def parse_vaccinated(self, soup):
regex = r"De los ([\d\.]+) vacunados un total de ([\d\.]+) \(([\d\.]+)%\) ya han recibido la 2ª dosis"
match = re.search(regex, soup.text)
people_vaccinated = match.group(1)
people_fully_vaccinated = match.group(2)
return clean_count(people_vaccinated), clean_count(
people_fully_vaccinated)
def parse_data(soup: BeautifulSoup) -> pd.Series:
# regex = (
# r"So far, ([\d,]+) \(([\d,]+)% of the estimated population of 65,000\) have received at least one dose of a"
# r" COVID-19 vaccine, with ([\d,]+)% having completed the two-dose course"
# )
# matches = re.search(regex, soup.text)
# people_vaccinated = clean_count(matches.group(1))
# proportion_dose1 = clean_count(matches.group(2))
# proportion_dose2 = clean_count(matches.group(3))
# assert proportion_dose1 >= proportion_dose2
# people_fully_vaccinated = round(people_vaccinated * proportion_dose2 / proportion_dose1)
# total_vaccinations = people_vaccinated + people_fully_vaccinated
regex_1 = (
r"There have been ([\d,]+) Covid-19 vaccinations given in total in the Cayman Islands."
)
total_vaccinations = clean_count(re.search(regex_1, soup.text).group(1))
regex_2 = (
r"Of these, ([\d,]+) \(([\d,]+)% of (?:[a-zA-Z0-9,]+)\) have had at least one dose of a COVID-19 "
r"vaccine and ([\d,]+)% have completed the two dose course.")
matches = re.search(regex_2, soup.text)
people_vaccinated = clean_count(matches.group(1))
proportion_dose1 = clean_count(matches.group(2))
proportion_dose2 = clean_count(matches.group(3))
assert proportion_dose1 >= proportion_dose2
people_fully_vaccinated = round(total_vaccinations * proportion_dose2 /
100)
return pd.Series({
"total_vaccinations": total_vaccinations,
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated,
})
def parse_data(soup: BeautifulSoup) -> pd.Series:
people_vaccinated = clean_count(
soup
.find(class_="status_infoArea")
.find(class_="round1")
.find(class_="big")
.text
)
people_fully_vaccinated = clean_count(
soup
.find(class_="status_infoArea")
.find(class_="round2")
.find(class_="big")
.text
)
total_vaccinations = people_vaccinated + people_fully_vaccinated
date = str((datetime.datetime.now(pytz.timezone("Asia/Seoul")) - datetime.timedelta(days=1)).date())
data = {
"date": date,
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated,
"total_vaccinations": total_vaccinations,
}
return pd.Series(data=data)
def connect_parse_data(source: str, source_old: str) -> pd.Series:
op = Options()
op.add_argument("--headless")
with webdriver.Chrome(options=op) as driver:
driver.get(source)
time.sleep(5)
total_vaccinations = driver.find_element_by_id("counter1").text
people_vaccinated = driver.find_element_by_id("counter2").text
people_fully_vaccinated = driver.find_element_by_id("counter3").text
driver.get(source_old)
time.sleep(5)
# Sanity check
total_vaccinations_old = driver.find_element_by_id("counter1").text
if total_vaccinations != total_vaccinations_old:
raise ValueError(
"Both dashboards may not be synced and hence may refer to different timestamps. Consider"
"Introducing the timestamp manually.")
