def main():
'''
The main loop
'''
wikipedia.setSite(wikipedia.getSite(u'commons', u'commons'))
conn = None
cursor = None
(conn, cursor) = connectDatabase()
imagerecat.initLists()
generator = None;
genFactory = pagegenerators.GeneratorFactory()
mark = True
for arg in wikipedia.handleArgs():
if arg.startswith('-dontmark'):
mark = False
elif arg.startswith('-page'):
if len(arg) == 5:
generator = [wikipedia.Page(wikipedia.getSite(), wikipedia.input(u'What page do you want to use?'))]
else:
generator = [wikipedia.Page(wikipedia.getSite(), arg[6:])]
elif arg.startswith('-yesterday'):
generator = [wikipedia.Page(wikipedia.getSite(), u'Category:Media_needing_categories_as_of_' + getYesterday())]
else:
generator = genFactory.handleArg(arg)
if generator:
for page in generator:
if((page.namespace() == 14) and (page.title().startswith(u'Category:Media needing categories as of'))):
wikipedia.output(u'Working on ' + page.title())
for (image, gals, cats) in getImagesToCategorize(cursor, page.titleWithoutNamespace()):
categorizeImage(image, gals, imagerecat.applyAllFilters(cats))
if (mark):
categoriesChecked(page.title())
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 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 getNewCategories(self, imagepage):
'''
Get a categories for the image
Dont forget to filter
'''
result = u''
(commonshelperCats, usage, galleries) = imagerecat.getCommonshelperCats(imagepage)
newcats = imagerecat.applyAllFilters(commonshelperCats)
for newcat in newcats:
result = result + u'[[Category:' + newcat + u']] '
return result
def getNewCategories(self, imagepage):
'''
Get a categories for the image
Dont forget to filter
'''
result = u''
(commonshelperCats, usage, galleries) = imagerecat.getCommonshelperCats(imagepage)
newcats = imagerecat.applyAllFilters(commonshelperCats)
for newcat in newcats:
result = result + u'[[Category:' + newcat + u']] '
return result
def getNewCategories(self, imagepage):
"""
Get a categories for the image
Dont forget to filter
"""
result = u""
(commonshelperCats, usage, galleries) = imagerecat.getCommonshelperCats(imagepage)
newcats = imagerecat.applyAllFilters(commonshelperCats)
for newcat in newcats:
result += u"[[Category:" + newcat + u"]] "
return result
def getDescription(photoInfo=None,
panoramioreview=False,
reviewer=u'',
override=u'',
addCategory=u''):
'''
Build description for the image.
'''
desc = u''
desc = desc + u'{{Information\n'
desc = desc + u'|description=%(photo_title)s\n'
desc = desc + u'|date=%(upload_date)s (upload date)\n'
desc = desc + u'|source=[%(photo_url)s Panoramio]\n'
desc = desc + u'|author=[%(owner_url)s?with_photo_id=%(photo_id)s %(owner_name)s] \n'
desc = desc + u'|permission=\n'
desc = desc + u'|other_versions=\n'
desc = desc + u'|other_fields=\n'
desc = desc + u'}}\n'
if photoInfo.get(u'latitude') and photoInfo.get(u'longitude'):
desc = desc + u'{{Location dec|%(latitude)s|%(longitude)s|source:Panoramio}}\n'
desc = desc + u'\n'
desc = desc + u'=={{int:license-header}}==\n'
if override:
desc = desc + override
else:
if photoInfo.get(u'license') == u'by-sa':
desc = desc + u'{{Cc-by-sa-3.0}}\n'
if panoramioreview:
desc = desc + u'{{Panoramioreview|%s|{{subst:CURRENTYEAR}}-{{subst:CURRENTMONTH}}-{{subst:CURRENTDAY2}}}}\n' % (
reviewer, )
else:
desc = desc + u'{{Panoramioreview}}\n'
desc = desc + u'\n'
cats = u''
if addCategory:
desc = desc + u'\n[[Category:%s]]\n' % (addCategory, )
cats = True
# Get categories based on location
if photoInfo.get(u'latitude') and photoInfo.get(u'longitude'):
cats = imagerecat.getOpenStreetMapCats(photoInfo.get(u'latitude'),
photoInfo.get(u'longitude'))
cats = imagerecat.applyAllFilters(cats)
for cat in cats:
desc = desc + u'[[Category:%s]]\n' % (cat, )
if not cats:
desc = desc + u'{{subst:Unc}}\n'
return desc % photoInfo
def getDescription(photoInfo=None, panoramioreview=False, reviewer=u'',
override=u'', addCategory=u''):
'''
Build description for the image.
