTable, warnMsgsThisTable = self.convertTable(table)
# show the changes for this table
if not self.quietMode:
wikipedia.showDiff(table.replace("##table##", "table"), newTable)
warningSum += warningsThisTable
for msg in warnMsgsThisTable:
warningMessages += "In table %i: %s" % (convertedTables + 1, msg)
text = text[:start] + newTable + text[end:]
convertedTables += 1
wikipedia.output(warningMessages)
return text, convertedTables, warningSum
def save(self, page, newText):
"""
Saves the page to the wiki, if the user accepts the changes made.
"""
pywikibot.showDiff(page.get(), newText)
if not self.always:
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'Always yes'], ['y', 'N', 'a'], 'Y')
if choice == 'n':
return
elif choice == 'a':
self.always = True
if self.always:
try:
page.put(newText)
except pywikibot.EditConflict:
pywikibot.output(u'Skipping %s because of edit conflict'
% (page.title(),))
except pywikibot.SpamfilterError, e:
pywikibot.output(
u'Cannot change %s because of blacklist entry %s'
% (page.title(), e.url))
except pywikibot.LockedPage:
pywikibot.output(u'Skipping %s (locked page)' % (page.title(),))
def treat(self, page):
# Show the title of the page we're working on.
# Highlight the title in purple.
wikipedia.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" % page.title())
try:
oldText = page.get()
text = oldText
curpos = 0
while curpos < len(text):
match = self.linkR.search(text, pos = curpos)
if not match:
break
# Make sure that next time around we will not find this same hit.
curpos = match.start() + 1
text, jumpToBeginning = self.handleNextLink(text, match)
if jumpToBeginning:
curpos = 0
if oldText == text:
wikipedia.output(u'No changes necessary.')
else:
wikipedia.showDiff(oldText, text)
page.put(text)
except wikipedia.NoPage:
wikipedia.output(u"Page %s does not exist?!" % page.aslink())
except wikipedia.IsRedirectPage:
wikipedia.output(u"Page %s is a redirect; skipping." % page.aslink())
except wikipedia.LockedPage:
wikipedia.output(u"Page %s is locked?!" % page.aslink())
def tagNowCommons(wImage, cImage, timestamp):
site = wikipedia.getSite()
language = site.language()
family = site.family.name
imagepage = wikipedia.ImagePage(wikipedia.getSite(), wImage)
if not imagepage.exists() or imagepage.isRedirectPage():
return
if skips.get(family) and skips.get(family).get(language):
localskips = skips.get(family).get(language)
else:
localskips = skips.get('_default')
for template in imagepage.templates():
title = template.replace(u'_', u' ').strip()
if title in localskips:
return
text = imagepage.get()
oldtext = text
text = u'{{NowCommons|File:%s|date=%s|bot=~~~}}\n' % (cImage.replace(
u'_', u' '), timestamp) + text
comment = u'File is available on Wikimedia Commons.'
wikipedia.showDiff(oldtext, text)
try:
imagepage.put(text, comment)
#print u'put'
except wikipedia.LockedPage:
return
def tagNowCommons(wImage, cImage, timestamp):
site = wikipedia.getSite()
language = site.language()
family = site.family.name
imagepage = wikipedia.ImagePage(wikipedia.getSite(), wImage)
if not imagepage.exists() or imagepage.isRedirectPage():
return
if skips.get(family) and skips.get(family).get(language):
localskips = skips.get(family).get(language)
else:
localskips = skips.get('_default')
for template in imagepage.templates():
title = template.replace(u'_', u' ').strip()
if title in localskips:
return
text = imagepage.get()
oldtext = text
text = u'{{NowCommons|File:%s|date=%s|bot=~~~}}\n' % (cImage.replace(u'_', u' '), timestamp) + text
comment = u'File is available on Wikimedia Commons.'
