def add_text(generator):
fa_page_title_list = get_query()
for page in generator:
if _cache.get(tuple([page.title(), 'add_text'])):
wikipedia.output(
u'\03{lightred}>>> Page ' + page.title() +
u' was checked before so it will pass\03{default}')
continue
original_text = u''
if page.namespace() != 0:
continue
try:
pagetitle_source = page.title()
original_text = page.get()
pagetitle = pagetitle_source
redirection = 0
except wikipedia.NoPage:
wikipedia.output(u"%s doesn't exist, skip!" % page.title())
continue
except wikipedia.IsRedirectPage:
wikipedia.output(u"%s is a redirect, skip!" % page.title())
pagemain = page.getRedirectTarget()
try:
original_text = pagemain.get()
except:
wikipedia.output(u"%s doesn't exist, skip!" % pagemain.title())
continue
pagetitle_source = pagemain.title()
pagetitle = page.title()
redirection = 1
except:
continue
pagetitle3 = re.sub(
ur'[qwertyuiopasdfghjklzxcvbnmQWERTYUIOPASDFGHJKLZXCVBNM]', ur"",
pagetitle)
if pagetitle3 != pagetitle:
continue
if pagetitle.find(u'در حال ویرایش') != -1:
continue
_cache[tuple([page.title(), 'add_text'])] = 1
if original_text:
if redirection == 0:
wrong_words = ur'ًٌٍَُِّْٔ' + u'يٰك' + u"@#$%^&*'~`"
pagetitle2 = re.sub(ur'[' + wrong_words + ur']', ur"",
pagetitle)
passp = redirect_find(pagetitle)
if not passp:
if pagetitle != pagetitle2:
for vowel in wrong_words:
if vowel in pagetitle:
break
passport = False
text = u'{| class="wikitable plainlinks"\n|-\n'
page = wikipedia.Page(fasite,
u"user:fawikibot/movearticles2")
text_fa = page.get()
if not pagetitle in text_fa:
text += u"|[[" + pagetitle + u"]] ||«" + vowel + u"»\n|-\n"
passport = True
text += u'\n|}\n'
if passport:
page.put(text_fa + u'\n' + text,
u"ربات:مقالهها برای انتقال")
try:
#-------------------------1----------------------------------
if u"ی" in pagetitle or u"ک" in pagetitle:
if not u"" in pagetitle:
New_redirect_name = pagetitle.replace(u"ی",
u"ي").replace(
u"ک", u"ك")
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر از ی و ک عربی به ی و ک فارسی (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
else:
New_redirect_name = pagetitle.replace(
u"ی", u"ي").replace(u"ک",
u"ك").replace(u"", u" ")
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر از ی و ک عربی به ی و ک فارسی و فاصله به فاصلهٔ مجازی (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
#-------------------------2----------------------------------
if u"" in pagetitle:
New_redirect_name = pagetitle.replace(u"", u" ")
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر از فاصله به فاصلهٔ مجازی (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
#-------------------------3----------------------------------
if u"آ" in pagetitle:
New_redirect_name = pagetitle.replace(u"آ", u"ا")
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر از ا به آ (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
#-------------------------3----------------------------------
if u"أ" in pagetitle:
New_redirect_name = pagetitle.replace(u"أ", u"ا")
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر از ا به أ (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
#-------------------------3.5----------------------------------
if u"ء" in pagetitle:
New_redirect_name = pagetitle.replace(u"ء", u"")
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر از ء به (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
#-------------------------3.5----------------------------------
if (u"," or u"،" or u"(") in pagetitle:
New_redirect_name = pagetitle.replace(u",", u" ").replace(
u"،", u" ").replace(u")",
u" ").replace(u"(", u" ").replace(
u" ", u" ").strip()
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر از ,()، به (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
#-------------------------3.5----------------------------------
if (u"(" or u"،" or u",") in pagetitle:
New_redirect_name = pagetitle.replace(u" ،", u"،").replace(
u" ,", u",").replace(u"،", u"، ").replace(
u",", u", ").replace(u"(", u" (").replace(
u")", u") ").replace(u" ", u" ").strip()
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر فاصله برای سجاوندی (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
#-------------------------3.5----------------------------------
if u"ة" in pagetitle:
New_redirect_name = pagetitle.replace(u"ة", u"ه")
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر از ه به ة (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
#-------------------------4----------------------------------
if u"،" in pagetitle:
New_redirect_name = pagetitle.replace(u" ،", u"،")
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر سجاوندی درست برای ویرگول(" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
#-------------------------5----------------------------------
if u"," in pagetitle:
New_redirect_name = pagetitle.replace(u",", u"،")
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر سجاوندی درست برای ویرگول غیرفارسی (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
#-------------------------5.5----------------------------------
b = -1
sources = [
u'اول', u'یکم', u'ثانی', u'ثالث', u'نخستین', u'اولین'
]
targets = [u'یکم', u'اول', u'دوم', u'سوم', u'اولین', u'نخستین']
for i in sources:
b += 1
j = targets[b]
if i in pagetitle:
New_redirect_name = (u' ' + pagetitle + u' ').replace(
u' ' + i + u' ', u' ' + j + u' ').strip()
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر از " + j + u" به " + i + u" (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
#-------------------------6----------------------------------
if u"ؤ" in pagetitle:
New_redirect_name = pagetitle.replace(u"ؤ", u"و")
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر و به ؤ (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
#-------------------------6----------------------------------
if u"کامپیوتر" in pagetitle:
New_redirect_name = pagetitle.replace(
u"کامپیوترها", u"رایانهها").replace(
u"کامپیوتری",
u"رایانهای").replace(u"کامپیوتر", u"رایانه")
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر رایانه به کامپیوتر (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
#-------------------------7----------------------------------
if u"هی" in pagetitle:
New_redirect_name = pagetitle.replace(u"هی", u"ه")
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر ه به هی (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
#-------------------------8----------------------------------
if u"ه " in pagetitle and redirection == 0 and pagetitle.find(
u'كه '
) == -1 and pagetitle.find(u'اه ') == -1 and pagetitle.find(
u'ه اي '
) == -1 and pagetitle.find(u'ه ای ') == -1 and pagetitle.find(
u'که '
) == -1 and pagetitle.find(u'راه ') == -1 and pagetitle.find(
u'ه با '
) == -1 and pagetitle.find(u'گروه ') == -1 and pagetitle.find(
u'ه که '
) == -1 and pagetitle.find(u'ه كه ') == -1 and pagetitle.find(
u'ه در '
) == -1 and pagetitle.find(u'ه براي ') == -1 and pagetitle.find(
u'ه برای '
) == -1 and pagetitle.find(u'ه از ') == -1 and pagetitle.find(
u'ه ;'
) == -1 and pagetitle.find(u'علیه ') == -1 and pagetitle.find(
u'عليه '
) == -1 and pagetitle.find(u'ه و ') == -1 and pagetitle.find(
u'ه :'
) == -1 and pagetitle.find(u'شاه ') == -1 and pagetitle.find(
u'به '
) == -1 and pagetitle.find(u'الله ') == -1 and pagetitle.find(
u'ه (') == -1 and pagetitle.find(
u'گه ') == -1 and pagetitle.find(
u'ه -') == -1 and pagetitle.find(u'ه-') == -1:
New_redirect_name = pagetitle.replace(u"ه ", u"هٔ ")
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر هٔ به ه (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
#-------------------------9----------------------------------
if u"ها " in pagetitle and redirection == 0 and pagetitle.find(
u'ها ('
) == -1 and pagetitle.find(
u'ها براي '
) == -1 and pagetitle.find(
u'ها برای '
) == -1 and pagetitle.find(u'ها با ') == -1 and pagetitle.find(
u'ها در '
) == -1 and pagetitle.find(u'ها از ') == -1 and pagetitle.find(
u'ها كه '
) == -1 and pagetitle.find(u'ها که ') == -1 and pagetitle.find(
u'ها و ') == -1 and pagetitle.find(
u'ها :') == -1 and pagetitle.find(u'ها ;') == -1:
New_redirect_name = pagetitle.replace(u"ها ", u"های ")
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر های به ها (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
#-------------------------10----------------------------------
if u"ها" in pagetitle:
New_redirect_name = pagetitle.replace(u"ها", u"ها")
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر فاصلهٔ مجازی+ها به ها (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
#-------------------------10.5----------------------------------
if u"ها" in pagetitle:
New_redirect_name = pagetitle.replace(u"ها", u" ها")
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر فاصلهٔ مجازی+ها به فاصله+ها (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
#-------------------------11----------------------------------
if u"می" in pagetitle or u"مي" in pagetitle:
New_redirect_name = pagetitle.replace(u"می",
u"می").replace(
u"مي", u"مي")
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر می+فاصلهٔ مجازی به می (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
#-------------------------12----------------------------------
farsinum = [
u'۰', u'۱', u'۲', u'۳', u'۴', u'۵', u'۶', u'۷', u'۸', u'۹'
]
counters = -1
pagetitle2 = pagetitle
for num in farsinum:
counters += 1
pagetitle2 = pagetitle2.replace(num, str(counters))
if pagetitle2 != pagetitle:
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر عدد لاتین به عدد فارسی (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
#-------------------------13----------------------------------
if u"ایالات متحده آمریکا" in pagetitle:
New_redirect_name = pagetitle.replace(
u"ایالات متحده آمریکا", u"ایالات متحده")
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
elif u"آمریکا" in pagetitle:
if not u"آمریکایی" in pagetitle:
New_redirect_name = pagetitle.replace(
u"آمریکا", u"ایالات متحده")
if fa_page_title_list.find(u'\n' +
New_redirect_name.strip() +
u'\n') == -1:
msg = u"ربات:تغییرمسیر (" + botVersion + u")"
fa_page_title_list = creat_redirect(
fa_page_title_list, New_redirect_name,
pagetitle_source, msg)
pagetitle_source, New_redirect_name, msg = u'', u'', u''
except:
continue
# it under the terms of the GNU General Public License as published by
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
import wikipedia, re, catlib
essite = wikipedia.Site('es', 'wikipedia')
selfcat = wikipedia.Page(
essite, u'Wikipedia:Informes automáticos/Categorías autocontenidas')
spam = u"Usando: [[Wikipedia:Informes automáticos/Categorías autocontenidas]]"
m = re.compile(ur"(?i)\[\[:(C[^\]].*?)\]\]").finditer(selfcat.get())
for i in m:
cattitle = i.group(1)
catpage = catlib.Category(essite, cattitle)
if catpage.exists(
) and not catpage.isRedirectPage() and not catpage.isDisambig():
cattitleWithout = catpage.titleWithoutNamespace()
cattext = catpage.get()
wikipedia.output(catpage.title())
#marcamos para destruir las que no tienen artículos ni subcategorías
if len(cattext) >= len(cattitle) + 4 and len(
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
import datetime
import os, re, wikipedia
site=wikipedia.Site("es", "wikipedia")
#discusiones mas activas
os.system('mysql -h sql-s3 -e "use eswiki_p;select count(*) as count, rc_title from recentchanges where rc_timestamp>=date_add(now(), interval -3 day) and rc_namespace=1 group by rc_title order by count desc limit 25;" > /home/emijrp/temporal/tarea006data')
f=open('/home/emijrp/temporal/tarea006data', 'r')
sql=unicode(f.read(), 'utf-8')
m=re.compile(ur"(\d+)\s+(.*)").finditer(sql)
page=wikipedia.Page(site, "Template:DiscusionesActivas")
s=u"<div class='plainlinks'>\n{| class='wikitable' style='width: {{{ancho|275px}}};clear: right;float: right;margin: 0 0 1em 1em;text-align: center;'\n! Discusiones más activas [[Image:FireIcon.svg|18px]]\n! Ediciones\n"