date = driver.find_element_by_id("pupdateddate").text.replace(
"Updated ", "")
date = str(pd.to_datetime(date, dayfirst=True).date())
data = {
"total_vaccinations": clean_count(total_vaccinations),
"people_vaccinated": clean_count(people_vaccinated),
"people_fully_vaccinated": clean_count(people_fully_vaccinated),
"date": date,
}
return pd.Series(data=data)
def parse_data(url: str) -> pd.Series:
kwargs = {"pandas_options": {"dtype": str, "header": None}}
dfs_from_pdf = tabula.read_pdf(url, pages="all", **kwargs)
for df in dfs_from_pdf:
if "Beneficiaries vaccinated" in dfs_from_pdf[0].values.flatten():
break
df = df[df[0] == "India"]
ncols = df.shape[1]
people_vaccinated = clean_count(df[ncols - 3].item())
people_fully_vaccinated = clean_count(df[ncols - 2].item())
total_vaccinations = clean_count(df[ncols - 1].item())
return pd.Series({
"date":
str((datetime.datetime.now(pytz.timezone("Asia/Kolkata")) -
datetime.timedelta(days=1)).date()),
"people_vaccinated":
people_vaccinated,
"people_fully_vaccinated":
people_fully_vaccinated,
"total_vaccinations":
total_vaccinations,
"source_url":
url,
})
def parse_data(soup: BeautifulSoup) -> pd.Series:
a = 1 + 2
b = 1
regex_1 = (
r"([\d,]+) C(ovid|OVID)-19 vaccinations has been given in total in the Cayman Islands"
)
regex_1 = r"([\d,]+) C(ovid|OVID)-19 vaccinations (?:had|have) been given in total in the Cayman Islands"
total_vaccinations = clean_count(re.search(regex_1, soup.text).group(1))
# regex_2 = (
# r"Of these, ([\d,]+) \((?:[\d,]+)% of (?:[a-zA-Z0-9,]+)\) have had at least one dose"
# )
# assert total_vaccinations >= people_vaccinated
# people_fully_vaccinated = total_vaccinations - people_vaccinated
regex_2 = (
r"Of these,? ([\d,]+) \((?:[\d,]+)% of (?:[\d,]+)\) (?:have)? had at least one dose of a C(?:ovid|OVID)-19 "
r"vaccine and (?:approximately)? (?:[\d,]+)% \(([\d,]+)\) have completed the two-dose course\."
)
matches = re.search(regex_2, soup.text)
people_vaccinated = clean_count(matches.group(1))
people_fully_vaccinated = clean_count(matches.group(2))
return pd.Series({
"total_vaccinations": total_vaccinations,
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated,
})
def read(source: str) -> pd.Series:
op = Options()
op.add_argument("--headless")
with webdriver.Chrome(options=op) as driver:
driver.get(source)
time.sleep(1)
for h5 in driver.find_elements_by_tag_name("h5"):
if "Primera dosis" in h5.text:
people_vaccinated = clean_count(
h5.find_element_by_xpath("./preceding-sibling::div").text)
elif "Total dosis aplicadas" in h5.text:
total_vaccinations = clean_count(
h5.find_element_by_xpath("./preceding-sibling::div").text)
elif "Población completamente vacunada" in h5.text:
people_fully_vaccinated = clean_count(
h5.find_element_by_xpath("./preceding-sibling::div").text)
elif "Acumulados al" in h5.text:
date = h5.text.replace("Acumulados al ", "")
date = str(dateparser.parse(date, languages=["es"]).date())
data = {
"date": date,
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated,
"total_vaccinations": total_vaccinations,
}
return pd.Series(data=data)
def _parse_data(self) -> pd.Series:
op = Options()
op.add_argument("--headless")
with webdriver.Chrome(options=op) as driver:
# Main page
driver.get(self.source_url)
# Get report page from within iframe
source = driver.find_element_by_xpath(
"/html/body/section[2]/iframe").get_attribute("src")
driver.get(source)
data_blocks = (WebDriverWait(driver, 20).until(
EC.visibility_of_all_elements_located(
(By.CLASS_NAME, "card"))))
for block in data_blocks:
block_title = block.get_attribute("aria-label")
if "first dose" in block_title:
people_vaccinated = re.search(r"first dose +(\d+)\.",
block_title).group(1)
elif "sec dose" in block_title:
people_fully_vaccinated = re.search(
r"sec dose +(\d+)\.", block_title).group(1)
people_vaccinated = clean_count(people_vaccinated)
