class ReplicsCounter():
def __init__(self):
self.cache = Storage()
self.cache.create("articles", \
{"oldid":"INT UNIQUE", "name":"TEXT", "ts":"DATE", "replics": "INT"})
def countPage(self, page):
"""Counts repics at AFI page"""
sections = {}
sect = None
n = -1 # one line for header
for s in page.getSections():
if sect != None:
sections[sect] = (n, s[0])
sect = s[3]
n = s[0]
sections[sect] = (n, len(page.get())) # last one
for s in sections:
replics = -1 # one for header
text = page.get()[sections[s][0]:sections[s][1]].splitlines()
for line in text:
sline = line.strip()
if (len(sline) > 2):
if sline[:2] != "{{" and sline[:-2] != "}}":
replics += 1
#print "%s %s" % (replics, line)
wikipedia.output( u"%s %s %s" % (s, sections[s], replics))
self.cache.execute(u'UPDATE articles SET replics = %s WHERE name = "%s";' % (replics, self.cache.quote(s)))
def countCat(self, catname):
cat = catlib.Category(wikipedia.getSite(), catname)
for page in cat.articles():
print page
self.countPage(page)
def replicsPage(self, pagename):
r = self.cache.findone('articles', {"name":pagename}, what = ["replics"])
if r == None:
return "-"
else:
return r[0]
class AllAFI:
"""module for AFI stats update"""
def __init__(self, action):
self.action = action
self.site = wikipedia.getSite()
self.afi = catlib.Category(self.site, \
u'Категория:Википедия:Статьи для срочного улучшения')
self.afi_list = []
self.afi_list_title = []
self.cache = Storage()
def load_all(self):
"""Loads all articles for improvement to sqlite table"""
self.cache.create('category', {'name':'TEXT', 'cat':'TEXT'})
self.cache.delete('category')
self.afi_list = self.afi.articlesList()
self.afi_list_title = [self.cache.quote(_.title(withNamespace=False)) for _ in self.afi.articlesList()]
for a in self.afi_list:
wikipedia.output(a)
for cat in a.categories():
self.cache.insert('category', (a.title(withNamespace=False), cat.title(withNamespace=False)))
# now clear articles table from non-actual articles
re = self.cache.cursor.execute(u"SELECT name FROM articles;")
for l in re.fetchall():
if l[0] not in self.afi_list_title:
wikipedia.output(l[0])
self.cache.delete('articles', {'name':l[0]})
def update_stats(self):
"""prints stats to wikipedia page"""
text = ""
n1 = self.cache.cursor.execute("SELECT count(DISTINCT name) FROM category;").fetchone()[0]
n2 = self.cache.cursor.execute("SELECT count(*) FROM articles;").fetchone()[0]
text += u"Всего статей на КУЛ: '''%s''', статей в базе бота '''%s''' \r\n" % (n1, n2)
re = self.cache.cursor.execute("SELECT cat, count(*) AS c FROM category GROUP BY cat HAVING c>10 ORDER BY c DESC;")
text += u"== Топ категорий <ref>Категории, в которых более 10 статей на улучшении, количество статей указано в скобках</ref> == \r\n"
for l in re.fetchall():
text += u"* [[:Категория:%s|]]: (%s) \r\n" % l
text += u"== Самые старые статьи <ref>Учитывается самая первая номинация КУЛ</ref> == \r\n"
re = self.cache.cursor.execute(u"SELECT name, ts FROM articles ORDER BY ts limit 20;")
for l in re.fetchall():
text += u"* [[%s]] (%s) \r\n" % l
re = self.cache.cursor.execute("SELECT count(*), replics FROM articles GROUP BY replics;")
text += u"== По количеству реплик == \r\n"
for l in re.fetchall():
text += u"* Обсуждения %s статей имеют %s реплик\r\n" % (l)
re = self.cache.cursor.execute("SELECT topic, topic, n, ts FROM updates ORDER BY n DESC;")
text += u"== Последние обновления == \r\n"
for l in re.fetchall():
text += u"* [[Википедия:К улучшению/Тематические обсуждения/%s|%s]]: (Статей %s, обновлена %s) \r\n" % (l)
text += u"== Примечания ==\r\n{{примечания}}"
P = wikipedia.Page(self.site, u"Википедия:К улучшению/Тематические обсуждения/Статистика")
P.put(text, u"Обновление статистики", botflag = True)
def run(self):
"""entry point"""
if self.action == "all":
self.load_all()
self.update_stats()