c=1
ss=""
for i in m:
ed=str(i.group(1))
art_=i.group(2)
art=re.sub("_", " ", art_)
if not re.search(u"Candidatura a destacado", art):
if c<=5:
ss+=u"|-\n| [[Discusión:%s|%s]] || [http://es.wikipedia.org/w/index.php?title=Discusión:%s&action=history %s] \n" % (art,art,art_,ed)
c+=1
s+=ss
s+=u"|-\n| colspan='2' | <small>Actualizado: {{subst:CURRENTTIME}} (UTC) del {{subst:CURRENTDAY}} de {{subst:CURRENTMONTHNAME}} de {{subst:CURRENTYEAR}}</small>\n"
s+=u"|}\n</div>"
wikipedia.output(s)
def main():
limit = 14
conn = MySQLdb.connect(host='sql-s3',
db='eswiki_p',
read_default_file='~/.my.cnf',
use_unicode=True)
cursor = conn.cursor()
cursor.execute(
"SELECT rc_timestamp from recentchanges where rc_user_text='AVBOT' and rc_namespace=0 and rc_deleted=0 and rc_timestamp>=date_add(now(), interval -%d day);"
% limit)
result = cursor.fetchall()
days = {}
c = 0
for row in result:
if len(row) == 1:
rc_timestamp = row[0][:8]
if days.has_key(rc_timestamp):
days[rc_timestamp] += 1
else:
days[rc_timestamp] = 1
c += 1
percent(c)
l = []
for day, edits in days.items():
l.append([day, edits])
l.sort()
l.reverse()
site = wikipedia.Site('es', 'wikipedia')
weekday = {
0: u'lunes',
1: u'martes',
2: u'miércoles',
3: u'jueves',
4: u'viernes',
5: u'sábado',
6: u'domingo'
}
monthname = {
1: u'enero',
2: u'febrero',
3: u'marzo',
4: u'abril',
5: u'mayo',
6: u'junio',
7: u'julio',
8: u'agosto',
9: u'septiembre',
10: u'octubre',
11: u'noviembre',
12: u'diciembre'
}
output = u"{| class='wikitable sortable' align='right' style='text-align: center' \n! Día !! Ediciones "
for day, edits in l:
date = datetime.datetime(year=int(day[0:4]),
month=int(day[4:6]),
day=int(day[6:8]))
output += u"\n|-\n| %s, [[%d de %s]] || %d " % (
weekday[date.weekday()], date.day, monthname[date.month], edits)
output += u"\n|-\n| colspan=2 | <small>''Esta tabla recoge la actividad de AVBOT<br/>en los últimos días<br/>* La tasa ha disminuido gracias a<br/>la nueva herramienta [[Special:AbuseFilter|AbuseFilter]]''</small>\n|}"
wii = wikipedia.Page(site, u"User:AVBOT/Últimos días")
wii.put(output, u"BOT - Actualizando plantilla")
def doImage(self, image):
r = re.compile(u'\|', re.UNICODE | re.DOTALL)
data = re.split(r, image)
imageName = data[0]
newImageName = data[0]
r = re.compile(u'^\s*$', re.UNICODE | re.DOTALL)
if len(data) >= 2 and not re.match(r, data[1]):
newImageName = data[1]
sourceWiki = u'anime'
if len(data) >= 3:
sourceWiki = data[2]
exclusionMode = u'normal'
if len(data) >= 4:
exclusionMode = data[3]
exclusionInfo = u''
if len(data) >= 5:
exclusionInfo = data[4]
sourceSite = None
outputSites = []
sourceImage = None
sourcePage = None
wikipedia.output(u'Doing Image %s' % imageName)
for site in self.siteList:
if site.family.name == sourceWiki:
sourceSite = site
if exclusionMode == u'normal':
outputSites.append(site)
elif exclusionMode == u'include':
r = re.compile(u',', re.UNICODE | re.DOTALL)
includes = re.split(r, exclusionInfo)
if site.family.name in includes:
outputSites.append(site)
elif exclusionMode == u'exclude':
r = re.compile(u',', re.UNICODE | re.DOTALL)
excludes = re.split(r, exclusionInfo)
if site.family.name not in includes:
outputSites.append(site)
else:
wikipedia.output(u'Unknown exclusion mode. Skiping %s.' %
imageName)
return False
if sourceSite == None:
wikipedia.output(u'No source site found. Skiping %s.' % imageName)
return False
try:
sourceDescriptionPage = wikipedia.Page(sourceSite, imageName, None,
6) #6=Image Namespace
sourceImagePage = wikipedia.ImagePage(
sourceSite, sourceDescriptionPage.title())
except wikipedia.NoPage:
wikipedia.output(u'No source page found. Skiping %s.' % imageName)
return False
sourceURL = sourceImagePage.fileUrl()
if '://' not in sourceURL:
sourceURL = u'http://%s%s' % (sourceSite.hostname(), sourceURL)
# Get file contents
uo = wikipedia.MyURLopener()
sourceFile = uo.open(sourceURL, "rb")
wikipedia.output(u'Reading file %s' % sourceURL)
sourceContents = sourceFile.read()
if sourceContents.find(
"The requested URL was not found on this server.") != -1:
wikipedia.output("Couldn't download the image. Skiping.")
return False
sourceFile.close()
#Setup Description Page
pageDescription = sourceDescriptionPage.get()
r = re.compile(u'== Summary ==\n?')
if re.search(r, pageDescription):
pageDescription = re.sub(r, u'', pageDescription)
mirrorText = u'{{networkMirror|%s|%s}}' % (imageName,
sourceSite.family.name)
comm = re.compile(u'({{commons(\|[^{}]*)?}})', re.IGNORECASE)
if re.search(comm, pageDescription):
pageDescription = re.sub(comm, u'\\1\n%s' % mirrorText,
pageDescription)
else:
pageDescription = u'%s%s' % (mirrorText, pageDescription)
pageDescription = u'== Summary ==\n%s' % pageDescription
for site in outputSites:
if sourceSite.family.name != site.family.name or imageName != newImageName:
doUpload = False
doDescription = False
try:
siteDescriptionPage = wikipedia.Page(
site, newImageName, None, 6) #6=Image Namespace
siteImagePage = wikipedia.ImagePage(
site, siteDescriptionPage.title())
siteURL = siteImagePage.fileUrl()
if '://' not in siteURL:
siteURL = u'http://%s%s' % (site.hostname(), siteURL)
uo2 = wikipedia.MyURLopener()
siteFile = uo2.open(siteURL, "rb")
wikipedia.output(u'Reading file %s' % siteURL)
siteContents = siteFile.read()
if sourceContents.find(
"The requested URL was not found on this server."
) != -1:
wikipedia.output(
"Couldn't download the image at new location.")
doUpload = True
break
siteFile.close()
if siteContents != sourceContents:
doUpload = True
if siteDescriptionPage.get() != pageDescription:
doDescription = True
except wikipedia.NoPage:
doUpload = True
doDescription = True
if doUpload:
bot = upload.UploadRobot(url=sourceURL,
useFilename=newImageName,
keepFilename=True,
verifyDescription=False,
description=msg['en'],
targetSite=site,
urlEncoding=sourceSite.encoding())
bot.run()
if doDescription:
siteDescriptionPage.put(pageDescription)
# the Free Software Foundation, either version 3 of the License, or
# (at your option) any later version.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
# GNU General Public License for more details.
#
# You should have received a copy of the GNU General Public License
# along with this program. If not, see <http://www.gnu.org/licenses/>.
import wikipedia,re
site=wikipedia.Site("es", "wikipedia")
page=wikipedia.Page(site, u"Wikipedia:Candidaturas a bibliotecario/Tabla")
#{{CandidaturaBibliotecario|Racso|Tomatejc|18/01/2008|03/04/2007|4402|color=#FFFFCC}}
m=re.compile(ur"\{\{CandidaturaBibliotecario\|(?P<candidato>[^\|]+)\|(?P<propuesto>[^\|]+)\|").finditer(page.get())
s=u"{| class='wikitable' width='500px' style='font-size: 90%s;text-align: center;'\n! colspan=7 | Candidaturas a bibliotecario \n|-\n! # !! Usuario !! Propuesto por !! A favor !! En contra !! %s !! Estado" % ("%", "%")
raw=u""
c=0
send=False
limite=0
for i in m:
limite+=1
if limite>3:
break
cafavor=0
cencontra=0
estado=u"Abierta"
def main():
quietMode = False # use -quiet to get less output
# if the -file argument is used, page titles are stored in this array.
# otherwise it will only contain one page.
articles = []
# if -file is not used, this temporary array is used to read the page title.
page_title = []
# Which namespaces should be processed?
# default to [] which means all namespaces will be processed
namespaces = []
xmlfilename = None
gen = None
# This factory is responsible for processing command line arguments
# that are also used by other scripts and that determine on which pages
# to work on.
genFactory = pagegenerators.GeneratorFactory()
for arg in pywikibot.handleArgs():
if arg.startswith('-xml'):
if len(arg) == 4:
xmlfilename = pywikibot.input(
u'Please enter the XML dump\'s filename:')
else:
xmlfilename = arg[5:]
gen = TableXmlDumpPageGenerator(xmlfilename)
elif arg == '-sql':
query = u"""
SELECT page_namespace, page_title
FROM page JOIN text ON (page_id = old_id)
WHERE old_text LIKE '%<table%'
LIMIT 200"""
gen = pagegenerators.MySQLPageGenerator(query)
elif arg.startswith('-namespace:'):
try:
namespaces.append(int(arg[11:]))
except ValueError:
namespaces.append(arg[11:])
elif arg.startswith('-skip:'):
articles = articles[articles.index(arg[6:]):]
elif arg.startswith('-auto'):
config.table2wikiAskOnlyWarnings = True
config.table2wikiSkipWarnings = True
print "Automatic mode!\n"
elif arg.startswith('-quiet'):
quietMode = True
else:
if not genFactory.handleArg(arg):
page_title.append(arg)
# if the page is given as a command line argument,
# connect the title's parts with spaces
if page_title != []:
page_title = ' '.join(page_title)
page = pywikibot.Page(pywikibot.getSite(), page_title)
gen = iter([page])
if not gen:
gen = genFactory.getCombinedGenerator()
if gen:
if namespaces != []:
gen = pagegenerators.NamespaceFilterPageGenerator(gen, namespaces)
preloadingGen = pagegenerators.PreloadingGenerator(gen)
bot = Table2WikiRobot(preloadingGen, quietMode)
bot.run()
else:
pywikibot.showHelp('table2wiki')
def _parseCategory(self, purge=False, startFrom=None):
"""
Yields all articles and subcategories that are in this category.
Set purge to True to instruct MediaWiki not to serve a cached version.
Set startFrom to a string which is the title of the page to start from.
Yielded results are tuples in the form (tag, page) where tag is one
of the constants ARTICLE and SUBCATEGORY, and title is the Page or Category
object.
Note that results of this method need not be unique.
This should not be used outside of this module.
"""
if self.site().versionnumber() < 4:
Rtitle = re.compile('title\s?=\s?\"([^\"]*)\"')
elif self.site().versionnumber() < 8:
# FIXME seems to parse all links
Rtitle = re.compile('/\S*(?: title\s?=\s?)?\"([^\"]*)\"')
else:
Rtitle = re.compile(
'<li>(?:<span.*?>)?<a href=\".*?\"\s?title\s?=\s?\"([^\"]*)\"\>\+?[^\<\+]'
)
if self.site().versionnumber() < 8:
Rsubcat = None
Rimage = None
else:
Rsubcat = re.compile(
'CategoryTreeLabelCategory\"\s?href=\".+?\">(.+?)</a>')
Rimage = re.compile(
'<div class\s?=\s?\"thumb\"\sstyle=\"[^\"]*\">(?:<div style=\"[^\"]*\">)?<a href=\".*?\"(?:\sclass="image")?\stitle\s?=\s?\"([^\"]*)\"'
)
ns = self.site().category_namespaces()
# regular expression matching the "(next 200)" link
RLinkToNextPage = re.compile('&from=(.*?)" title="')
if startFrom:
currentPageOffset = urllib.quote(
startFrom.encode(self.site().encoding()))
else:
currentPageOffset = None
while True:
path = self.site().get_address(self.urlname())
if purge:
path += '&action=purge'
if currentPageOffset:
path += '&from=' + currentPageOffset
wikipedia.output(
'Getting [[%s]] starting at %s...' %
(self.title(),
wikipedia.url2link(currentPageOffset, self.site(),
self.site())))
else:
wikipedia.output('Getting [[%s]]...' % self.title())
wikipedia.get_throttle()
txt = self.site().getUrl(path)
# index where subcategory listing begins
if self.site().versionnumber() >= 9:
# These IDs were introduced in 1.9
if '<div id="mw-subcategories">' in txt:
ibegin = txt.index('<div id="mw-subcategories">')
elif '<div id="mw-pages">' in txt:
ibegin = txt.index('<div id="mw-pages">')
elif '<div id="mw-category-media">' in txt:
ibegin = txt.index('<div id="mw-category-media">')
else:
# No pages
return
else:
ibegin = txt.index('<!-- start content -->'
) # does not work for cats without text
# TODO: This parses category text and may think they are
# pages in category! Check for versions before 1.9
# index where article listing ends
if '<div class="printfooter">' in txt:
iend = txt.index('<div class="printfooter">')
elif '<div class="catlinks">' in txt:
iend = txt.index('<div class="catlinks">')
else:
iend = txt.index('<!-- end content -->')
txt = txt[ibegin:iend]
for title in Rtitle.findall(txt):
if title == self.title():
