def _parse_date(self, text: str):
thai_date_replace = {
# Months
"มกราคม": 1,
"กุมภาพันธ์": 2,
"มีนาคม": 3,
"เมษายน": 4,
"พฤษภาคม": 5,
"พฤษภำคม": 5,
"มิถุนายน": 6,
"มิถุนำยน": 6,
"กรกฎาคม": 7,
"กรกฎำคม": 7,
"สิงหาคม": 8,
"สิงหำคม": 8,
"กันยายน": 9,
"ตุลาคม": 10,
"พฤศจิกายน": 11,
"ธันวาคม": 12,
}
date_raw = re.search(self.regex_date, text)
day = clean_count(date_raw.group(1))
month = thai_date_replace[date_raw.group(2)]
year = clean_count(date_raw.group(3)) - self._year_difference_conversion
return clean_date(datetime(year, month, day))
def pipe_date(self, df: pd.DataFrame) -> pd.DataFrame:
dt = pd.to_datetime(df.week, format=DATE_FORMAT)
dt = dt + timedelta(days=14)
last_update = self._parse_last_update_date
dt = dt.apply(
lambda x: clean_date(min(x.date(), last_update), DATE_FORMAT))
df = df.assign(date=dt, )
return df.drop(columns=["week"])
def _propose_df(self):
regex = r"Comunicado N° (\d{3,4}).*"
data = []
for tweet in self.tweets:
match = re.search(regex, tweet.full_text)
if match:
dt = clean_date(
from_tz_to_tz(tweet.created_at, to_tz="America/Panama"))
if self.stop_search(dt):
break
data.append({
"date": dt,
"text": tweet.full_text,
"source_url": self.build_post_url(tweet.id),
"num": match.group(1),
})
self.tweets_relevant.append(tweet)
df = pd.DataFrame(data)
df = df.drop_duplicates(subset=["num"], keep="last")
return df
def _weekday_to_date(self, d):
new_date = clean_date(d + "+5", "%Y-W%W+%w")
if new_date > localdate("Europe/London"):
new_date = clean_date(d + "+2", "%Y-W%W+%w")
return new_date
def date_limit_one_dose_ddmmyyyy(self):
return clean_date(self.date_limit_one_dose,
"%Y-%m-%d",
output_fmt="%d%m%Y")
def _get_num_gap_days(self, df_current):
return (localdatenow(tz=None, as_datetime=True) - clean_date(
df_current.date.max(), "%Y-%m-%d", as_datetime=True)).days
def _parse_date_from_link_title(self, title):
match = re.search(r".*สรุปวัคซีน ประจำวันที่\s+(\d+) .* (25\d\d)", title).group(1, 2)
year = int(match[1]) - self._year_difference_conversion
return clean_date(f"{year}-{self._current_month}-{match[0]}", "%Y-%m-%d")
def _week_to_date(self, week: int) -> str:
"""Converts week to date."""
year = localdate("Asia/Amman", as_datetime=True).isocalendar().year
date = clean_date(f"{year} {week} +5", "%Y %W +%w")
return date