def _parse_date_from_text(self, year: str, text: str) -> str:
"""Get date from relevant element."""
match = re.search(self.regex["date"], text)
if not match:
return None
month_day = match.group(1)
return clean_date(f"{month_day} {year}", "%B %d %Y")
def _parse_data(self, data):
data = [{
"date":
clean_date(f"{d['year']}-{d['month']}-{d['day']}", "%Y-%m-%d"),
"total_vaccinations":
d.get("usedToDate"),
"people_vaccinated":
d["administered"].get("toDate"),
"people_fully_vaccinated":
d["administered2nd"].get("toDate"),
"total_boosters":
d["administered3rd"].get("toDate"),
"vaccine":
self._build_vaccine_str(d),
} for d in data]
df = pd.DataFrame(data)
return df
def _build_df(self, data):
# Get dates
dt = clean_date(data["fecha_inicial"],
"%Y-%m-%dT%H:%M:%S%z",
as_datetime=False)
dates = pd.date_range(dt, periods=data["dias"], freq="D")
# Build df
# Notes on differences adicional vs refuerzo:
# https://github.com/owid/covid-19-data/issues/2532#issuecomment-1074137207
df = pd.DataFrame({
"date": clean_date_series(list(dates)),
"vaccine": data["denominacion"],
"dose_1": data["dosis1"],
"dose_2": data["dosis2"],
"dose_additional": data["adicional"],
"people_fully_vaccinated": data["esquemacompleto"],
"total_boosters": data["refuerzo"],
})
return df
def _build_df_age_group(self, data):
# Get dates
dt = clean_date(data["fecha_inicial"],
"%Y-%m-%dT%H:%M:%S%z",
as_datetime=False)
dates = pd.date_range(dt, periods=data["dias"], freq="D")
# Build df
df = pd.DataFrame({
"date": dates,
"people_vaccinated": data["dosis1"],
"people_fully_vaccinated": data["esquemacompleto"],
# "people_with_booster": [d + b for d, b in zip(data["refuerzo"], data["adicional"])],
"people_with_booster": data[
"refuerzo"], # likely an under estimate (missing doses for immunocompromised)
}).assign(
**{
"age_group_min":
data["desdeedad"],
"age_group_max":
data["hastaedad"] if data["hastaedad"] is not None else "",
"age_group":
data["denominacion"],
})
return df
def _parse_date(self, t_scraper: TableauScraper) -> str:
"""Parse date from TableauScraper"""
date = t_scraper.getWorksheet("COVID-19 | Prensa.Titulo").data.iat[0,
0]
return clean_date(date, "%d/%m/%Y")
def _parse_date(self, soup: BeautifulSoup) -> str:
"""Parse date from soup"""
date = soup.find("p").text.lower()
return clean_date(date, "As of %B %d, %Y")
def _parse_date(self, soup: BeautifulSoup) -> str:
"""Parse date from soup"""
date = soup.find(text=re.compile(self.regex["date"]))
return clean_date(date, "%d.%m.%Yг.")