# This is only a link to "previous 200" or "next 200".
# Ignore it.
pass
# For MediaWiki versions where subcats look like articles
elif isCatTitle(title, self.site()):
ncat = Category(self.site(), title)
yield SUBCATEGORY, ncat
else:
yield ARTICLE, wikipedia.Page(self.site(), title)
if Rsubcat:
# For MediaWiki versions where subcats look differently
for titleWithoutNamespace in Rsubcat.findall(txt):
title = 'Category:%s' % titleWithoutNamespace
ncat = Category(self.site(), title)
yield SUBCATEGORY, ncat
if Rimage:
# For MediaWiki versions where images work through galleries
for title in Rimage.findall(txt):
# In some MediaWiki versions, the titles contain the namespace,
# but they don't in other (newer) versions. Use the ImagePage's
# defaultNamespace feature to get everything correctly.
yield ARTICLE, wikipedia.ImagePage(self.site(), title)
# try to find a link to the next list page
matchObj = RLinkToNextPage.search(txt)
if matchObj:
currentPageOffset = matchObj.group(1)
else:
break
def treat(text, linkedPage, targetPage):
"""
Based on the method of the same name in solve_disambiguation.py
"""
mysite = pywikibot.getSite()
linktrail = mysite.linktrail()
# make a backup of the original text so we can show the changes later
linkR = re.compile(
r'\[\[(?P<title>[^\]\|#]*)(?P<section>#[^\]\|]*)?(\|(?P<label>[^\]]*))?\]\](?P<linktrail>'
+ linktrail + ')')
curpos = 0
# This loop will run until we have finished the current page
while True:
m = linkR.search(text, pos=curpos)
if not m:
break
# Make sure that next time around we will not find this same hit.
curpos = m.start() + 1
# ignore interwiki links and links to sections of the same page
if m.group('title').strip() == '' or \
mysite.isInterwikiLink(m.group('title')):
continue
else:
actualLinkPage = pywikibot.Page(targetPage.site(),
m.group('title'))
# Check whether the link found is to page.
if actualLinkPage != linkedPage:
continue
# how many bytes should be displayed around the current link
context = 15
# at the beginning of the link, start red color.
# at the end of the link, reset the color to default
#pywikibot.output(text[max(0, m.start() - context) : m.start()] + '\03{lightred}' + text[m.start() : m.end()] + '\03{default}' + text[m.end() : m.end() + context])
choice = 'y'
# The link looks like this:
# [[page_title|link_text]]trailing_chars
page_title = m.group('title')
link_text = m.group('label')
if not link_text:
# or like this: [[page_title]]trailing_chars
link_text = page_title
if m.group('section') == None:
section = ''
else:
section = m.group('section')
trailing_chars = m.group('linktrail')
if trailing_chars:
link_text += trailing_chars
if choice in "uU":
# unlink - we remove the section if there's any
text = text[:m.start()] + link_text + text[m.end():]
continue
replaceit = choice in "rR"
# remove preleading ":"
if link_text[0] == ':':
link_text = link_text[1:]
if link_text[0].isupper():
new_page_title = targetPage.title()
else:
new_page_title = targetPage.title()[0].lower() + \
targetPage.title()[1:]
# remove preleading ":"
if new_page_title[0] == ':':
new_page_title = new_page_title[1:]
if replaceit and trailing_chars:
newlink = "[[%s%s]]%s" % (new_page_title, section, trailing_chars)
elif replaceit or (new_page_title == link_text and not section):
newlink = "[[%s]]" % new_page_title
# check if we can create a link with trailing characters instead of a
# pipelink
elif len(new_page_title) <= len(link_text) and \
firstcap(link_text[:len(new_page_title)]) == \
firstcap(new_page_title) and \
re.sub(re.compile(linktrail), '', link_text[len(new_page_title):]) == '' and not section:
newlink = "[[%s]]%s" % (link_text[:len(new_page_title)],
link_text[len(new_page_title):])
else:
newlink = "[[%s%s|%s]]" % (new_page_title, section, link_text)
text = text[:m.start()] + newlink + text[m.end():]
continue
return text
def main():
args = wikipedia.handleArgs()
all = False
force = False
for currentArgument in args:
if currentArgument.startswith("-always"):
all = True
if currentArgument.startswith("-force"):
force = True
templateFile = codecs.open("modello_totocalcio.txt", "r", "utf-8")
modelloVoce = templateFile.read() # Legge il modello della pagina
templateFile.close()
urlo = "http://www.calcio.sisal.it/pages/totocalcio/ultimo.xwb"
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
concorso = re.search("<h2>Concorso n. (\d+) di (.*?) (\d+) (.*?) (\d+)</h2>", htmlText)
montepremi = re.search("<tr>\s*<th[^>]*>Il Montepremi</th>\s*</tr>\s*<tr>\s*<TD[^>]*>\s*Del Concorso \(premi a punteggio\)\s*</TD>\s*<TD>\s*EUR\s*</TD>\s*<TD>\s*(.*?)\s*</TD>\s*</tr>\s*<tr>\s*<TD[^>]*>\s*Riporto Jackpot conc\. precedente\s*</TD>\s*<TD>\s*EUR\s*</TD>\s*<TD[^>]*>\s*(.*?)\s*</TD>\s*</tr>\s*<tr\s*>\s*<TD[^>]*>\s*Montepremi totale del concorso\s*</TD>\s*<TD>\s*EUR\s*</TD>\s*<TD[^>]*>\s*(.*?)\s*</TD>\s*</tr>", htmlText, re.I)
montepremi9 = re.search("<tr>\s*<th[^>]*>Il Montepremi \"Il9\"</th>\s*</tr>\s*<tr>\s*<TD[^>]*>\s*Del Concorso \(premi a punteggio\)\s*</TD>\s*<TD>\s*EUR\s*</TD>\s*<TD>\s*(.*?)\s*</TD>\s*</tr>\s*<tr>\s*<TD[^>]*>\s*Riporto Jackpot conc\. precedente\s*</TD>\s*<TD>\s*EUR\s*</TD>\s*<TD[^>]*>\s*(.*?)\s*</TD>\s*</tr>\s*<tr>\s*<TD[^>]*>\s*Montepremi totale del concorso 9\s*</TD>\s*<TD>\s*EUR\s*</td>\s*<TD[^>]*>\s*(.*?)\s*</TD>\s*</tr>", htmlText, re.I)
bloccoQuote = "<tr>\s*<td>\s*(.*?)\s*</td>\s*<td>\"%s\"</td>\s*<td[^>]*>\s*(.*?)\s*</td>\s*</tr>"
bloccoPartita = "<tr[^>]*>\s*<td[^>]*>\s*<b>\s*%s\s*</b>\s*</td>\s*<td[^>]*>\s*(.*?)\s*</td>\s*<td[^>]*>\s*(.*?)\s*</td>\s*<td[^>]*>\s*<b>\s*(\d+)\s*-\s*(\d+) \s*</b>\s*</td>\s*<td[^>]*>\s*<b>\s*([12X]) \s*</b>\s*</td>\s*</tr>"
jackpotFuturi = re.search("<table.*?>\s*<tr>\s*<th[^>]*>\s*Jackpot prossimo concorso\s*</th>\s*</tr>\s*<tr>\s*<th[^>]*>.*?</th>\s*</tr>\s*<tr>\s*<td[^>]*><h2><b>14</b></h2></td>\s*<td[^>]*><h1>(.*?)<font[^>]*>.*?</font></h1></td>\s*</tr>\s*</table>", htmlText, re.I)
page = wikipedia.Page(wikipedia.getSite(code='it', fam='wikinews'), "Italia: concorso n. " + concorso.group(1) + "/" + concorso.group(5) + " del Totocalcio")
if page.exists() and not force:
wikipedia.output("Nessuna nuova estrazione. Mi fermo.")
return
elencoSostituzioni = { # Sostituisce le variabili nel modello
'#super-id': concorso.group(1),
'#dow': concorso.group(2).replace('ì', u'ì'),
'#giorno': concorso.group(3),
'#mese': concorso.group(4),
'#anno': concorso.group(5),
'#montepremi-parz': montepremi.group(1),
'#jackpot': montepremi.group(2),
'#montepremi-tot': montepremi.group(3),
'#9-montepremi-parz': montepremi9.group(1),
'#9-jackpot': montepremi9.group(2),
'#9-montepremi-tot': montepremi9.group(3),
}
try:
elencoSostituzioni['#futuro-jackpot'] = jackpotFuturi.group(1)
except:
elencoSostituzioni['#futuro-jackpot'] = '-'
try:
elencoSostituzioni['#9-futuro-jackpot'] = jackpotFuturi.group(2)
except:
elencoSostituzioni['#9-futuro-jackpot'] = '-'
partite = range(1, 15)
for p in partite:
match = re.search(bloccoPartita % p, htmlText, re.I)
elencoSostituzioni['#sq-' + str(p) + 'a'] = match.group(1).capitalize()
elencoSostituzioni['#sq-' + str(p) + 'b'] = match.group(2).capitalize()
elencoSostituzioni['#res-' + str(p) + 'a'] = match.group(3)
elencoSostituzioni['#res-' + str(p) + 'b'] = match.group(4)
elencoSostituzioni['#ok-' + str(p)] = match.group(5)
quotes = [9, 12, 13, 14]
for c in quotes:
match = re.search(bloccoQuote % c, htmlText, re.I)
elencoSostituzioni['#vincitori-' + str(c)] = match.group(1).replace('nessuna', '0')
elencoSostituzioni['#euro-' + str(c)] = match.group(2).replace('-', '0')
nuovoTesto = massiveReplace(elencoSostituzioni, modelloVoce)
#page = wikipedia.Page(wikipedia.getSite(code='it', fam='wikinews'), "Utente:BimBot/Sandbox") #DEBUG
wikipedia.output(">>>>> " + page.title() + " <<<<<")
try:
vecchioTesto = page.get()
except wikipedia.NoPage:
vecchioTesto = ''
wikipedia.showDiff(vecchioTesto, 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: Inserisco nuova estrazione del Totocalcio")
def main():
gen = None
prefix = None
oldName = None
newName = None
noredirect = True
always = False
skipredirects = False
summary = None
fromToPairs = []
# This factory is responsible for processing command line arguments
# that are also used by other scripts and that determine on which pages
# to work on.
genFactory = pagegenerators.GeneratorFactory()
for arg in wikipedia.handleArgs():
if arg.startswith('-pairs'):
if len(arg) == len('-pairs'):
filename = wikipedia.input(
u'Enter the name of the file containing pairs:')
else:
filename = arg[len('-pairs:'):]
oldName1 = None
for page in pagegenerators.TextfilePageGenerator(filename):
if oldName1:
fromToPairs.append([oldName1, page.title()])
oldName1 = None
else:
oldName1 = page.title()
if oldName1:
wikipedia.output(
u'WARNING: file %s contains odd number of links' %
filename)
elif arg == '-noredirect':
noredirect = False
elif arg == '-always':
always = True
elif arg == '-skipredirects':
skipredirects = True
elif arg.startswith('-from:'):
if oldName:
wikipedia.output(u'WARNING: -from:%s without -to:' % oldName)
oldName = arg[len('-from:'):]
elif arg.startswith('-to:'):
if oldName:
fromToPairs.append([oldName, arg[len('-to:'):]])
oldName = None
else:
wikipedia.output(u'WARNING: %s without -from' % arg)
elif arg.startswith('-prefix'):
if len(arg) == len('-prefix'):
prefix = wikipedia.input(u'Enter the prefix:')
else:
prefix = arg[8:]
elif arg.startswith('-summary'):
if len(arg) == len('-summary'):
summary = wikipedia.input(u'Enter the summary:')
else:
summary = arg[9:]
else:
genFactory.handleArg(arg)
if oldName:
wikipedia.output(u'WARNING: -from:%s without -to:' % oldName)
for pair in fromToPairs:
page = wikipedia.Page(wikipedia.getSite(), pair[0])
bot = MovePagesBot(None, prefix, noredirect, always, skipredirects,
summary)
bot.moveOne(page, pair[1])
if not gen:
gen = genFactory.getCombinedGenerator()
if gen:
preloadingGen = pagegenerators.PreloadingGenerator(gen)
bot = MovePagesBot(preloadingGen, prefix, noredirect, always,
skipredirects, summary)
bot.run()
elif not fromToPairs:
wikipedia.showHelp('movepages')
l = l.strip()
if l:
if l[0] in [';', ':', '|', '{', '}', '<', '[', ']', '!', '#', '*', ' ']:
continue
else:
if pagetitle.lower() in l.lower():
abstract = compensatehtmlcomments(l)
break
#capturar imagenes
images = re.findall(ur"(?im)(?:(?:Archivo|File|Image)\s*\:|(?:image[ _]?skyline|picture|photo|photography|imagen?|foto|fotograf[íi]a)\s*=)\s*([^\|\[\]]+?\.(?:jpe?g))", revtext)
selectedimage = ''
caption = ''
if images and images[0]:
selectedimage = images[0]
commonspage = wikipedia.Page(commonssite, u'File:%s' % (selectedimage))
if commonspage.exists():
caption = revtext.split(selectedimage)[1].strip()
if caption.startswith('|thumb') or caption.startswith('|left') or caption.startswith('|right'):
m = re.findall(ur'(?im)^\s*\|\s*(?:thumb|thumbnail|frame|(?:(?:up)?(?:left|right|center)(?:\s*=?\s*\d*\.?\d*)?))([^\[\]]*?)\]\]', caption)
if m:
caption = m[0].strip().lstrip('|')
else:
brackets = 2
c = 0
while len(caption) > c and c <= 500 and brackets != 0:
if caption[c] == '[':
brackets += 1
elif caption[c] == ']':
brackets -= 1
c += 1
def subTemplate(self, content, param):
"""Substitute the template tags in content according to param.