wikipedia.showDiff(oldtext, text)
try:
imagepage.put(text, comment)
#print u'put'
except wikipedia.LockedPage:
return
def save(self, page, text):
if text != page.get():
# Show the title of the page we're working on.
# Highlight the title in purple.
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" %
page.title())
pywikibot.showDiff(page.get(), text)
if not self.always:
choice = pywikibot.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'Always yes'], ['y', 'N', 'a'], 'N')
if choice == 'n':
return
elif choice == 'a':
self.always = True
if self.always:
try:
page.put(text, comment=self.comment)
except pywikibot.EditConflict:
pywikibot.output(u'Skipping %s because of edit conflict' %
(page.title(), ))
except pywikibot.SpamfilterError, e:
pywikibot.output(
u'Cannot change %s because of blacklist entry %s' %
(page.title(), e.url))
except pywikibot.LockedPage:
pywikibot.output(u'Skipping %s (locked page)' %
(page.title(), ))
def tagNowcommons(self, imagepage, filename):
""" Tagged the imag which has been moved to Commons for deletion. """
if pywikibot.Page(pywikibot.getSite('commons', 'commons'),
u'File:' + filename).exists():
# Get a fresh copy, force to get the page so we dont run into edit
# conflicts
imtxt = imagepage.get(force=True)
# Remove the move to commons templates
if imagepage.site().language() in moveToCommonsTemplate:
for moveTemplate in moveToCommonsTemplate[imagepage.site().language()]:
imtxt = re.sub(u'(?i)\{\{' + moveTemplate +
u'[^\}]*\}\}', u'', imtxt)
# add {{NowCommons}}
if imagepage.site().language() in nowCommonsTemplate:
addTemplate = nowCommonsTemplate[
imagepage.site().language()] % filename
else:
addTemplate = nowCommonsTemplate['_default'] % filename
commentText = i18n.twtranslate(
imagepage.site(), 'commons-file-now-available',
{'localfile': imagepage.title(withNamespace=False),
'commonsfile': filename})
pywikibot.showDiff(imagepage.get(), imtxt + addTemplate)
imagepage.put(imtxt + addTemplate, comment=commentText)
def tagUncategorized(templateTitle):
site = wikipedia.getSite()
language = site.language()
family = site.family.name
page = wikipedia.Page(wikipedia.getSite(), u'Template:%s' % (templateTitle,))
if not page.exists() or page.isRedirectPage():
return False
text = page.get()
oldtext = text
text = text + u'<noinclude>\n\n%s\n</noinclude>' % (uncategorizedTemplate.get(family).get(language), )
wikipedia.showDiff(oldtext, text)
try:
wikipedia.output(page.title())
page.put(text, editComment.get(family).get(language), maxTries=1)
except wikipedia.LockedPage:
return
except wikipedia.MaxTriesExceededError:
return
except wikipedia.EditConflict:
return
def put_page(self, page, new):
""" Prints diffs between orginal and new (text), puts new text for page
"""
pywikibot.output(u"\n\n>>> \03{lightpurple}%s\03{default} <<<" %
page.title())
pywikibot.showDiff(page.get(), new)
if not self.acceptall:
choice = pywikibot.inputChoice(
u'Do you want to accept ' + u'these changes?',
['Yes', 'No', 'All'], ['y', 'N', 'a'], 'N')
if choice == 'a':
self.acceptall = True
if choice == 'y':
page.put_async(new, self.msg)
if self.acceptall:
try:
page.put(new, self.msg)
except pywikibot.EditConflict:
pywikibot.output(u'Skipping %s because of edit conflict' %
page.title())
except pywikibot.SpamfilterError, e:
pywikibot.output(
u'Cannot change %s because of blacklist entry %s' %
(page.title(), e.url))
except pywikibot.PageNotSaved, error:
pywikibot.error(u'putting page: %s' % error.args)
def updateInterwiki(self, wikipediaPage=None, commonsPage=None):
'''
Update the interwiki's at commons from a wikipedia page. The bot just
replaces the interwiki links at the commons page with the interwiki's from
the wikipedia page. This should probably be more intelligent. We could use
add all the interwiki's and remove duplicates. Or only remove language links
if multiple language links to the same language exist.
This function is disabled for the moment untill i figure out what the best
way is to update the interwiki's.
