వాడుకరి:Mpradeepbot/mpc.villageCreate.py
ఈ ప్రోగ్రాముకు సహాకారిగా ఈ ఫైలును కూడా వాడండి.
import wikipedia, pagegenerators, catlib, config, codecs, time
# This function returns the list of articles as a list object
# in given category. Please give only the Category Name,
# namespace will be addd automatically.
# --function requires both 'wikipedia' and 'catlib' to be imported
def getCatList(catTitle):
cat = catlib.Category(wikipedia.getSite(), u'Category:'+catTitle)
listOfArticles = cat.articles()
return listOfArticles
def doReplacements(oText, en_list, te_list):
nText = oText
if len(en_list) != len(te_list):
wikipedia.output(u'length of the lists do not match.')
return oText
count = len(en_list)
i = 0
while i < count:
nText = nText.replace(en_list[i], te_list[i])
i = i + 1
return nText
def createSubPages(otext, hDes, mainContent, disambigTemplate, reviewTemplate, comments, mTitle):
en_list = []
en_list.append(u'gggg')
en_list.append(u'mmmm')
en_list.append(u'jjjj')
diff = 0
lines = otext.splitlines()
newpages = (len(lines) + 1) / 3;
ntext = u''
# number of line did not match the pattern
if ((len(lines) - 2) % 3) != 0:
return otext
# number of reviewTemplates did not match the pattern
if (newpages-1) != otext.count(reviewTemplate):
return otext
print '%d new pages are being created' % newpages
logfile.write(u'* [[' + mTitle + u']]\r\n')
site = wikipedia.getSite()
i = 0
while i < newpages:
next = lines[i*3].find('\'\'\'',3)
if i == 0:
gggg = lines[i][3:next]
mmmm = lines[i*3-diff][lines[i*3-diff].rfind('[[')+2:lines[i*3-diff].rfind(']]')]
mmmm = mmmm.split(' (')[0].split('(')[0].split(' ,')[0].split(',')[0]
temp = mmmm.split('|')
if len(temp) > 1:
mmmm = temp[1]
jjjj = lines[i*3-diff][lines[i*3-diff].find('[[')+2:lines[i*3-diff].find(']]')]
jjjj = jjjj.split(' (')[0].split('(')[0].split(' ,')[0].split(',')[0]
temp = jjjj.split('|')
if len(temp) > 1:
jjjj = temp[1]
te_list = []
te_list.append(gggg)
te_list.append(mmmm)
te_list.append(jjjj)
if i == 0:
ntext = doReplacements(hDes, en_list, te_list) + u'\r\n'
ntext = ntext + u'\r\n' + doReplacements(mainContent, en_list, te_list)
gPageTitle = u'' + gggg + u' (' + mmmm + u')'
logfile.write(u'** [[' + gPageTitle + u']]')
gPageContents = u'' + lines[i*3-diff] + u'\r\n' + lines[i*3-diff+1] + u'\r\n'
# logfile.write(u'' + gPageContents + u'\r\n')
# creating stub pages.
page = wikipedia.Page(site, gPageTitle)
try:
old = page.get()
if not page.canBeEdited():
logfile.write(u' - page exists and locked, should contain \r\n' + gPageContents + u'\r\n')
old = u'abcd'
except wikipedia.IsRedirectPage:
logfile.write(u' - page exists and is redirect, should contain \r\n' + gPageContents + u'\r\n')
old = u'abcd'
except wikipedia.NoPage:
old = u''
if old != '':
logfile.write(u' - page exists, should contain \r\n' + gPageContents + u'\r\n')
else:
logfile.write(u'\r\n')
try:
page.put(gPageContents, comment = comments)
except wikipedia.EditConflict:
logfile.write(u'Skipping [[%s]] because of edit conflict\r\n' % (page.title()))
except wikipedia.SpamfilterError, url:
logfile.write(u'Cannot change [[%s]] because of blacklist entry %s\r\n' % (page.title(), url))
if i == newpages - 1:
ntext = ntext + u'\r\n\r\n' + disambigTemplate
if i == 0:
diff = 1
i = i + 1
return ntext
logfile = codecs.open('mpc.villageCreate.log', encoding='utf-8', mode='wb')
replaceFile = open('mpc.villageCreate.txt', 'rb' )
#omit 3 characters if it is UTF-8
replaceFile.read(3)
commentDis = u"" + unicode(replaceFile.readline(), 'utf8')
commentVil = u"" + unicode(replaceFile.readline(), 'utf8')
# read category
line = u"" + unicode(replaceFile.readline(), 'utf8')
line = line.replace(u'\n', u'')
line = line.replace(u'\r', u'')
villageCategory = line
# read header description
line = u"" + unicode(replaceFile.readline(), 'utf8')
line = line.replace(u'\n', u'')
line = line.replace(u'\r', u'')
headerDescription = line
# read main content line
line = u"" + unicode(replaceFile.readline(), 'utf8')
line = line.replace(u'\n', u'')
line = line.replace(u'\r', u'')
mainContent = line
# read Disambiguation Template line
line = u"" + unicode(replaceFile.readline(), 'utf8')
line = line.replace(u'\n', u'')
line = line.replace(u'\r', u'')
disambigTemplate = line
# read Review Template line
line = u"" + unicode(replaceFile.readline(), 'utf8')
line = line.replace(u'\n', u'')
line = line.replace(u'\r', u'')
reviewTemplate = line
pageList = getCatList(villageCategory)
for page in pageList:
#get the page from wikipedia
try:
# Load the page's text from the wiki
original_text = page.get()
if not page.canBeEdited():
logfile.write(u'* Skipping locked page [[%s]]\r\n' % page.title())
continue
except wikipedia.NoPage:
logfile.write(u'* Page [[%s]] not found\r\n' % page.title())
continue
except wikipedia.IsRedirectPage:
original_text = page.get(get_redirect=True)
new_text = createSubPages(original_text, headerDescription, mainContent, disambigTemplate, reviewTemplate, commentVil, page.title())
if new_text == original_text:
logfile.write(u'* No changes were necessary in %s\r\n' % page.title())
continue
else:
# logfile.write(u'* modified [[' + page.title() + u']]\r\n')
# logfile.write(u'' + new_text + u'\r\n')
# Show the title of the page where the link was found.
# Highlight the title in purple.
colors = [None] * 5 + [13] * len(page.title()) + [None] * 4
wikipedia.output(u'\n>>> %s <<<' % page.title(), colors = colors)
wikipedia.showDiff(original_text, new_text)
try:
page.put(new_text, comment = commentDis)
except wikipedia.EditConflict:
logfile.write(u'Skipping [[%s]] because of edit conflict\r\n' % (page.title()))
except wikipedia.SpamfilterError, url:
logfile.write(u'Cannot change [[%s]] because of blacklist entry %s\r\n' % (page.title(), url))
print 'Completed modifing, Sleeping for 20 seconds...'
time.sleep(10)
logfile.close()
replaceFile.close()