@param content: Content with tags to substitute.
@type content: string
@param param: Param with data how to substitute tags.
@type param: dict
Returns a tuple containig the new content with tags
substituted and a list of those tags.
"""
substed_tags = [] # DRTRIGON-73
metadata = {
'mw-signature': u'~~~~',
'mw-timestamp': u'~~~~~',
} # DRTRIGON-132
# 0.2.) check for 'simple' mode and get additional params
if param['simple']:
p = self.site.getExpandedString(param['simple'])
param.update(pywikibot.extract_templates_and_params(p)[0][1])
# 0.5.) check cron/date
if param['cron']:
# [min] [hour] [day of month] [month] [day of week]
# (date supported only, thus [min] and [hour] dropped)
if not (param['cron'][0] == '@'):
param['cron'] = '* * ' + param['cron']
entry = crontab.CronTab(param['cron'])
# find the delay from midnight (does not return 0.0 - but next)
delay = entry.next(datetime.datetime.now().replace(hour=0,
minute=0,
second=0,
microsecond=0) - \
datetime.timedelta(microseconds=1))
pywikibot.output(u'CRON delay for execution: %.3f (<= %i)' %
(delay, self._bot_config['CRONMaxDelay']))
if not (delay <= self._bot_config['CRONMaxDelay']):
return (content, substed_tags, metadata)
# 1.) getUrl or wiki text
# (security: check url not to point to a local file on the server,
# e.g. 'file://' - same as used in xsalt.py)
secure = False
for item in [
u'http://', u'https://', u'mail://', u'local://', u'wiki://'
]:
secure = secure or (param['url'][:len(item)] == item)
param['zip'] = ast.literal_eval(param['zip'])
if not secure:
return (content, substed_tags, metadata)
if param['url'][:7] == u'wiki://':
url = param['url'][7:].strip('[]') # enable wiki-links
if ast.literal_eval(param['expandtemplates']
): # DRTRIGON-93 (only with 'wiki://')
external_buffer = pywikibot.Page(self.site,
url).get(expandtemplates=True)
else:
external_buffer = self.load(pywikibot.Page(self.site, url))
elif (param['url'][:7] == u'mail://'): # DRTRIGON-101
url = param['url'].replace(u'{{@}}', u'@') # e.g. nlwiki
mbox = SubsterMailbox(
pywikibot.config.datafilepath(self._bot_config['data_path'],
self._bot_config['mbox_file'],
''))
external_buffer = mbox.find_data(url)
mbox.close()
elif (param['url'][:8] == u'local://'): # DRTRIGON-131
if (param['url'][8:] == u'cache/state_bots'):
# filename hard-coded
d = shelve.open(
pywikibot.config.datafilepath('cache', 'state_bots'))
external_buffer = pprint.pformat(
ast.literal_eval(pprint.pformat(d)))
d.close()
else:
external_buffer = u'n/a'
else:
# consider using 'expires', 'last-modified', 'etag' in order to
# make the updating data requests more efficient! use those stored
# on page, if the user placed them, else use the conventional mode.
# http://www.diveintopython.net/http_web_services/etags.html
f_url, external_buffer = http.request(self.site,
param['url'],
no_hostname=True,
back_response=True)
headers = f_url.headers # same like 'f_url.info()'
#if param['zip']:
if ('text/' not in headers['content-type']):
pywikibot.output(u'Source is of non-text content-type, '
u'using raw data instead.')
external_buffer = f_url.read()
del f_url # free some memory (no need to keep copy)
for h in ['content-length', 'date', 'last-modified', 'expires']:
if h in headers:
metadata['url-%s' % h] = headers[h]
# some intermediate processing (unzip, xlsx2csv, ...)
if param['zip']: # 'application/zip', ...
fileno = 0 if (param['zip'] is True) else (param['zip'] - 1)
external_buffer = self.unzip(external_buffer, fileno)
if param[
'xlsx']: # 'application/vnd.openxmlformats-officedocument.spreadsheetml.sheet'
external_buffer = self.xlsx2csv(external_buffer, param['xlsx'])
if param['ods']: # 'application/vnd.oasis.opendocument.spreadsheet'
external_buffer = self.ods2csv(external_buffer, param['ods'])
if not ast.literal_eval(param['beautifulsoup']): # DRTRIGON-88
# 2.) regexp
#for subitem in param['regex']:
subitem = param['regex']
regex = re.compile(subitem, re.S | re.I)
# 3.) subst in content
external_data = regex.search(external_buffer)
external_data_dict = {}
if external_data: # not None
external_data = external_data.groups()
pywikibot.output(u'Groups found by regex: %i' %
len(external_data))
# DRTRIGON-114: Support for named groups in regexs
if regex.groupindex:
for item in regex.groupindex:
external_data_dict[u'%s-%s' %
(param['value'],
item)] = external_data[
regex.groupindex[item] - 1]
elif (len(external_data) == 1):
external_data_dict = {param['value']: external_data[0]}
else:
external_data_dict = {param['value']: str(external_data)}
pywikibot.debug(str(external_data_dict))
param['postproc'] = eval(param['postproc'])
# should be secured as given below, but needs code changes in wiki too
#param['postproc'] = ast.literal_eval(param['postproc'])
for value in external_data_dict:
external_data = external_data_dict[value]
# 4.) postprocessing
func = param['postproc'][
0] # needed by exec call of self._code
DATA = [external_data]
args = param['postproc'][1:]
scope = {} # (scope to run in)
scope.update(locals()) # (add DATA, *args, ...)
scope.update(globals()) # (add imports and else)
if func:
exec(
self._code + (self._bot_config['CodeTemplate'] % func),
scope, scope)
external_data = DATA[0]
pywikibot.debug(external_data)
# 5.) subst content
(content, tags) = self.subTag(content, value, external_data,
int(param['count']))
substed_tags += tags
else:
# DRTRIGON-105: Support for multiple BS template configurations
value = param['value']
if value:
value += u'-'
# DRTRIGON-88: Enable Beautiful Soup power for Subster
BS_tags = self.get_BS_regex(value).findall(content)
pywikibot.output(u'BeautifulSoup tags found by regex: %i' %
len(BS_tags))
prev_content = content
BS = BeautifulSoup.BeautifulSoup(external_buffer)
for item in BS_tags:
external_data = eval('BS.%s' % item[1])
external_data = self._BS_regex_str % {
'var1': value + 'BS:' + item[1],
'var2': value,
'cont': external_data
}
content = content.replace(item[0], external_data, 1)
if (content != prev_content):
substed_tags.append(value + 'BS')
metadata['bot-timestamp'] = pywikibot.Timestamp.now().isoformat(' ')
return (content, substed_tags, metadata)
def _parseCategory(self,
purge=False,
startFrom=None,
sortby=None,
sortdir=None):
"""
Yields all articles and subcategories that are in this category by API.
Set startFrom to a string which is the title of the page to start from.
Yielded results are tuples in the form (tag, page) where tag is one
of the constants ARTICLE and SUBCATEGORY, and title is the Page or Category
object.
Note that results of this method need not be unique.
This should not be used outside of this module.
"""
if not self.site().has_api() or self.site().versionnumber() < 11:
for tag, page in self._oldParseCategory(purge, startFrom):
yield tag, page
return
currentPageOffset = None
params = {
'action': 'query',
'list': 'categorymembers',
'cmtitle': self.title(),
'cmprop': ['title', 'ids', 'sortkey', 'timestamp'],
#'': '',
}
if sortby:
params['cmsort'] = sortby
if sortdir:
params['cmdir'] = sortdir
while True:
if wikipedia.config.special_page_limit > 500:
params['cmlimit'] = 500
else:
params['cmlimit'] = wikipedia.config.special_page_limit
if currentPageOffset:
params.update(currentPageOffset)
wikipedia.output(
'Getting [[%s]] list from %s...' %
(self.title(), "%s=%s" % currentPageOffset.popitem()))
elif startFrom:
startFrom = startFrom.upper(
) # category sort keys are uppercase
params['cmstartsortkey'] = startFrom
wikipedia.output('Getting [[%s]] list starting at %s...' %
(self.title(), startFrom))
else:
wikipedia.output('Getting [[%s]]...' % self.title())
wikipedia.get_throttle()
data = query.GetData(params, self.site())
if 'error' in data:
raise RuntimeError("%s" % data['error'])
count = 0
for memb in data['query']['categorymembers']:
count += 1
# For MediaWiki versions where subcats look like articles
if memb['ns'] == 14:
yield SUBCATEGORY, Category(self.site(),
memb['title'],
sortKey=memb['sortkey'])
elif memb['ns'] == 6:
yield ARTICLE, wikipedia.ImagePage(self.site(),
memb['title'])
else:
yield ARTICLE, wikipedia.Page(self.site(),
memb['title'],
defaultNamespace=memb['ns'])
if count >= params['cmlimit']:
break
# try to find a link to the next list page
if 'query-continue' in data and count < params['cmlimit']:
currentPageOffset = data['query-continue']['categorymembers']
else:
break
def run(self):
"""
Starts the robot.
"""
# Run the generator which will yield Pages which might need to be
# changed.
for page in self.generator:
wikipedia.output(u'\n>>> %s <<<' % page.title())
#Current time
sectiont0 = time.time()
try:
# Load the page's text from the wiki.
original_text = page.get()
if not page.canBeEdited():
wikipedia.output(
u'Pagina %s wordt overgeslagen, deze pagina is beveiligd.'
% page.title())
continue
#No page, so ignore
except wikipedia.NoPage:
wikipedia.output(u'Pagina %s bestaat niet.' % page.title())
continue
#Get the archiving settings.
settings = self.loadConfig(original_text)
#No settings were found, leave a message on the page.
if not settings:
wikipedia.output(
u'Er kunnen geen instellingen worden gevonden op %s. Er wordt een bericht achtergelaten.'
% page.title())
page.put(original_text + self.nosettingscomment,
self.commentsummary,
minorEdit=False)
continue
#Incorrect magicwords settings were found, leave a message on the page.
if not self.settings[
'magicwords'] == u'oudste' and not self.settings[
'magicwords'] == u'recentste':
wikipedia.output(
u'Pagina %s wordt overgeslagen, er zijn geen of foute magicwords instellingen opgegeven, opgegeven was %s. Er wordt een bericht achtergelaten.'
% (page.title(), self.settings['magicwords']))
page.put(original_text + self.nomagicwordscomment,
self.commentsummary,
minorEdit=False)
continue
#Get the number of days after which a section should be archived.
self.settings['dagen'] = int(self.settings['dagen'])
#Get the template for the archive page, some variables still have to be replaced using the section's oldest or most
#recent date.
#Make it a subpage of the current page.
archive_titletemplate = page.title(
) + '/' + self.doDateReplacements(self.settings['archief'].strip())
#Get a datetime object for the current date and time to compare other dates.
todaydt = datetime.datetime.today()
#Split the text into sections
sections = self.resection.split(original_text)
#The text before the first section won't be checked.
new_text = sections[0]
#A dictionary containing the archive page as key and the text as item.
archives_dictionary = {}
#The archiving target to be used in summaries.
archive_target = 'n.v.t.'