'''
desc = u''
desc = desc + u'{{Information\n'
desc = desc + u'|description=%(photo_title)s\n'
desc = desc + u'|date=%(upload_date)s (upload date)\n'
desc = desc + u'|source=[%(photo_url)s Panoramio]\n'
desc = desc + u'|author=[%(owner_url)s?with_photo_id=%(photo_id)s %(owner_name)s] \n'
desc = desc + u'|permission=\n'
desc = desc + u'|other_versions=\n'
desc = desc + u'|other_fields=\n'
desc = desc + u'}}\n'
if photoInfo.get(u'latitude') and photoInfo.get(u'longitude'):
desc = desc + u'{{Location dec|%(latitude)s|%(longitude)s|source:Panoramio}}\n'
desc = desc + u'\n'
desc = desc + u'=={{int:license-header}}==\n'
if override:
desc = desc + override
else:
if photoInfo.get(u'license')==u'by-sa':
desc = desc + u'{{Cc-by-sa-3.0}}\n'
if panoramioreview:
desc = desc + u'{{Panoramioreview|%s|{{subst:CURRENTYEAR}}-{{subst:CURRENTMONTH}}-{{subst:CURRENTDAY2}}}}\n' % (reviewer,)
else:
desc = desc + u'{{Panoramioreview}}\n'
desc = desc + u'\n'
cats = u''
if addCategory:
desc = desc + u'\n[[Category:%s]]\n' % (addCategory,)
cats = True
# Get categories based on location
if photoInfo.get(u'latitude') and photoInfo.get(u'longitude'):
cats=imagerecat.getOpenStreetMapCats(photoInfo.get(u'latitude'), photoInfo.get(u'longitude'))
cats=imagerecat.applyAllFilters(cats)
for cat in cats:
desc = desc + u'[[Category:%s]]\n' % (cat,)
if not cats:
desc = desc + u'{{subst:Unc}}\n'
return desc % photoInfo
def main():
'''
The main loop
'''
wikipedia.setSite(wikipedia.getSite(u'commons', u'commons'))
conn = None
cursor = None
(conn, cursor) = connectDatabase()
imagerecat.initLists()
generator = None
genFactory = pagegenerators.GeneratorFactory()
mark = True
for arg in wikipedia.handleArgs():
if arg.startswith('-dontmark'):
mark = False
elif arg.startswith('-page'):
if len(arg) == 5:
generator = [
wikipedia.Page(
wikipedia.getSite(),
wikipedia.input(u'What page do you want to use?'))
]
else:
generator = [wikipedia.Page(wikipedia.getSite(), arg[6:])]
elif arg.startswith('-yesterday'):
generator = [
wikipedia.Page(
wikipedia.getSite(),
u'Category:Media_needing_categories_as_of_' +
getYesterday())
]
else:
generator = genFactory.handleArg(arg)
if generator:
for page in generator:
if ((page.namespace() == 14) and (page.title().startswith(
u'Category:Media needing categories as of'))):
wikipedia.output(u'Working on ' + page.title())
for (image, gals, cats) in getImagesToCategorize(
cursor, page.titleWithoutNamespace()):
categorizeImage(image, gals,
imagerecat.applyAllFilters(cats))
if (mark):
categoriesChecked(page.title())