def filter_titles(self):
i = 0
titles = []
if self.lang_key:
path = join(conf.PARSED_STORAGE_PATH, 'lists', 'langs', 'articles')
all_titles = read_lines(f'{path}/{self.lang_key}.txt',
ignore_absent=True)
else:
all_titles = storage.load_articles()
for title in all_titles:
if re.fullmatch(self.regexp, title):
if i // self.page_size > self.page:
self.more = True
break
if i // self.page_size == self.page:
titles.append(title)
i += 1
return titles
def iterate_daily_logs(self, slug, start_from):
logs_path = join(self.logs_path, slug)
curr_date = start_from.date() - timedelta(days=1)
while curr_date <= datetime.now().date():
curr_date += timedelta(days=1)
path = f"{logs_path}/{dtf('Ym/Ymd', curr_date)}.txt"
if not exists(path):
# todo: log something?
continue
lines = read_lines(path)
for line in lines:
if not line:
continue
if not re.match('\d{4}-\d\d-\d\d \d\d:\d\d:\d\d: ', line):
raise ImpossibleError('Wrong log format')
log_dt = dtp(line[:19])
if log_dt < start_from:
continue
yield log_dt, line[21:]
def get(cls):
return set(read_lines(cls.filename))
def load_titles(self):
return read_lines(self.titles_filename)