#The number of sections that will be archived.
numberofsections = 0
#A dictionary containing the archive page as key and the number of sections that will
#be archived to that page as item.
nos_dictionary = {}
#Check all sections
for i in range(2, len(sections), 2):
archive_text = ''
section_text = sections[i]
#Check if the page shouldn't be archived.
if self.renoarchive.search(section_text):
#Ignore this section.
new_text += sections[i - 1] + section_text
continue
#A list of the dates in wikisyntax.
dates = self.redate.findall(section_text)
if dates:
#A list of the dates as datetimeobjects.
datesdt = []
#A list of the difference in seconds between the date and now.
differences = {}
j = 0
#Create datetime objects from all found dates.
for date in dates:
datematch = self.redatematch.match(date[0])
try:
datedt = datetime.datetime(
int(datematch.group(3)),
self.monthn[datematch.group(2)],
int(datematch.group(1)),
int(datematch.group(4)),
int(datematch.group(5)))
except:
wikipedia.output(
u'Could not create a datetime object, skipping date'
)
continue
datesdt.append(datedt)
differencedt = todaydt - datedt
differences[
j] = differencedt.days * 86400 + differencedt.seconds
j += 1
try:
diferences_sortedkeys = self.sort_by_value(differences)
difference = todaydt - datesdt[
diferences_sortedkeys[0]]
except:
wikipedia.output(
u'Could not get the difference, probably because of skipping a date.'
)
#Add daylight saving time
if time.daylight == 1:
dst = 'CEST'
else:
dst = 'CET'
section_text += '\n<!-- %s %s %s -->' % (
time.strftime('%d'), self.month[int(
time.strftime('%m'))],
time.strftime('%Y %H:%M (%Z)'))
new_text += sections[i - 1] + section_text
continue
#Check if a section should be archived using the most recent date.
if difference.days >= self.settings['dagen']:
if self.settings['magicwords'] == 'recentste':
archive_title = self.doTitleReplacements(
archive_titletemplate,
datesdt[diferences_sortedkeys[0]])
else:
archive_title = self.doTitleReplacements(
archive_titletemplate,
datesdt[diferences_sortedkeys[
len(diferences_sortedkeys) - 1]])
#Add section to archive.
numberofsections += 1
#Add the text and number of sections to the corresponding dictionaries.
if archives_dictionary.has_key(archive_title):
archives_dictionary[archive_title] += sections[
i - 1] + section_text
nos_dictionary[archive_title] += 1
else:
archives_dictionary[archive_title] = sections[
i - 1] + section_text
nos_dictionary[archive_title] = 1
#Add archive_title to archive_target
archive_target = '[[%s]]' % archive_title
else:
new_text += sections[i - 1] + section_text
else:
#No date was found, add one.
#We have to fill in the date ourselves because MediaWiki ignores <!-- ~~~~~ -->.
#Add daylight saving time
if time.daylight == 1:
dst = 'CEST'
else:
dst = 'CET'
section_text += '\n<!-- %s %s %s (%s) -->' % (
time.strftime('%d'), self.month[int(
time.strftime('%m'))], time.strftime('%Y %H:%M'),
dst)
new_text += sections[i - 1] + section_text
#Check if there are multiple archive pages
if len(archives_dictionary) > 1:
archive_target = '%i archiefpagina\'s' % len(
archives_dictionary)
if not original_text == new_text:
if page.isRedirectPage() or not page.canBeEdited():
wikipedia.output(u'Can not edit %s. Aborting.' %
page.title())
continue
abort = False
for title in archives_dictionary.keys():
ap = wikipedia.Page(self.site, title)
if ap.isRedirectPage() or not ap.canBeEdited():
wikipedia.output(u'Can not edit %s. Aborting.' %
ap.title())
try:
page.put(page.get() + self.cantedit % ap.title(),
self.canteditsummary,
minorEdit=False)
except wikipedia.EditConflict:
wikipedia.output(
u'Pagina %s wordt overgeslagen vanwege een bewerkingsconflict.'
% (page.title()))
abort = True
break
if abort:
continue
if not original_text == new_text:
diff = len(original_text) - len(new_text)
reduction = (diff / len(original_text)) * 100
wikipedia.output(
u'Er worden %d onderwerpen gearchiveerd ouder dan %d dagen. In totaal worden %d tekens aangepast, een reductie van %d procent.'
% (numberofsections, self.settings['dagen'], diff,
reduction))
wikipedia.output(
u'Deze onderwerpen worden gearchiveerd naar %d verschillende archiefpagina\'s.'
% (len(archives_dictionary)))
if not self.acceptall:
cview = wikipedia.inputChoice(
u'Wilt u deze wijzigingen bekijken?', ['Yes', 'No'],
['y', 'N'], 'N')
if cview in ['y', 'Y']:
wikipedia.showDiff(original_text, new_text)
choice = wikipedia.inputChoice(
u'Wilt u deze wijzigingen doorvoeren?',
['Yes', 'No', 'All'], ['y', 'N', 'a'], 'N')
if choice in ['a', 'A']:
self.acceptall = True
#Archive the page.
if self.acceptall or choice in ['y', 'Y']:
if numberofsections:
wikipedia.setAction(
'nlwikibots: [[Gebruiker:Erwin85/Bot/Archivering|Archivering]] van %i %s ouder dan %i dagen naar %s.'
% (numberofsections,
self.plural(numberofsections, 'onderwerp',
'onderwerpen'),
self.settings['dagen'], archive_target))
else:
wikipedia.setAction(
'nlwikibots: Datum toegevoegd in verband met [[Gebruiker:Erwin85/Bot/Archivering|archivering]].'
)
try:
page.put(new_text)
except wikipedia.EditConflict:
wikipedia.output(
u'Pagina %s wordt overgeslagen vanwege een bewerkingsconflict.'
% (page.title()),
toStdout=True)
continue
except wikipedia.LockedPage:
wikipedia.output(u'Pagina %s is beveiligd.' %
(page.title()),
toStdout=True)
continue
for archive_title, archivetext in archives_dictionary.items(
):
redirect = False
if numberofsections:
wikipedia.setAction(
'nlwikibots: [[Gebruiker:Erwin85/Bot/Archivering|Archivering]] van %i %s ouder dan %i dagen van [[%s]].'
% (nos_dictionary[archive_title],
self.plural(nos_dictionary[archive_title],
'onderwerp', 'onderwerpen'),
self.settings['dagen'], page.title()))
try:
archivepage = wikipedia.Page(
self.site, archive_title)
# Load the page's text from the wiki
original_archivetext = archivepage.get()
if not page.canBeEdited():
wikipedia.output(
u'Pagina %s wordt overgeslagen, deze pagina is beveiligd.'
% archive_title)
continue
except wikipedia.NoPage:
wikipedia.output(u'Pagina %s bestaat niet.' %
archive_title)
original_archivetext = ''
except wikipedia.IsRedirectPage:
wikipedia.output(
u'Pagina %s is een doorverwijzing.' %
archive_title)
redirect = True
if not redirect:
if original_archivetext:
archivetext = original_archivetext + '\n' + archivetext
else:
if self.settings['sjabloon']:
archivetext = '{{subst:%s}}\n' % self.settings[
'sjabloon'] + archivetext
try:
archivepage.put(archivetext)
except wikipedia.EditConflict:
wikipedia.output(
u'Pagina %s wordt overgeslagen vanwege een bewerkingsconflict.'
% (archive_title))
else:
wikipedia.output(
u'Leaving message informing that archive page is a redirect.'
)
try:
page.put(page.get() +
self.cantedit % archive_title,
self.canteditsummary,
minorEdit=False)
except wikipedia.EditConflict:
wikipedia.output(
u'Pagina %s wordt overgeslagen vanwege een bewerkingsconflict.'
% (page.title()))
else:
#No need for archiving.
wikipedia.output(u'Archivering is niet nodig.')
#Execution time for this section.
sectiontimediff = time.time() - sectiont0
wikipedia.output(u'Executiontime: %ss.' % str(sectiontimediff))
#Total execution time.
timediff = time.time() - self.t0
wikipedia.output(u'Total executiontime: %ss.' % str(timediff))
def main():
args = wikipedia.handleArgs()
all = False
for currentArgument in args:
if currentArgument.startswith("-always"):
all = True
templateFile = codecs.open("modello_meteo.txt", "r", "utf-8")
modelloVoce = templateFile.read() # Legge il modello della pagina
templateFile.close()
urlo = "http://www.meteoam.it/modules/tempoInAtto/infoStazione.php?icao=%s"
replacements = {}
for i in codiciStazioni:
try:
htmlText = pageText(urlo % i)
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
match = re.search(
'<div class="titolo">Informazioni meteorologiche/climatologiche per (.*?)</div>',
htmlText)
nomeLocalita = unicode(match.group(1))
wikipedia.output(nomeLocalita + " (" + i + ")")
nuvoloMatch = re.search(
u'<b>Nuvolosità</b></font></td>\s*<td.*?>\s*.*?\s*</td>\s*<td .*?>\s*<p .*?><img .*? alt\s*="(.*?)" .*?>\s*</td>',
htmlText)
ventoMatch = re.search(
u'<b>Vento</b></font></td>\s*<td.*?>\s*.*?\s*</td>\s*<td .*?>\s*<p .*?><img .*? alt\s*="Vento (.*?)( Direzione (.*?))?" .*?>\s*</td>',
htmlText)
maxMatch = re.search(
u'<td .*?>\s*<font .*?><b>Temperatura</b></font>\s*<p><font .*?><b> Max</b></font></td>\s*<td.*?>\s*.*?\s*</td>\s*<td .*?><b>\s*<font .*?>([+-]?\s*\d+)</font></b></td>',
htmlText)
minMatch = re.search(
u'<td .*?>\s*<font .*?><b>Temperatura</b></font>\s*<p><font .*?><b> Min</b></font></td>\s*<td.*?>\s*.*?\s*</td>\s*<td .*?><b>\s*<font .*?>([+-]?\s*\d+)</font></b></td>',
htmlText)
if nuvoloMatch != None:
replacements['#tempo-' + nomeLocalita + '#'] = iconaTempo(
nuvoloMatch.group(1))
else:
replacements['#tempo-' + nomeLocalita + '#'] = nd
if ventoMatch != None:
replacements['#intensita-' + nomeLocalita +
'#'] = ventoMatch.group(1)
if ventoMatch.group(2) != None:
replacements['#vento-' + nomeLocalita +
'#'] = ventoMatch.group(3)
elif ventoMatch.group(2) == None and ventoMatch.group(
1) == "variabile":
replacements['#vento-' + nomeLocalita + '#'] = "variabile"
replacements['#intensita-' + nomeLocalita + '#'] = "debole"
else:
replacements['#vento-' + nomeLocalita + '#'] = nd
else:
replacements['#vento-' + nomeLocalita + '#'] = nd
replacements['#intensita-' + nomeLocalita + '#'] = nd
if maxMatch != None:
replacements['#max-' + nomeLocalita + '#'] = maxMatch.group(1)
else:
replacements['#max-' + nomeLocalita + '#'] = nd
if minMatch != None:
replacements['#min-' + nomeLocalita + '#'] = minMatch.group(1)
else:
replacements['#min-' + nomeLocalita + '#'] = nd
nuovoTesto = massiveReplace(replacements, modelloVoce)
page = wikipedia.Page(wikipedia.Site('it', 'wikinews'),
'Template:Pagina principale/Secondo piano/Meteo')
vecchioTesto = page.get()
wikipedia.showDiff(vecchioTesto, 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 meteo")
def replace_image(self,
image,
site,
page_title,
summary,
replacement=None):
""" The actual replacement. Giving None as argument for replacement
will delink instead of replace."""
