def load_pages(book_name, opt, cache):
# It's more efficient to do two pass, in the first we don't preload
# contents but only check if the cache is ok.
remaining_pages = []
pages = []
page_ns_name = page_prefixes['wikisource'][opt.lang]
page_name = page_ns_name + u':' + book_name + u'/'
gen = pagegen.PrefixingPageGenerator(page_name, site=opt.site)
for p in gen:
page_nr = int(re.match(u'.*/(\d+)$', p.title()).group(1))
if not cache.has_key(
page_nr) or cache[page_nr][0] != p.latestRevision():
remaining_pages.append(p)
else:
pages.append((None, page_nr, p.latestRevision()))
# and in the second pass we preload contents for cache miss,
# imported pages are never cached, but that's not a no big deal
for p in pagegen.PreloadingGenerator(remaining_pages):
text = p.get()
if not is_imported_page(text):
page_nr = int(re.match(u'.*/(\d+)$', p.title()).group(1))
pages.append((text, page_nr, p.latestRevision()))
return pages
def handlePotd(self, potd):
"""
Handle one picture of the day
:param potd: The POTD template of that day
"""
regex = u'\{\{Potd filename\|([^\|]+)\|(\d\d\d\d)\|(\d{1,2})|(\d{1,2})\}\}'
match = re.search(regex, potd.text)
captions = {}
filename = None
if match:
filename = match.group(1)
for potdlang in pagegenerators.PrefixingPageGenerator(
potd.title() + u'_(', site=self.site,
includeredirects=False):
potdinfo = self.handlePotdLang(potdlang)
if potdinfo:
(lang, caption) = potdinfo
captions[lang] = caption
# Reshufle so I don't end up getting the captions all the time
if captions and filename:
filepage = pywikibot.FilePage(self.site, title=filename)
if filepage.exists():
# Might run into redirects
mediaid = u'M%s' % (filepage.pageid, )
if not self.mediaInfoExists(mediaid):
self.addCaptions(mediaid, captions)
currentDateTime = datetime.datetime.utcnow()
mailFrom = 'WikiBG Admin Notifier <*****@*****.**>'
mailRcpt = '*****@*****.**'
mailSubj = 'Промени в "Заявки към администраторите"'
mailBody = ''
mail = MIMEMultipart('alternative')
mail.set_charset('utf-8')
mail['From'] = mailFrom
mail['To'] = mailRcpt
mail['Subject'] = Header(mailSubj.encode('utf-8'), 'utf-8')
adminReqPagesPrevYear = pagegenerators.PrefixingPageGenerator(
'Заявки към администраторите/' + str(currentDateTime.year - 1),
namespace='Уикипедия',
includeredirects=False)
adminReqPagesCurrYear = pagegenerators.PrefixingPageGenerator(
'Заявки към администраторите/' + str(currentDateTime.year),
namespace='Уикипедия',
includeredirects=False)
adminReqPages = pagegenerators.CombinedPageGenerator(
[adminReqPagesPrevYear, adminReqPagesCurrYear])
adminReqPagesRecent = pagegenerators.EdittimeFilterPageGenerator(
adminReqPages, last_edit_start=lastDateTime)
revisionCount = 0
for reqPage in adminReqPagesRecent:
def main():
lang = 'en'
wikisite = pywikibot.Site(lang, 'wikipedia')
site = pywikibot.Site('wikidata', 'wikidata')
repo = site.data_repository()
#https://en.wikipedia.org/wiki/Category:YearParamUsageCheck_tracking_categories
#https://en.wikipedia.org/wiki/Category:Year_by_category_%E2%80%94_used_with_year_parameter(s)_equals_year_in_page_title
method = 'all'
if len(sys.argv) > 1:
method = sys.argv[1]
if method == 'all' or method == 'method1':
groups = [
#['Category:%s births' % (i) for i in range(100, 2050)],
#['Category:%s deaths' % (i) for i in range(100, 2050)],
#['Category:%s establishments' % (i) for i in range(100, 2050)],
#['Category:%s disestablishments' % (i) for i in range(100, 2050)],
#['Category:%s books' % (i) for i in range(100, 2050)],
#['Category:%s comic debuts' % (i) for i in range(100, 2050)],
#['Category:%s compositions' % (i) for i in range(100, 2050)],
#['Category:%s documents' % (i) for i in range(100, 2050)],
#['Category:%s films' % (i) for i in range(1850, 2050)],
#['Category:%s musicals' % (i) for i in range(100, 2050)],
#['Category:%s operas' % (i) for i in range(100, 2050)],
#['Category:%s paintings' % (i) for i in range(100, 2050)],
#['Category:%s plays' % (i) for i in range(100, 2050)],
#['Category:%s poems' % (i) for i in range(100, 2050)],
#['Category:%s sculptures' % (i) for i in range(100, 2050)],
#['Category:%s short stories' % (i) for i in range(100, 2050)],
#['Category:%s songs' % (i) for i in range(100, 2050)],
#['Category:%s treaties' % (i) for i in range(100, 2050)],
#['Category:%s works' % (i) for i in range(100, 2050)],