people_fully_vaccinated = clean_count(people_fully_vaccinated)
return pd.Series({
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated,
})
def connect_parse_data(source: str) -> pd.Series:
op = Options()
op.add_argument("--headless")
with webdriver.Chrome(options=op) as driver:
driver.get(source)
time.sleep(10)
date = driver.find_element_by_class_name(
"as_of").find_element_by_tag_name("span").text
date = clean_date(date, "%d.%m.%Y")
for elem in driver.find_elements_by_class_name("counter_block"):
if "1 ДОЗУ" in elem.text:
people_vaccinated = elem.find_element_by_tag_name("h2").text
if "2 ДОЗИ" in elem.text:
people_fully_vaccinated = elem.find_element_by_tag_name(
"h2").text
data = {
"people_vaccinated": clean_count(people_vaccinated),
"people_fully_vaccinated": clean_count(people_fully_vaccinated),
"date": date,
}
return pd.Series(data=data)
def parse_vaccinations(elem) -> dict:
# Get news text
url = elem.find_parent(class_="card").find("a").get("href")
soup = get_soup(url)
text = "\n".join([p.text for p in soup.find("article").find_all("p")])
# Find metrics
metrics = dict()
# total_vaccinations = re.search(r"疫苗共有(?P<count>[\d,]*)人次", text)
total_vaccinations = re.search(r"疫苗劑數為(?P<count>[\d,]*)劑", text)
# print(total_vaccinations)
# people_vaccinated = re.search(r"1劑疫苗共有(?P<count>[\d,]*)人次", text)
people_vaccinated = re.search(r"已接種人數共有(?P<count>[\d,]*)人", text)
# people_fully_vaccinated = re.search(r"2劑疫苗共有(?P<count>[\d,]*)人次", text)
people_fully_vaccinated = re.search(r"已完成接種2劑有(?P<count>[\d,]*)人", text)
if total_vaccinations:
metrics["total_vaccinations"] = clean_count(
total_vaccinations.group(1))
if people_vaccinated:
metrics["people_vaccinated"] = clean_count(people_vaccinated.group(1))
if people_fully_vaccinated:
metrics["people_fully_vaccinated"] = clean_count(
people_fully_vaccinated.group(1))
return metrics
def parse_data(soup: BeautifulSoup):
regex = r"Укупно вакцинација: ([\d.]+), од тога ревакцинација: ([\d.]+)"
matches = re.search(regex, soup.text)
total_vaccinations = clean_count(matches.group(1))
people_fully_vaccinated = clean_count(matches.group(2))
return total_vaccinations, people_fully_vaccinated
def connect_parse_data(source: str) -> pd.Series:
headers = {
"User-Agent":
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.16; rv:86.0) Gecko/20100101 Firefox/86.0",
"Accept":
"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
"Accept-Language": "fr,fr-FR;q=0.8,en-US;q=0.5,en;q=0.3",
"Accept-Encoding": "gzip, deflate, br",
"Connection": "keep-alive",
"Upgrade-Insecure-Requests": "1",
"Pragma": "no-cache",
"Cache-Control": "no-cache",
}
soup = BeautifulSoup(
requests.get(source, headers=headers).content, "html.parser")
data = re.search(r"De los ([\d\.]+) vacunados un total de ([\d\.]+)",
soup.text)
people_vaccinated = clean_count(data.group(1))
people_fully_vaccinated = clean_count(data.group(2))
data = {
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated,
}
return pd.Series(data=data)
def main():
data = {
"location": "Guatemala",
"source_url": "https://gtmvigilanciacovid.shinyapps.io/3869aac0fb95d6baf2c80f19f2da5f98",
"vaccine": "Moderna, Oxford/AstraZeneca",
}
op = Options()
op.add_argument("--headless")
with webdriver.Chrome(options=op) as driver:
driver.maximize_window() # For maximizing window
driver.implicitly_wait(20) # gives an implicit wait for 20 seconds
driver.get(data["source_url"])
driver.find_element_by_class_name("fa-syringe").click()
date = driver.find_element_by_class_name("logo").text
dose1 = driver.find_element_by_id("dosisaplicadas1").find_element_by_tag_name("h3").text
dose2 = driver.find_element_by_id("dosisaplicadas2").find_element_by_tag_name("h3").text
data["people_vaccinated"] = clean_count(dose1)
data["people_fully_vaccinated"] = clean_count(dose2)