page = wikipedia.Page(site, page_title)
hook = None
# TODO: Per site config.
if page.namespace(
) in self.CommonsDelinker.config['delink_namespaces']:
try:
text = page.get(get_redirect=True)
except wikipedia.NoPage:
return 'failed'
new_text = text
m_image = ImmutableByReference(image)
m_replacement = ImmutableByReference(replacement)
self.CommonsDelinker.exec_hook(
'before_replace', (page, summary, m_image, m_replacement))
image = m_image.get()
replacement = m_replacement.get()
def create_regex(s):
first, other = re.escape(s[0]), re.escape(s[1:])
return ur'(?:[%s%s]%s)' % (first.upper(), first.lower(), other)
def create_regex_i(s):
return ur'(?:%s)' % u''.join(
[u'[%s%s]' % (c.upper(), c.lower()) for c in s])
namespaces = site.namespace(6, all=True) + site.namespace(-2,
all=True)
r_namespace = ur'\s*(?:%s)\s*\:\s*' % u'|'.join(
map(create_regex_i, namespaces))
# Note that this regex creates a group!
r_image = u'(%s)' % create_regex(image).replace(r'\_', '[ _]')
def simple_replacer(match):
m_replacement = ImmutableByReference(replacement)
groups = list(match.groups())
if hook:
if False is self.CommonsDelinker.exec_hook(
'%s_replace' % hook,
(page, summary, image, m_replacement, match, groups)):
return u''.join(groups)
if m_replacement.get() is None:
return u''
else:
groups[1] = m_replacement.get()
return u''.join(groups)
# Previously links in image descriptions will cause
# unexpected behaviour: [[Image:image.jpg|thumb|[[link]] in description]]
# will truncate at the first occurence of ]]. This cannot be
# fixed using one regular expression.
# This means that all ]] after the start of the image
# must be located. If it then does not have an associated
# [[, this one is the closure of the image.
r_simple_s = u'(\[\[%s)%s' % (r_namespace, r_image)
r_s = '\[\['
r_e = '\]\]'
# First determine where wikilinks start and end
image_starts = [
match.start() for match in re.finditer(r_simple_s, text)
]
link_starts = [match.start() for match in re.finditer(r_s, text)]
link_ends = [match.end() for match in re.finditer(r_e, text)]
r_simple = u'(\[\[%s)%s(.*)' % (r_namespace, r_image)
hook = 'simple'
replacements = []
for image_start in image_starts:
current_link_starts = [
link_start for link_start in link_starts
if link_start > image_start
]
current_link_ends = [
link_end for link_end in link_ends
if link_end > image_start
]
end = image_start
if current_link_ends: end = current_link_ends[0]
while current_link_starts and current_link_ends:
start = current_link_starts.pop(0)
end = current_link_ends.pop(0)
if end <= start and end > image_start:
# Found the end of the image
break
# Check whether this image is the first one on the line
if image_start == 0:
prev = ''
else:
prev = new_text[image_start - 1]
if prev in ('', '\r', '\n') and replacement is None:
# Kill all spaces after end
while (end + 1) < len(new_text):
if new_text[end + 1] in WHITESPACE:
end += 1
else:
break
# Add the replacement to the todo list. Doing the
# replacement right know would alter the indices.
replacements.append((new_text[image_start:end],
re.sub(r_simple, simple_replacer,
new_text[image_start:end])))
# Perform the replacements
for old, new in replacements:
if old: new_text = new_text.replace(old, new)
# Remove the image from galleries
hook = 'gallery'
r_galleries = ur'(?s)(\<%s\>)(.*?)(\<\/%s\>)' % (
create_regex_i('gallery'), create_regex_i('gallery'))
r_gallery = ur'(?m)^((?:%s)?)%s(\s*(?:\|.*?)?\s*$)' % (r_namespace,
r_image)
def gallery_replacer(match):
return ur'%s%s%s' % (match.group(1),
re.sub(r_gallery, simple_replacer,
match.group(2)), match.group(3))
new_text = re.sub(r_galleries, gallery_replacer, new_text)
if text == new_text or self.CommonsDelinker.config.get(
'force_complex', False):
# All previous steps did not work, so the image is
# likely embedded in a complicated template.
hook = 'complex'
r_templates = ur'(?s)(\{\{.*?\}\})'
r_complicated = u'(?s)(?<=[|{=])[\s\u200E\uFEFF\u200B\u200C]*((?:%s)?)%s[\u200E\uFEFF\u200B\u200C]*' % (
r_namespace, r_image)
def template_replacer(match):
return re.sub(r_complicated, simple_replacer,
match.group(1))
new_text = re.sub(r_templates, template_replacer, text)
if text != new_text:
# Save to the wiki
# Code for checking user page existance has been moved
# to summary() code, to avoid checking the user page
# for each removal.
new_text = ImmutableByReference(new_text)
m_summary = ImmutableByReference(summary)
if False is self.CommonsDelinker.exec_hook(
'before_save', (page, text, new_text, m_summary)):
return 'skipped'
is_retry = False
while True:
try:
if self.CommonsDelinker.config.get('edit', True) and not \
((self.CommonsDelinker.site.lang == 'commons') ^ \
(config.usernames.get('commons', {}).get(
'commons') == 'CommonsDelinker')):
page.put(new_text.get(), m_summary.get())
return 'ok'
except wikipedia.ServerError, e:
output(u'Warning! ServerError: %s' % str(e))
except wikipedia.EditConflict:
# Try again
output(u'Got EditConflict trying to remove %s from %s:%s.' % \
(image, site, page_title))
return self.replace_image(image,
site,
page_title,
summary,
replacement=None)
except wikipedia.PageNotSaved:
if is_retry: return 'failed'
is_retry = True
except wikipedia.LockedPage:
return 'failed'
if newpages:
for (page, date, length, loggedIn, user, comment) in pywikibot.getSite().newpages(1000):
checkPage(page, checknames, knownonly)
elif start:
for page in pagegenerators.PreloadingGenerator(pagegenerators.AllpagesPageGenerator(start=start,includeredirects=False)):
checkPage(page, checknames, knownonly)
if longpages:
for (page, length) in pywikibot.getSite().longpages(500):
checkPage(page, checknames, knownonly)
else:
title = ' '.join(title)
while title != '':
try:
page = pywikibot.Page(mysite,title)
text = page.get()
except pywikibot.NoPage:
print "Page does not exist."
except pywikibot.IsRedirectPage:
print "Page is a redirect page"
else:
checkPage(page, knownonly=knownonly)
title = pywikibot.input(u"Which page to check now? (enter to stop)")
finally:
pywikibot.stopme()
filename = pywikibot.config.datafilepath('externals/spelling',
'spelling-' + checklang + '.txt')
if rebuild:
list = knownwords.keys()
list.sort()
def main():
start = '0'
force = False
msg = {'en':'Creating state abbreviation redirect',
'ar':u'إنشاء تحويلة اختصار الولاية',
'fa':u'ایجاد تغییرمسیر برای نام اختصاری ایالت',
'he':u'יוצר הפניה מראשי התיבות של המדינה',
}
abbrev = {
'Alabama': 'AL',
'Alaska': 'AK',
'Arizona': 'AZ',
'Arkansas': 'AR',
'California': 'CA',
'Colorado': 'CO',
'Delaware': 'DE',
'Florida': 'FL',
'Georgia': 'GA',
'Hawaii': 'HI',
'Idaho': 'ID',
'Illinois': 'IL',
'Indiana': 'IN',
'Iowa': 'IA',
'Kansas': 'KS',
'Kentucky': 'KY',
'Louisiana': 'LA',
'Maine': 'ME',
'Maryland': 'MD',
'Massachusetts': 'MA',
'Michigan': 'MI',
'Minnesota': 'MN',
'Mississippi': 'MS',
'Missouri': 'MO',
'Montana': 'MT',
'North Carolina': 'NC',
'North Dakota': 'ND',
'Nebraska': 'NE',
'Nevada': 'NV',
'New Hampshire': 'NH',
'New Jersey': 'NJ',
'New Mexico': 'NM',
'New York': 'NY',
'Ohio': 'OH',
'Oklahoma': 'OK',
'Oregon': 'OR',
'Pennsylvania': 'PA',
'Rhode Island': 'RI',
'South Carolina': 'SC',
'South Dakota': 'SD',
'Tennessee': 'TN',
'Texas': 'TX',
'Utah': 'UT',
'Vermont': 'VT',
'Virginia': 'VA',
'Washington': 'WA',
'West Virginia': 'WV',
'Wisconsin': 'WI',
'Wyoming': 'WY'
}
for arg in pywikibot.handleArgs():
if arg.startswith('-start:'):
start = arg[7:]
elif arg == '-force':
force = True
else:
pywikibot.output(
u'Warning: argument "%s" not understood; ignoring.' % arg)
mysite = pywikibot.getSite()
for p in mysite.allpages(start = start):
for sn in abbrev:
R=re.compile('[^[]]*' + '\%2C_' + sn)
for res in R.findall(p.title()):
pl=pywikibot.Page(mysite, p.title().replace(sn,abbrev[sn]))
# A bit hacking here - the real work is done in the
# 'except pywikibot.NoPage' part rather than the 'try'.
try:
goal = pl.getRedirectTarget().title()
if pywikibot.Page(mysite, goal):
pywikibot.output(
u"Not creating %s - redirect already exists."
% goal)
else:
pywikibot.output(
u"WARNING!!! %s already exists but redirects elsewhere!"
% goal)
except pywikibot.IsNotRedirectPage:
pywikibot.output(
u"WARNING!!! Page %s already exists and is not a redirect. Please check page!"
% goal)
except pywikibot.NoPage:
change=''
if p.isRedirectPage():
p2 = p.getRedirectTarget()
wikipeda.ouput(
u'Note: goal page is redirect. Creating redirect to "%s" to avoid double redirect.'
% p2.title().replace("%2C",",").replace("_"," "))
else:
p2 = p
if force:
change='y'
else:
while not change in ['y','n']:
pywikibot.output(
u"Create redirect %s" %
pl.title().replace("%2C",",").replace("_"," "))
change = raw_input("(y/n)? ")
if change=='y':
text = '#REDIRECT [['+p2.title().replace("%2C",",").replace("_"," ")+']]'
pl.put(text, comment=pywikibot.translate(mysite, msg),
minorEdit = '0')
def main():
args = wikipedia.handleArgs()
all = False
force = False
for currentArgument in args:
if currentArgument.startswith("-always"):
all = True
if currentArgument.startswith("-force"):
force = True
templateFile = codecs.open("modello_superenalotto.txt", "r", "utf-8")
modelloVoce = templateFile.read() # Legge il modello della pagina
templateFile.close()
now = datetime.datetime.utcnow()
urlo = "http://www.sisal.it/se/se_main/1,4136,se_Default,00.html"
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
numeri = re.search(
"<TABLE[^>]*>\s*<tr>\s*<td[^>]*>\s*<a[^>]*><nobr><font[^>]*>\s*(\d+) - \s*(\d+) - \s*(\d+) - \s*(\d+) - \s*(\d+) - \s*(\d+)\s*</font>\s*</nobr>\s*</a>\s*</td>\s*</tr>\s*</table>",
htmlText)
jolly = re.search(
"<td[^>]*background=\"/giochi/se2006/hp2009/img/BTN_JOLLY.gif\"[^>]*>\s*<a[^>]*><font[^>]*><b>(\d+)</b></font></a>\s*</td>",
htmlText)
superstar = re.search(
"<td[^>]*background=\"/giochi/se2006/hp2009/img/BTN_SUPERSTAR.gif\"[^>]*>\s*<a[^>]*><font[^>]*><b>(\d+)</b></font></a>\s*</td>",
htmlText)
concorso = re.search(
"<font[^>]*><font[^>]*><b>Concorso n. (\d+) di (.*?) (\d+)/(\d+)/(\d+)</b></font></a>",
htmlText)
montepremiparz = re.search(
"<td><a[^>]*><font class=testo8[^>]*>Del Concorso</a></td>\s*<td[^>]*><a[^>]*><font class=testo8[^>]*>(.*?) euro</font></a></td>",
htmlText)
jackpot = re.search(
"<td><a[^>]*><font class=testo8[^>]*>\s*Riporto Jackpot</a>\s*</td>\s*<td[^>]*><a[^>]*><font class=testo8[^>]*>(.*?) euro</font></a></td>",
htmlText)
montepremitot = re.search(
"<td><a[^>]*><font class=testo8[^>]*><b>Totale</a></td>\s*<td[^>]*><a[^>]*><font class=testo8[^>]*><b>(.*?) euro</font></a></td>",
htmlText)
bloccoQuote = "<tr[^>]*>\s*<td[^>]*><a[^>]*><font class=testo8[^>]*>(.*?)</font></a></td>\s*<td[^>]*><a[^>]*><font class=testo8[^>]*>"%s"</a></td>\s*<td[^>]*><a[^>]*><font class=testo8[^>]*>(.*?)</font></a></td>\s*</tr>"
page = wikipedia.Page(
wikipedia.getSite(code='it', fam='wikinews'), "Italia: concorso n. " +
concorso.group(1) + "/" + concorso.group(5) + " del SuperEnalotto")
if page.exists() and not force:
wikipedia.output("Nessuna nuova estrazione. Mi fermo.")