'''
interwikis = {}
comment = u''
interwikilist = wikipediaPage.interwiki()
interwikilist.append(wikipediaPage)
for interwikiPage in interwikilist:
interwikis[interwikiPage.site()] = interwikiPage
oldtext = commonsPage.get()
# The commonssite object doesnt work with interwiki's
newtext = pywikibot.replaceLanguageLinks(oldtext, interwikis,
pywikibot.getSite(u'nl'))
comment = u'Updating interwiki\'s from [[' + \
wikipediaPage.site().language() + \
u':' + wikipediaPage.title() + u']]'
if newtext != oldtext:
#This doesnt seem to work. Newtext has some trailing whitespace
pywikibot.showDiff(oldtext, newtext)
commonsPage.put(newtext=newtext, comment=comment)
def createredir(origname):
site = wikipedia.getSite()
redircontent = re.sub('OH', 'Ohio', origname)
redircontent = '#REDIRECT [[%s]]' %(redircontent)
page = wikipedia.Page(site, origname)
print page
wikipedia.showDiff('', redircontent)
page.put(redircontent, 'Creating redirect per [[WP:BOTREQ#Need_some_redlinks_to_become_redirects|BOTREQ]]')
def changeCommonscat (page = None, oldtemplate = u'', oldcat = u'', newtemplate = u'', newcat = u''):
'''
Change the current commonscat template and target.
'''
newtext = re.sub(u'(?i)\{\{' + oldtemplate + u'\|?[^}]*\}\}', u'{{' + newtemplate + u'|' + newcat + u'}}', page.get())
comment = u'Changing commonscat link from [[:Commons:Category:' + oldcat + u'|' + oldcat + u']] to [[:Commons:Category:' + newcat + u'|' + newcat + u']]'
wikipedia.showDiff(page.get(), newtext)
page.put(newtext, comment)
def main():
pagesDict = {
'Template:Weather_World_C/Auto':
"http://tools.wikimedia.de/~skenmy/wnweather/overlays/%d%b%y-%H-C-world",
'Template:Weather_World_F/Auto':
"http://tools.wikimedia.de/~skenmy/wnweather/overlays/%d%b%y-%H-F-world",
}
args = wikipedia.handleArgs()
all = False
for currentArgument in args:
if currentArgument.startswith("-always"):
all = True
for pageName in pagesDict:
formatUrl = pagesDict[pageName]
now = datetime.datetime.utcnow()
urlo = now.strftime(formatUrl)
wikipedia.output(u'Prendo la pagina dal server...')
try:
htmlText = pageText(urlo)
except urllib2.HTTPError:
try:
wikipedia.output(
u"Errore del server. Aspetto 10 secondi... " +
time.strftime("%d %b %Y %H:%M:%S (UTC)", time.gmtime()))
time.sleep(10)
htmlText = pageText(urlo)
except urllib2.HTTPError:
wikipedia.output(u"Errore del server. Chiudo.")
return
htmlText = re.sub("Wikinews Weather Service",
"Servizio Meteo di Wikinotizie", htmlText)
htmlText = re.sub("World Map", r"Mondo", htmlText)
htmlText = re.sub(
"''\d{2}:\d{2} UTC .*? .*? .*?''</span>",
"''{{subst:LOCALDAY}} {{subst:LOCALMONTHNAME}} {{subst:LOCALYEAR}}, {{subst:LOCALHOUR}}:00 [[w:CET|<span style=\"color:white; text-decoration:underline;\">CET</span>]] ({{subst:CURRENTHOUR}}:00 [[w:UTC|<span style=\"color:white; text-decoration:underline;\">UTC</span>]])''</span>",
htmlText)
page = wikipedia.Page(wikipedia.getSite(code='it', fam='wikinews'),
pageName)
if page.exists():
oldtext = page.get()
else:
oldtext = ""
wikipedia.showDiff(oldtext, htmlText)
if not all:
choice = wikipedia.inputChoice(u"Modificare?",
['Yes', 'No', 'All'],
['y', 'N', 'a'], 'N')
else:
choice = 'y'
if choice in ['A', 'a']:
all = True
choice = 'y'
if choice in ['Y', 'y']:
page.put(htmlText, u"Bot: Aggiorno il meteo")
def categoriesChecked(category):
page = wikipedia.Page(wikipedia.getSite(), category)
if (page.exists()):
old = u'\{\{UncategorizedHeader([^\}]*)\}\}'
new = u'{{UncategorizedHeader\\1|galleries=~~~~}}'
newtext = wikipedia.replaceExcept(page.get(), old, new, [])
comment = u'No more images in galleries'
wikipedia.showDiff(page.get(), newtext)
page.put(newtext, comment)
def main():
args = wikipedia.handleArgs()
all = False
for currentArgument in args:
if currentArgument.startswith("-always"):
all = True
templateFile = codecs.open("modello_wikinews_oil.txt", "r", "utf-8")
modelloVoce = templateFile.read() # Legge il modello della pagina
templateFile.close()
now = datetime.datetime.utcnow()
urlo = "http://www.nymex.com/index.aspx"
wikipedia.output(u'Prendo la pagina dal server...')