#['%s in film' % (i) for i in range(1850, 2050)],
]
for titles in groups:
for c in range(0, len(titles)):
title = titles[c]
titleprev = c > 0 and titles[c - 1] or ''
titlenext = c < len(titles) - 1 and titles[c + 1] or ''
print('\n==', title.encode('utf-8'), '==')
page = pywikibot.Page(wikisite, title)
if not page.exists() or page.isRedirectPage():
print("Page doesnt exist or is redirect: %s" %
(page.title().encode('utf-8')))
continue
item = pywikibot.ItemPage.fromPage(page)
if item:
core(repo=repo,
item=item,
page=page,
lang=lang,
wikisite=wikisite,
titleprev=titleprev,
titlenext=titlenext)
else:
print("Page doest have item")
if method == 'all' or method == 'method2':
#cat = pywikibot.Category(wikisite, 'Category:Year by category — used with year parameter(s) equals year in page title')
#cat = pywikibot.Category(wikisite, 'Category:YearParamUsageCheck tracking categories')
cat = pywikibot.Category(wikisite, 'Category:Categories by year')
#gen = pagegenerators.SubCategoriesPageGenerator(cat)
gen = pagegenerators.SubCategoriesPageGenerator(cat, recurse=5)
for page in gen:
print('\n==', page.title().encode('utf-8'), '==')
year = ''
titleprev = ''
titlenext = ''
if re.findall(r'(?m)^Category:(\d{4}) [^\d]+$', page.title()):
year = int(
re.findall(r'(?m)^Category:(\d{4}) [^\d]+$',
page.title())[0])
titleprev = re.sub(r'(?m)^(Category):%s ([^\d]+)$' % (year),
r'\1:%s \2' % (year - 1), page.title())
titlenext = re.sub(r'(?m)^(Category):%s ([^\d]+)$' % (year),
r'\1:%s \2' % (year + 1), page.title())
elif re.findall(r'(?m)^Category:[^\d]+ in (\d{4})$', page.title()):
year = int(
re.findall(r'(?m)^Category:[^\d]+ in (\d{4})$',
page.title())[0])
titleprev = re.sub(r'(?m)^(Category):([^\d]+ in) %s$' % (year),
r'\1:\2 %s' % (year - 1), page.title())
titlenext = re.sub(r'(?m)^(Category):([^\d]+ in) %s$' % (year),
r'\1:\2 %s' % (year + 1), page.title())
else:
print("Not a yearly category")
continue
if not year or len(str(year)) != 4:
print("Couldnt parse correct year from page name")
continue
print(year)
item = ''
try:
item = pywikibot.ItemPage.fromPage(page)
except:
print("No wikidata item for this page")
continue
if item:
if titleprev and titlenext:
core(repo=repo,
item=item,
page=page,
lang=lang,
wikisite=wikisite,
titleprev=titleprev,
titlenext=titlenext)
else:
print("Not titleprev or titlenext")
else:
print("Page doest have item")
if method == 'all' or method == 'method3':
for year in range(1000, 2050):
prefix = '%s in ' % (year)
prefixprev = '%s in ' % (year - 1)
prefixnext = '%s in ' % (year + 1)
gen = pagegenerators.PrefixingPageGenerator(prefix,
namespace=0,
includeredirects=False,
site=wikisite,
total=None,
content=False)
for page in gen:
if not page.title().startswith(prefix):
break
if ' in science' in page.title():
continue
print('\n==', page.title().encode('utf-8'), '==')
titleprev = ''
titlenext = ''
if re.findall(r'(?m)^%s([^\d]+)$' % (prefix), page.title()):
titleprev = re.sub(r'(?m)^%s([^\d]+)$' % (prefix),
r'%s\1' % (prefixprev), page.title())
titlenext = re.sub(r'(?m)^%s([^\d]+)$' % (prefix),
r'%s\1' % (prefixnext), page.title())
else:
print("Not a yearly page")
continue
item = ''
try:
item = pywikibot.ItemPage.fromPage(page)
except:
print("No wikidata item for this page")
continue
if item:
if titleprev and titlenext:
core(repo=repo,
item=item,
page=page,
lang=lang,
wikisite=wikisite,
titleprev=titleprev,
titlenext=titlenext)
else:
print("Not titleprev or titlenext")
else:
print("Page doest have item")
'1.21.0': 'Q21683643',
'1.22.0': 'Q21683645',
'1.23.0': 'Q21683646',
'1.24.0': 'Q21683648',
'1.25.0': 'Q21683649',
'1.26.0': 'Q21683659',
'1.27.0': 'Q21683650',
}
def normalize_version(ver):
ver = ver.split(' ')[0]
if len(ver.split('.')) == 2:
ver += '.0'
return ver
gen = pagegenerators.PrefixingPageGenerator('Manual:Hooks/', site=site, content=True, includeredirects=False)
for page in gen:
if len(page.title().split('/')) > 2:
#print('Skipping %s because it has 2+ subpage parts' % page.title())
continue
code = mwparserfromhell.parse(page.text)
dep = None
for temp in code.filter_templates():
if temp.name == 'TNT' and temp.get(1).value.strip() == 'MediaWikiHook':
if temp.has('deprecated'):
dep = str(temp.get('deprecated').value).strip()
break
elif temp.name == 'TNT' and temp.get(1).value.strip() == 'Deprecated':
dep = str(temp.get('2').value).strip()