return
elencoSostituzioni = { # Sostituisce le variabili nel modello
'#super-id': concorso.group(1),
'#dow': concorso.group(2).replace('ì', u'ì'),
'#giorno': concorso.group(3),
'#mese': concorso.group(4),
'#anno': concorso.group(5),
'#num-1': numeri.group(1),
'#num-2': numeri.group(2),
'#num-3': numeri.group(3),
'#num-4': numeri.group(4),
'#num-5': numeri.group(5),
'#num-6': numeri.group(6),
'#num-jolly': jolly.group(1),
'#num-superstar': superstar.group(1),
'#montepremi-parz': montepremiparz.group(1),
'#jackpot': jackpot.group(1),
'#montepremi-tot': montepremitot.group(1),
}
quotes = [
'punti 6', 'punti 5\+', 'punti 5', 'punti 4', 'punti 3', '5 stella',
'4 stella', '3 stella', '2 stella', '1 stella', '0 stella'
]
for c in quotes:
match = re.search(bloccoQuote % c, htmlText)
elencoSostituzioni['#' + c.lower().replace(' ', '-') +
'#'] = match.group(2).replace('nessuna', '0')
elencoSostituzioni['#vincitori-' + c.lower().replace(' ', '-') +
'#'] = match.group(1).replace('nessuna', '0')
nuovoTesto = massiveReplace(elencoSostituzioni, modelloVoce)
#page = wikipedia.Page(wikipedia.getSite(code='it', fam='wikinews'), "Utente:BimBot/Sandbox") #DEBUG
wikipedia.output(">>>>> " + page.title() + " <<<<<")
try:
vecchioTesto = page.get()
except wikipedia.NoPage:
vecchioTesto = ''
wikipedia.showDiff(vecchioTesto, 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: Inserisco nuova estrazione del SuperEnalotto")
def __iter__(self):
tableTagR = re.compile('<table', re.IGNORECASE)
for entry in self.xmldump.parse():
if tableTagR.search(entry.text):
yield pywikibot.Page(pywikibot.getSite(), entry.title)
'fecha': fecha,
'titulo': titulo,
'textoexp': textoexp,
'titulosub': titulosub,
'textosub': textosub,
'asentimiento': asentimiento,
'presentes': presentes,
'afavor': afavor,
'encontra': encontra,
'abstenciones': abstenciones,
'novotan': novotan,
'votos': votos,
})
p = wikipedia.Page(
wikipedia.Site('15mpedia', '15mpedia'),
u'Lista de votaciones del Congreso de los Diputados/%s/Sesión %s/Votación %s'
% (legislatura, sesion, numerovotacion))
p.put(output,
u'BOT - Creando página de votación del Congreso de los Diputados')
votaciones = u''
votacionesids.sort()
for votacionid in votacionesids:
votaciones += u"""
=== Votación %s ===
{{main|Lista de votaciones del Congreso de los Diputados/%s/Sesión %s/Votación %s}}
{{:Lista de votaciones del Congreso de los Diputados/%s/Sesión %s/Votación %s}}
""" % (votacionid, legislatura, sesion, votacionid, legislatura, sesion,
votacionid)
output = string.Template(
wikipediaen=wikipedia.Site('en', 'wikipedia')
gen=pagegenerators.AllpagesPageGenerator(start=st, namespace=0, includeredirects=False, site=commons)
preloadingGen=pagegenerators.PreloadingGenerator(gen, pageNumber=100, lookahead=100)
for page in preloadingGen:
if page.isRedirectPage() or page.isDisambig():
continue
else:
if not getAllInterwikis(page.get()):
wtitle=page.title()
wtext=newtext=page.get()
summary="BOT -"
eniw=getEnglishInterwiki(newtext)
wikipedia.output("=== %s ===" % wtitle)
wikipedia.output("La galería NO tiene interwikis")
enpage=wikipedia.Page(ensite, wtitle)
if enpage.exists() and not enpage.isRedirectPage() and not enpage.isDisambig():
commonsimages=getImageTitles(wtitle, commonssite)
enimages=getImageTitles(wtitle, ensite)
for image in enimages:
if commonsimages.count(image)!=0: #con que una imagen coincida, ya vale
eniws=enpage.interwiki()
eniws.append(enpage)
eniws.sort()
iws_=""
for iw in eniws:
iws_+="[[%s:%s]]\n" % (iw.site().lang, iw.title())
page.put(u"%s\n\n%s" % (wtext, iws_), u"BOT - Adding %d interwiki(s) from [[:en:%s]]" % (len(eniws), enpage.title()))
break
continue
else:
def run(self):
tosend={'language':self.imagePage.site().language().encode('utf-8'),
'image':self.imagePage.titleWithoutNamespace().encode('utf-8'),
'newname':self.newname.encode('utf-8'),
'project':self.imagePage.site().family.name.encode('utf-8'),
'username':'',
'commonsense':'1',
'remove_categories':'1',
'ignorewarnings':'1',
'doit':'Uitvoeren'
}
tosend=urllib.urlencode(tosend)
print tosend
CH=pageTextPost('http://www.toolserver.org/~magnus/commonshelper.php', tosend)
print 'Got CH desc.'
tablock=CH.split('<textarea ')[1].split('>')[0]
CH=CH.split('<textarea '+tablock+'>')[1].split('</textarea>')[0]
CH=CH.replace(u'×', u'×')
CH = self.fixAuthor(CH)
pywikibot.output(CH);
# I want every picture to be tagged with the bottemplate so i can check my contributions later.
CH=u'\n\n{{BotMoveToCommons|'+ self.imagePage.site().language() + '.' + self.imagePage.site().family.name +'|year={{subst:CURRENTYEAR}}|month={{subst:CURRENTMONTHNAME}}|day={{subst:CURRENTDAY}}}}' + CH
if self.category:
CH = CH.replace(u'{{subst:Unc}} <!-- Remove this line once you have added categories -->', u'')
CH = CH + u'[[Category:' + self.category + u']]'
bot = UploadRobot(url=self.imagePage.fileUrl(), description=CH, useFilename=self.newname, keepFilename=True, verifyDescription=False, ignoreWarning = True, targetSite = pywikibot.getSite('commons', 'commons'))
bot.run()
#Should check if the image actually was uploaded
if pywikibot.Page(pywikibot.getSite('commons', 'commons'), u'Image:' + self.newname).exists():
#Get a fresh copy, force to get the page so we dont run into edit conflicts
imtxt=self.imagePage.get(force=True)
#Remove the move to commons templates
if self.imagePage.site().language() in moveToCommonsTemplate:
for moveTemplate in moveToCommonsTemplate[self.imagePage.site().language()]:
imtxt = re.sub(u'(?i)\{\{' + moveTemplate + u'[^\}]*\}\}', u'', imtxt)
#add {{NowCommons}}
if self.imagePage.site().language() in nowCommonsTemplate:
addTemplate = nowCommonsTemplate[self.imagePage.site().language()] % self.newname
else:
addTemplate = nowCommonsTemplate['_default'] % self.newname
if self.imagePage.site().language() in nowCommonsMessage:
commentText = nowCommonsMessage[self.imagePage.site().language()]
else:
commentText = nowCommonsMessage['_default']
pywikibot.showDiff(self.imagePage.get(), imtxt+addTemplate)
self.imagePage.put(imtxt + addTemplate, comment = commentText)
self.gen = pagegenerators.FileLinksGenerator(self.imagePage)
self.preloadingGen = pagegenerators.PreloadingGenerator(self.gen)
#If the image is uploaded under a different name, replace all instances
if self.imagePage.titleWithoutNamespace() != self.newname:
if self.imagePage.site().language() in imageMoveMessage:
moveSummary = imageMoveMessage[self.imagePage.site().language()] % (self.imagePage.titleWithoutNamespace(), self.newname)
else:
moveSummary = imageMoveMessage['_default'] % (self.imagePage.titleWithoutNamespace(), self.newname)
imagebot = ImageRobot(generator = self.preloadingGen, oldImage = self.imagePage.titleWithoutNamespace(), newImage = self.newname, summary = moveSummary, always = True, loose = True)
imagebot.run()
return
def __init__(self):
self.runOk = False
#Setup Familys for Wikia Involved
self.anime = wikipedia.getSite(code=u'en', fam=u'anime')
wikipedia.setAction(wikipedia.translate(self.anime, msg))
self.siteList = []
self.imageList = []
#Get Project Wiki Listing
wikiaIds = []
page = wikipedia.Page(self.anime, u'Bots/Wiki', None,
4) #4=Project Namespace
try:
text = page.get()
r = re.compile(u'^.*<!-- \|\|START\|\| -->\n?',
re.UNICODE | re.DOTALL)
text = re.sub(r, u'', text)
r = re.compile(u'\n?<!-- \|\|END\|\| -->.*$',
re.UNICODE | re.DOTALL)
text = re.sub(r, u'', text)
r = re.compile(u'\n', re.UNICODE | re.DOTALL)
wikilist = re.split(r, text)
r = re.compile(u'^#|^\s*$|^\[',
re.UNICODE | re.MULTILINE | re.DOTALL)
for wiki in wikilist:
if not re.match(r, wiki):
wikiaIds.append(wiki)
except wikipedia.NoPage:
return False
for wiki in wikiaIds:
self.siteList.append(wikipedia.getSite(code=u'en', fam=wiki))
#Get Image Info List
page = wikipedia.Page(self.anime, u'Bots/ImageMirror/Images', None,
4) #4=Project Namespace
try:
text = page.get()
r = re.compile(u'^.*<!-- \|\|START\|\| -->\n?',
re.UNICODE | re.DOTALL)
text = re.sub(r, u'', text)
r = re.compile(u'\n?<!-- \|\|END\|\| -->.*$',
re.UNICODE | re.DOTALL)
text = re.sub(r, u'', text)
r = re.compile(u'\n', re.UNICODE | re.DOTALL)
images = re.split(r, text)
r = re.compile(u'^#|^\s*$', re.UNICODE | re.MULTILINE | re.DOTALL)
for image in images:
if not re.match(r, image):
self.imageList.append(image)
except wikipedia.NoPage:
return False
self.runOk = True
#Mirror the Images category and all subcategorys to all the wiki.
ImageCategorys = []
cat = catlib.Category(self.anime, u'Category:Images')
ImageCategorys.append(cat)
catlist = cat.subcategories(True)
for category in catlist:
ImageCategorys.append(category)
for category in ImageCategorys:
categorySource = u'{{networkMirror|%s|anime|category}}\n%s' % (
category.title(), category.get())
if categorySource != u'':
for site in self.siteList:
siteCategory = catlib.Category(site, category.title())
siteSource = u''
try:
siteSource = siteCategory.get()
except wikipedia.NoPage:
wikipedia.output(
u'Site %s has no %s category, creating it' %
(site, category.title()))
if siteSource != categorySource:
wikipedia.output(
u'Site \'%s\' category status: Needs Updating' %
site)
wikipedia.output(u'Updating category on %s' % site)
siteCategory.put(categorySource)
else:
wikipedia.output(u'Site \'%s\' category status: Ok' %
site)
else:
wikipedia.output(u'Category %s is blank, skipping category' %
category.title())
#Anime should only be in the list after categorys have been done.
self.siteList.append(self.anime)
def main(args):
generator = None;
#newname = "";
imagepage = None;
always = False
category = u''
# Load a lot of default generators
genFactory = pagegenerators.GeneratorFactory()
for arg in pywikibot.handleArgs():
if arg == '-always':
always = True
elif arg.startswith('-cc:'):
category = arg [len('-cc:'):]
else:
genFactory.handleArg(arg)
generator = genFactory.getCombinedGenerator()
if not generator:
raise add_text.NoEnoughData('You have to specify the generator you want to use for the script!')
pregenerator = pagegenerators.PreloadingGenerator(generator)
for page in pregenerator:
skip = False
if page.exists() and (page.namespace() == 6) and (not page.isRedirectPage()) :
imagepage = pywikibot.ImagePage(page.site(), page.title())
#First do autoskip.
if doiskip(imagepage.get()):
pywikibot.output("Skipping " + page.title())
skip = True
else:
# The first upload is last in the list.
try:
username = imagepage.getLatestUploader()[0]
except NotImplementedError:
#No API, using the page file instead
(datetime, username, resolution, size, comment) = imagepage.getFileVersionHistory().pop()
if always:
newname=imagepage.titleWithoutNamespace()
CommonsPage=pywikibot.Page(pywikibot.getSite('commons', 'commons'), u'File:'+newname)
if CommonsPage.exists():
skip = True
else:
while True:
# Do the Tkdialog to accept/reject and change te name
(newname, skip)=Tkdialog(imagepage.titleWithoutNamespace(), imagepage.get(), username, imagepage.permalink(), imagepage.templates()).getnewname()
if skip:
pywikibot.output('Skipping this image')
break
# Did we enter a new name?
if len(newname)==0:
#Take the old name
newname=imagepage.titleWithoutNamespace()
else:
newname = newname.decode('utf-8')
# Check if the image already exists
CommonsPage=pywikibot.Page(
pywikibot.getSite('commons', 'commons'),
u'File:'+newname)
if not CommonsPage.exists():
break
else:
pywikibot.output('Image already exists, pick another name or skip this image')
# We dont overwrite images, pick another name, go to the start of the loop
if not skip:
imageTransfer(imagepage, newname, category).start()
pywikibot.output(u'Still ' + str(threading.activeCount()) + u' active threads, lets wait')
for openthread in threading.enumerate():
if openthread != threading.currentThread():
openthread.join()
pywikibot.output(u'All threads are done')
def main():
# Load the configurations in the function namespace
global commento
global Template
global disambigPage
global commenttodisambig
global exception
enablePage = None # Check if someone set an enablePage or not
limit = 50000 # All the pages! (I hope that there aren't so many lonely pages in a project..)
generator = None # Check if the bot should use the default generator or not
genFactory = pagegenerators.GeneratorFactory(
) # Load all the default generators!
nwpages = False # Check variable for newpages
always = False # Check variable for always
disambigPage = None # If no disambigPage given, not use it.