try:
htmlText = pageText(urlo)
except urllib2.HTTPError:
try:
wikipedia.output(u"Errore del server. Aspetto 10 secondi... " + time.strftime("%d %b %Y %H:%M:%S (UTC)", time.gmtime()) )
time.sleep(10)
htmlText = pageText(urlo)
except urllib2.HTTPError:
wikipedia.output(u"Errore del server. Chiudo.")
return
prezzoCL = re.search("<span id=\"LastCL\".*?>(.*?)</span>", htmlText).group(1)
changeCL = re.search("<span id=\"ChangeCL\".*?>(<font.*?>)?(.*?)(</font>)?</span>", htmlText).group(2)
prezzoBZ = re.search("<span id=\"LastBZ\".*?>(.*?)</span>", htmlText).group(1)
changeBZ = re.search("<span id=\"ChangeBZ\".*?>(<font.*?>)?(.*?)(</font>)?</span>", htmlText).group(2)
elencoSostituzioni = { # Sostituisce le variabili nel modello
'#CL_curr': prezzoCL,
'#CL_diff': changeCL,
'#BZ_curr': prezzoBZ,
'#BZ_diff': changeBZ,
}
nuovoTesto = massiveReplace(elencoSostituzioni, modelloVoce)
#nuovoTesto = re.sub('\|- - - -', '|N.D.', nuovoTesto) # Per quando i dati non sono disponibili
page = wikipedia.Page(wikipedia.getSite(code='it', fam='wikinews'), "Template:Dati petrolio/Auto")
if page.exists():
oldtext = page.get()
else:
oldtext = ""
wikipedia.showDiff(oldtext, nuovoTesto)
if not all:
choice = wikipedia.inputChoice(u"Modificare?", ['Yes', 'No', 'All'], ['y', 'N', 'a'], 'N')
else:
choice = 'y'
if choice in ['A', 'a']:
all = True
choice = 'y'
if choice in ['Y', 'y']:
page.put(nuovoTesto, u"Bot: Aggiorno prezzi petrolio")
def main():
args = wikipedia.handleArgs()
all = False
for currentArgument in args:
if currentArgument.startswith("-always"):
all = True
templateFile = codecs.open("modello_palinsesto.txt", "r", "utf-8")
modelloVoce = templateFile.read() # Legge il modello della pagina
templateFile.close()
now = datetime.datetime.utcnow()
fasceOrarie = ['mattina', 'pomeriggio', 'sera']
pagineHtml = {}
elencoSostituzioni = {}
urlBase = "http://city.corriere.it/tv/tv.php?fascia="
for i in fasceOrarie:
urlo = urlBase + i
print urlo
wikipedia.output(u'Prendo la pagina dal server...')
try:
pagineHtml[i] = pageText(urlo)
except urllib2.HTTPError:
try:
wikipedia.output(u"Errore del server. Aspetto 10 secondi... " + time.strftime("%d %b %Y %H:%M:%S (UTC)", time.gmtime()) )
time.sleep(10)
pagineHtml[i] = pageText(urlo)
except urllib2.HTTPError:
wikipedia.output(u"Errore del server. Chiudo.")
