def test_NamespaceFilterPageGenerator(self):
self.assertFunction("NamespaceFilterPageGenerator")
site = self.site
gen = pagegenerators.PagesFromTitlesGenerator(self.titles, site)
gen = pagegenerators.NamespaceFilterPageGenerator(gen, 0, site)
self.assertEqual(len(tuple(gen)), 3)
gen = pagegenerators.PagesFromTitlesGenerator(self.titles, site)
gen = pagegenerators.NamespaceFilterPageGenerator(gen, 1, site)
self.assertEqual(len(tuple(gen)), 4)
gen = pagegenerators.PagesFromTitlesGenerator(self.titles, site)
gen = pagegenerators.NamespaceFilterPageGenerator(gen, 10, site)
self.assertEqual(len(tuple(gen)), 6)
gen = pagegenerators.PagesFromTitlesGenerator(self.titles, site)
gen = pagegenerators.NamespaceFilterPageGenerator(gen, (1, 10), site)
self.assertEqual(len(tuple(gen)), 10)
gen = pagegenerators.PagesFromTitlesGenerator(self.titles, site)
gen = pagegenerators.NamespaceFilterPageGenerator(
gen, ('Talk', 'Template'), site)
self.assertEqual(len(tuple(gen)), 10)
def user_talk_pages():
"A generator for valid user talk pages."
titles = ["User talk:" + name for name in people_to_notify.keys()]
for user_talk_page in [page for page in
pagegenerators.PagesFromTitlesGenerator(titles)
if page.exists() and not page.isRedirectPage()]:
# First, a sanity check
username = user_talk_page.title(withNamespace=False)
if username not in people_to_notify:
continue
# Then yield the page and username
yield (user_talk_page, username)
def test_RegexBodyFilterPageGenerator(self):
self.assertFunction("RegexBodyFilterPageGenerator")
gen = pagegenerators.PagesFromTitlesGenerator(self.titles,
site=self.site)
pages = []
for p in gen:
p.text = u"This is the content of %s as a sample" % p.title()
pages.append(p)
gen = pagegenerators.RegexBodyFilterPageGenerator(iter(pages), '/doc')
self.assertTrue(len(tuple(gen)) == 2)
gen = pagegenerators.RegexBodyFilterPageGenerator(iter(pages), 'This')
self.assertTrue(len(tuple(gen)) == 13)
gen = pagegenerators.RegexBodyFilterPageGenerator(iter(pages), 'talk',
quantifier='none')
self.assertTrue(len(tuple(gen)) == 9)
def main(argv):
parser = argparse.ArgumentParser()
parser.add_argument('--debug',
'-d',
help='enable debugging output',
action='store_true')
parser.add_argument('--category',
'--cat',
'-c',
help='specify starting category (default "{}")'.format(
defaultCategory),
default=defaultCategory)
parser.add_argument('--repeat',
'-r',
help='number of minutes in which to repeat',
type=int)
parser.add_argument('--always',
help='always save changes without prompting',
action='store_true')
parser.add_argument('pages',
help='List of page titles to process',
nargs=argparse.REMAINDER)
args = parser.parse_args(argv[1:])
site = pywikibot.Site()
while True:
# Select an appropriate page generator based on the --category
# argument and/or positional 'page' arguments
if args.pages:
pagegen = pagegenerators.PagesFromTitlesGenerator(args.pages)
else:
cat = pywikibot.Category(site, 'Category:' + args.category)
pagegen = pagegenerators.CategorizedPageGenerator(cat)
bot = PhotoCatBot(generator=pagegen,
debug=args.debug,
always=args.always)
bot.run()
if args.repeat:
nextrun = args.repeat * 60
print "{}: Next run in {} seconds...".format(
time.asctime(), nextrun)
time.sleep(nextrun)
else:
break
def test_RegexBodyFilterPageGenerator(self):
self.assertFunction("RegexBodyFilterPageGenerator")
gen = pagegenerators.PagesFromTitlesGenerator(self.titles,
site=self.site)
pages = []
for p in gen:
p.text = u"This is the content of %s as a sample" % p.title()
pages.append(p)
gen = pagegenerators.RegexBodyFilterPageGenerator(iter(pages), '/doc')
self.assertPagelistTitles(gen,
('Template:!/Doc', 'Template:Template/Doc'))
gen = pagegenerators.RegexBodyFilterPageGenerator(iter(pages), 'This')
self.assertPagelistTitles(gen, self.titles)
gen = pagegenerators.RegexBodyFilterPageGenerator(iter(pages),
'talk',
quantifier='none')
self.assertEqual(len(tuple(gen)), 9)
def test_PagesFromTitlesGenerator(self):
self.assertFunction("PagesFromTitlesGenerator")
gen = pagegenerators.PagesFromTitlesGenerator(self.titles)
self.assertTrue(len(self.titles) == len(tuple(gen)))
return year
property_map = {
'year': ('P571', lambda x: "+" + get_year(x) + "-01-01T00:00:00Z/9"),
'width_metric': ('P2049', lambda x: x.replace(",", ".") + "U174728"),
'height_metric': ('P2048', lambda x: x.replace(",", ".") + "U174728"),