# Arguments!
for arg in wikipedia.handleArgs():
if arg.startswith('-enable'):
if len(arg) == 7:
enablePage = wikipedia.input(
u'Would you like to check if the bot should run or not?')
else:
enablePage = arg[8:]
if arg.startswith('-disambig'):
if len(arg) == 9:
disambigPage = wikipedia.input(
u'In which page should the bot save the disambig pages?')
else:
disambigPage = arg[10:]
elif arg.startswith('-limit'):
if len(arg) == 6:
limit = int(
wikipedia.input(u'How many pages do you want to check?'))
else:
limit = int(arg[7:])
elif arg.startswith('-newpages'):
if len(arg) == 9:
nwlimit = 50 # Default: 50 pages
else:
nwlimit = int(arg[10:])
generator = wikipedia.getSite().newpages(number=nwlimit)
nwpages = True
elif arg == '-always':
always = True
else:
genFactory.handleArg(arg)
# Retrive the site
wikiSite = wikipedia.getSite()
if not generator:
generator = genFactory.getCombinedGenerator()
# If the generator is not given, use the default one
if not generator:
generator = wikiSite.lonelypages(repeat=True, number=limit)
# Take the configurations according to our project
comment = wikipedia.translate(wikiSite, commento)
commentdisambig = wikipedia.translate(wikiSite, commenttodisambig)
template = wikipedia.translate(wikiSite, Template)
exception = wikipedia.translate(wikiSite, exception)
# EnablePage part
if enablePage != None:
# Define the Page Object
enable = wikipedia.Page(wikiSite, enablePage)
# Loading the page's data
try:
getenable = enable.get()
except wikipedia.NoPage:
wikipedia.output(
u"%s doesn't esist, I use the page as if it was blank!" %
enable.title())
getenable = ''
except wikiepedia.IsRedirect:
wikipedia.output(u"%s is a redirect, skip!" % enable.title())
getenable = ''
# If the enable page is set to disable, turn off the bot
# (useful when the bot is run on a server)
if getenable != 'enable':
wikipedia.output('The bot is disabled')
return
# DisambigPage part
if disambigPage != None:
disambigpage = wikipedia.Page(wikiSite, disambigPage)
try:
disambigtext = disambigpage.get()
except wikipedia.NoPage:
wikipedia.output(u"%s doesn't esist, skip!" % disambigpage.title())
disambigtext = ''
except wikiepedia.IsRedirect:
wikipedia.output(u"%s is a redirect, don't use it!" %
disambigpage.title())
disambigPage = None
# Main Loop
for page in generator:
if nwpages == True:
page = page[
0] # The newpages generator returns a tuple, not a Page object.
wikipedia.output(u"Checking %s..." % page.title())
# Used to skip the first pages in test phase...
#if page.title()[0] in ['A', 'B', 'C', 'D', 'E', 'F', 'G', 'H', 'I', 'J', 'K', 'L', 'M', 'N', 'O', 'P', 'Q']:
#continue
if page.isRedirectPage(): # If redirect, skip!
wikipedia.output(u'%s is a redirect! Skip...' % page.title())
continue
# refs is not a list, it's a generator while resList... is a list, yes.
refs = page.getReferences()
refsList = list()
for j in refs:
if j == None:
# We have to find out why the function returns that value
wikipedia.output(u'Error: 1 --> Skip page')
continue
refsList.append(j)
# This isn't possible with a generator
if refsList != []:
wikipedia.output(u"%s isn't orphan! Skip..." % page.title())
continue
# Never understood how a list can turn in "None", but it happened :-S
elif refsList == None:
# We have to find out why the function returns that value
wikipedia.output(u'Error: 2 --> Skip page')
continue
else:
# Ok, no refs, no redirect... let's check if there's already the template
try:
oldtxt = page.get()
except wikipedia.NoPage:
wikipedia.output(u"%s doesn't exist! Skip..." % page.title())
continue
except wikipedia.IsRedirectPage:
wikipedia.output(u"%s is a redirect! Skip..." % page.title())
continue
# I've used a loop in a loop. If I use continue in the second loop, it won't do anything
# in the first. So let's create a variable to avoid this problem.
Find = False
for regexp in exception:
res = re.findall(regexp, oldtxt.lower())
# Found a template! Let's skip the page!
if res != []:
wikipedia.output(
u'Your regex has found something in %s, skipping...' %
page.title())
Find = True
break
# Skip the page..
if Find:
continue
# Is the page a disambig?
if page.isDisambig() and disambigPage != None:
wikipedia.output(u'%s is a disambig page, report..' %
page.title())
if not page.title().lower() in disambigtext.lower():
disambigtext = u"%s\n*[[%s]]" % (disambigtext,
page.title())
disambigpage.put(disambigtext, commentdisambig)
continue
# Is the page a disambig but there's not disambigPage? Skip!
elif page.isDisambig():
wikipedia.output(u'%s is a disambig page, skip...' %
page.title())
continue
else:
# Ok, the page need the template. Let's put it there!
newtxt = u"%s\n%s" % (template, oldtxt
) # Adding the template in the text
wikipedia.output(u"\t\t>>> %s <<<" %
page.title()) # Showing the title
wikipedia.showDiff(oldtxt, newtxt) # Showing the changes
choice = 'y' # Default answer
if not always:
choice = wikipedia.inputChoice(
u'Orphan page found, shall I add the template?',
['Yes', 'No', 'All'], ['y', 'n', 'a'])
if choice == 'a':
always = True
choice = 'y'
if choice == 'y':
try:
page.put(newtxt, comment)
except wikipedia.EditConflict:
wikipedia.output(u'Edit Conflict! Skip...')
continue
import os
import wikipedia
import re
import datetime
commonssite=wikipedia.Site("commons", "commons")
username="******"
password=""
f=open("/home/emijrp/.my.cnf2", "r")
raw=f.read()
f.close()
m=re.findall(ur'%s = *"(.*)"' % username, raw)
password=m[0]
today=datetime.date.today()
page=wikipedia.Page(commonssite, u"Template:Potd/%s" % today.isoformat())
m=re.findall(ur'(?i)\{\{ *potd filename *\| *1? *=? *([^\|]*?) *\|', page.get())
imagename=m[0]
page=wikipedia.Page(commonssite, u"Template:Potd/%s (en)" % today.isoformat())
m=re.findall(ur'(?i)\{\{ *potd description *\| *1? *=? *(.*?) *\| *2? *=? *en *\|', page.get())
imagedesc=m[0]
imagedesc=re.sub(ur'(?i)\[\[([^\|]*?)\|(?P<label>[^\]]*?)\]\]', ur'\g<label>', imagedesc)
imagedesc=re.sub(ur'(?i)[\[\]]', ur'', imagedesc)
if len(imagedesc)>40:
imagedesc=u'%s...' % (imagedesc[:40])
imagename_=re.sub(" ", "_", imagename)
msg=u'%s → http://commons.wikimedia.org/wiki/File:%s #commons #photos #wikipedia' % (imagedesc, imagename_)
orden='curl -u %s:%s -d status="%s" http://twitter.com/statuses/update.json' % (username, password, msg.encode("utf-8"))
os.system(orden)
u'eilimit': 'max',
u'format': 'json'
}
counts, destmap, catmap = {}, {}, {}
catlist, catpages, nonemptypages = [], [], []
target = self.cat_redirect_cat[self.site.family.name][self.site.lang]
# get a list of all members of the category-redirect category
for result in self.query_results(
generator=u'categorymembers',
gcmtitle=target,
gcmnamespace=u'14', # CATEGORY
gcmlimit=u'max',
prop='info|categoryinfo'):
for catdata in result['pages'].values():
thispage = pywikibot.Page(self.site, catdata['title'])
catpages.append(thispage)
if 'categoryinfo' in catdata \
and catdata['categoryinfo']['size'] != "0":
# save those categories that have contents
nonemptypages.append(thispage)
# preload the category pages for redirected categories
pywikibot.output(u"")
pywikibot.output(u"Preloading %s category redirect pages" %
len(catpages))
for cat in pagegenerators.PreloadingGenerator(catpages, 120):
cat_title = cat.titleWithoutNamespace()
if "category redirect" in cat_title:
self.log_text.append(u"* Ignoring %s" %
cat.title(asLink=True, textlink=True))
def run(self):
wikipedia.setAction(u'Robot: hardware import')
page = wikipedia.Page(wikipedia.getSite(), self.name)
tmpl = """{{MODEL|
|NAME=
|LOCATION=
|OWNER=
|SN=
|PN=
|OOBIP=
|OOBMAC=
|RPSUSED=1
|NICUSED=2
|NIC1=eth0
|NIC2=eth1
|NICMAC1=
|NICMAC2=
|CPUUSED=2x UnknownCPU
|RAMUSED=2x UnknownMB
|DISKSUSED=2x 146GB
|CONTRACT=
}}
{{Instance
|USAGE=[[OpenVZ HN]]
|OS=lenny
|ARCH=x86_64
|AUTH=ldap
|LDAPGROUP=hostgroup-admin-ssh
|ETH=
}}
"""
lines = list()
oldlines = tmpl.split("\n")
data = self.fetchIloData(self.ip)
print data
# now replace the values
for line in oldlines:
if line.startswith("{{MODEL"):
line = "{{HP_" + data['productname'].replace(
'ProLiant', '').replace(' ', '_') + '|'
if line.startswith("|NAME"): line = "|NAME=" + self.name
if line.startswith("|OOBIP"): line = "|OOBIP=" + self.ip
if line.startswith("|LOCATION"):
line = "|LOCATION=" + (
'%s-%s' %
(self.name.split('-')[0], self.name.split('-')[1]))
if line.startswith("|SN=") and data.has_key('serialnumber'):
line = "|SN=" + data['serialnumber']
del data['serialnumber']
if line.startswith("|PN=") and data.has_key('skunumber'):
line = "|PN=" + data['skunumber']
del data['skunumber']
if line.startswith("|OOBMAC") and data.has_key('oobmac'):
line = "|OOBMAC=" + data['oobmac']
del data['oobmac']
if line.startswith("|RPSUSED") and data.has_key('rpsused'):
line = "|RPSUSED=" + str(data['rpsused'])
del data['rpsused']
if line.startswith("|NICMAC1") and data.has_key('nicmac1'):
line = "|NICMAC1=" + str(data['nicmac1'])
del data['nicmac1']
if line.startswith("|NICMAC2") and data.has_key('nicmac2'):
line = "|NICMAC2=" + str(data['nicmac2'])
del data['nicmac2']
if line.startswith("}}"):
# hardware template is over, ensure that no other changes are made
data = dict()
lines.append(line)
pagetext = "\r\n".join(lines)
# Save the page
try:
page.put(pagetext)
except wikipedia.LockedPage:
wikipedia.output(u"Page %s is locked; skipping." % page.aslink())
except wikipedia.EditConflict:
wikipedia.output(u'Skipping %s because of edit conflict' %
(page.title()))
except wikipedia.SpamfilterError, error:
wikipedia.output(
u'Cannot change %s because of spam blacklist entry %s' %
(page.title(), error.url))