return
elencoSostituzioni['#rai1-' + i] = getProgramList('RAI 1', pagineHtml[i])
elencoSostituzioni['#rai2-' + i] = getProgramList('RAI 2', pagineHtml[i])
elencoSostituzioni['#rai3-' + i] = getProgramList('RAI 3', pagineHtml[i])
elencoSostituzioni['#rete4-' + i] = getProgramList('RETE 4', pagineHtml[i])
elencoSostituzioni['#canale5-' + i] = getProgramList('CANALE 5', pagineHtml[i])
elencoSostituzioni['#italia1-' + i] = getProgramList('ITALIA 1', pagineHtml[i])
elencoSostituzioni['#la7-' + i] = getProgramList('LA7', pagineHtml[i])
nuovoTesto = massiveReplace(elencoSostituzioni, modelloVoce)
page = wikipedia.Page(wikipedia.getSite(code='it', fam='wikinews'), "Template:ProgrammiTV")
if page.exists():
oldtext = page.get()
else:
oldtext = ""
wikipedia.showDiff(oldtext, nuovoTesto)
if not all:
choice = wikipedia.inputChoice(u"Modificare?", ['Yes', 'No', 'All'], ['y', 'N', 'a'], 'N')
else:
choice = 'y'
if choice in ['A', 'a']:
all = True
choice = 'y'
if choice in ['Y', 'y']:
page.put(nuovoTesto, u"Bot: Aggiorno palinsesto TV")
def categories(self):
for page in self.generator:
try:
wikipedia.output(u'\n>>>> %s <<<<' % page.title())
getCommons = wikipedia.getSite('commons', 'commons')
commonsCategory = catlib.Category(getCommons,
'Category:%s' % page.title())
try:
getcommonscat = commonsCategory.get(get_redirect=True)
commonsCategoryTitle = commonsCategory.title()
categoryname = commonsCategoryTitle.split('Category:',
1)[1]
if page.title() == categoryname:
oldText = page.get()
text = oldText
# for commonscat template
findTemplate = re.compile(ur'\{\{[Cc]ommons')
s = findTemplate.search(text)
findTemplate2 = re.compile(ur'\{\{[Ss]isterlinks')
s2 = findTemplate2.search(text)
if s or s2:
wikipedia.output(u'** Already done.')
else:
text = wikipedia.replaceCategoryLinks(
text + u'{{commonscat|%s}}' % categoryname,
page.categories())
if oldText != text:
wikipedia.showDiff(oldText, text)
if not self.acceptall:
choice = wikipedia.inputChoice(
u'Do you want to accept these changes?',
['Yes', 'No', 'All'], ['y', 'N', 'a'],
'N')
if choice == 'a':
self.acceptall = True
if self.acceptall or choice == 'y':
try:
msg = wikipedia.translate(
wikipedia.getSite(), comment2)
page.put(text, msg)
except wikipedia.EditConflict:
wikipedia.output(
u'Skipping %s because of edit conflict'
% (page.title()))
except wikipedia.NoPage:
wikipedia.output(u'Category does not exist in Commons!')
except wikipedia.NoPage:
wikipedia.output(u'Page %s does not exist?!' % page.title())
except wikipedia.IsRedirectPage:
wikipedia.output(u'Page %s is a redirect; skipping.' %
page.title())
except wikipedia.LockedPage:
wikipedia.output(u'Page %s is locked?!' % page.title())
def run(self):
hints, removeHints = self.warnfileReader.getHints()
k = hints.keys()
k.sort()
print "Fixing... %i pages" % len(k)
for page in k:
old = {}
try:
for page2 in page.interwiki():
old[page2.site()] = page2
except wikipedia.IsRedirectPage:
wikipedia.output(u"%s is a redirect page; not changing" %
page.aslink())
continue
except wikipedia.NoPage:
wikipedia.output(u"Page %s not found; skipping" %
page.aslink())
continue
new = {}
new.update(old)
if page in hints:
for page2 in hints[page]:
site = page2.site()
new[site] = page2
if page in removeHints:
for page2 in removeHints[page]:
site = page2.site()
try:
del new[site]
except KeyError:
pass
mods, adding, removing, modifying = interwiki.compareLanguages(
old, new, insite=page.site())
if mods:
wikipedia.output(page.aslink() + mods)
oldtext = page.get()
newtext = wikipedia.replaceLanguageLinks(oldtext, new)
if 1:
wikipedia.showDiff(oldtext, newtext)
try:
status, reason, data = page.put(newtext,
comment='warnfile ' +
mods)
except wikipedia.LockedPage:
wikipedia.output(u"Page is locked. Skipping.")
continue
except wikipedia.SpamfilterError, e:
wikipedia.output(
u'Cannot change %s because of blacklist entry %s' %
(page.title(), e.url))
continue
except wikipedia.Error:
wikipedia.output(u"Error while saving page.")
continue
if str(status) != '302':
print status, reason