'title': ('P1476', lambda x: 'en:"' + x.lstrip('«').rstrip('»') + '"'),
'artist': ('P170', find_by_label),
'image_file': ('P18', lambda x: '"' + x + '"'),
'image': ('P18', lambda x: '"' + x + '"'),
'museum': ('P195', find_by_label),
}
site = pywikibot.Site("en", "wikipedia")
for page in pagegenerators.PagesFromTitlesGenerator([find_by_sitelink(QID)],
site):
print(QID + "\tP31\tQ3305213")
# print(QID + "\tDen\t\"painting\"")
itemData = {}
for (template, args) in page.templatesWithParams():
# print(template.title())
if template.title() == 'Template:Infobox Artwork' \
or template.title() == 'Template:Infobox Painting' \
or template.title() == 'Template:Infobox artwork' \
or template.title() == 'Template:Infobox painting':
# print(args)
argmap = dict(
arg.split('=', maxsplit=1) for arg in args if '=' in arg)
for name in property_map:
if name in argmap:
value = argmap[name]
def test_PagesFromTitlesGenerator(self):
self.assertFunction("PagesFromTitlesGenerator")
gen = pagegenerators.PagesFromTitlesGenerator(self.titles, self.site)
self.assertPagelistTitles(gen, self.titles)
def test_CategoryFilterPageGenerator(self):
"""Test CategoryFilterPageGenerator."""
site = self.site
gen = pagegenerators.PagesFromTitlesGenerator(self.titles, site)
gen = pagegenerators.CategoryFilterPageGenerator(gen, self.catfilter_list, site)
self.assertEqual(len(tuple(gen)), 7)
def prune_list_of_people(people_to_notify):
"Removes people who shouldn't be notified from the list."
# Define a couple of helper functions...
# ... one purely for logging purposes,
def print_people_left(what_was_removed):
"Print the number of people left after removing something."
# This has been made a no-op for performance.
pass
#print("%d people for %d noms left after removing %s." %
# (len(people_to_notify),
# len(functools.reduce(operator.add,
# people_to_notify.values(),
# [])),
# what_was_removed))
# ... and another simply to save keystrokes.
def user_talk_pages():
"A generator for valid user talk pages."
titles = ["User talk:" + name for name in people_to_notify.keys()]
for user_talk_page in [
page
for page in pagegenerators.PagesFromTitlesGenerator(titles)
if page.exists() and not page.isRedirectPage()
]:
# First, a sanity check
username = user_talk_page.title(withNamespace=False)
if username not in people_to_notify:
continue
# Then yield the page and username
yield (user_talk_page, username)
# Prune empty entries
people_to_notify = {k: v for k, v in people_to_notify.items() if k}
print_people_left("empty entries")
# Prune talk pages that don't exist
user_talk_titles = [
"User talk:" + name for name in people_to_notify.keys()
]
titles_gen = pagegenerators.PagesFromTitlesGenerator(user_talk_titles)
usernames_without_talk_pages = [
page.title(withNamespace=False) for page in titles_gen
]
for each_username in usernames_without_talk_pages:
del people_to_notify[each_username]
# Prune people I've already notified
with open(CONFIG.get("dyknotifier",
"ALREADY_NOTIFIED_FILE")) as already_notified_file:
try:
already_notified_data = json.load(already_notified_file)
except ValueError as error:
if error.message != "No JSON object could be decoded":
raise
else:
already_notified_data = {}
# Since the outer dict in the file is keyed on month string,
# smush all the values together to get a dict keyed on username
already_notified = {}
for month_dict in already_notified_data.values():
for month_username, month_items in month_dict.items():
already_notified[month_username] =\
already_notified.get(month_username, []) + month_items
# Now that we've built a dict, filter the list for each username
for username, prior_nominations in already_notified.items():
if username not in people_to_notify:
continue
prior_nominations = [
CONFIG.get("dyknotifier", "NOMINATION_TEMPLATE") + x
for x in prior_nominations
]
proposed = set(people_to_notify[username])
people_to_notify[username] = list(proposed -
set(prior_nominations))
people_to_notify = {k: v for k, v in people_to_notify.items() if v}
print_people_left("already-notified people")
# Prune user talk pages that link to this nom.
for user_talk_page, username in user_talk_pages():
people_to_notify[username] = [
nom for nom in people_to_notify[username]
if nom not in user_talk_page.get()
]
people_to_notify = {k: v for k, v in people_to_notify.items() if v}
print_people_left("linked people")
return people_to_notify