data["total_vaccinations"] = data["people_vaccinated"] + data["people_fully_vaccinated"]
date = re.search(r"\d+/\d+/202\d", date).group(0)
data["date"] = clean_date(date, "%d/%m/%Y")
increment(
location=data["location"],
total_vaccinations=data["total_vaccinations"],
people_vaccinated=data["people_vaccinated"],
people_fully_vaccinated=data["people_fully_vaccinated"],
date=data["date"],
source_url=data["source_url"],
vaccine=data["vaccine"],
)
def connect_parse_data(source: str) -> pd.Series:
op = Options()
op.add_argument("--headless")
with webdriver.Chrome(options=op) as driver:
driver.get(source)
time.sleep(10)
date = re.search(r"Fecha de corte : ([\d/]{10})",
driver.page_source).group(1)
for block in driver.find_elements_by_class_name("unselectable"):
if block.get_attribute("aria-label") == "Dosis aplicadas Card":
total_vaccinations = clean_count(
block.find_element_by_class_name("value").text)
elif block.get_attribute(
"aria-label") == "Segundas dosis aplicadas Card":
people_fully_vaccinated = clean_count(
block.find_element_by_class_name("value").text)
people_vaccinated = total_vaccinations - people_fully_vaccinated
return pd.Series({
"total_vaccinations": total_vaccinations,
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated,
"date": clean_date(date, "%d/%m/%Y")
})
def parse_data(soup: BeautifulSoup) -> pd.Series:
for p in soup.find_all("p"):
if "Primera dosis" in p.text:
people_vaccinated = clean_count(
re.search(r"[\d,]{6,}", p.text).group(0))
elif "Total dosis aplicadas" in p.text:
total_vaccinations = clean_count(
re.search(r"[\d,]{6,}", p.text).group(0))
elif "Población completamente vacunada" in p.text:
people_fully_vaccinated = clean_count(
re.search(r"[\d,]{6,}", p.text).group(0))
date = soup.find("h6").text.replace("Acumulados al ", "")
date = str(dateparser.parse(date, languages=["es"]).date())
data = {
"date": date,
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated,
"total_vaccinations": total_vaccinations,
}
return pd.Series(data=data)
def parse_data(data: dict) -> pd.Series:
dose1 = clean_count(data["data"][0]["vakdose1"])
dose2 = clean_count(data["data"][0]["vakdose2"])
data = pd.Series({
"date": datetime.fromtimestamp(data["updated"] // 1000).strftime("%Y-%m-%d"),
"people_vaccinated": dose1,
"people_fully_vaccinated": dose2,
"total_vaccinations": dose1 + dose2
})
return data
def parse_data(soup: BeautifulSoup) -> pd.Series:
numbers = soup.find(class_="cifras-coronavirus").find_all(class_="cifra")
return pd.Series(
data={
"total_vaccinations": clean_count(numbers[1].text),
"people_fully_vaccinated": clean_count(numbers[2].text),
"date": set_date()
})
def parse_data(self, soup):
widgets = soup.find_all(class_="textwidget")
total_vaccinations = clean_count(widgets[0].text)
people_fully_vaccinated = clean_count(widgets[1].text)
people_vaccinated = total_vaccinations - people_fully_vaccinated
return pd.Series({
"total_vaccinations": total_vaccinations,
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated,
"date": localdate("Asia/Tbilisi")
})
def _parse_metrics(self, soup: BeautifulSoup):
total_vaccinations = clean_count(
re.search(self.regex["total_vaccinations"], soup.text).group(1)
)
people_vaccinated = clean_count(
re.search(self.regex["people_vaccinated"], soup.text).group(1)
)
people_fully_vaccinated = clean_count(
re.search(self.regex["people_fully_vaccinated"], soup.text).group(1)
)
return total_vaccinations, people_vaccinated, people_fully_vaccinated
def parse_data(self, soup):
regex = r"ja s’han administrat ([\d\.]+) dosis i ([\d\.]+) persones han rebut, com a mínim, una dosi del vaccí"
match = re.search(regex, soup.text)
# Metrics
total_vaccinations = clean_count(match.group(1))
people_vaccinated = clean_count(match.group(2))
people_fully_vaccinated = total_vaccinations - people_vaccinated
return pd.Series({
"total_vaccinations": total_vaccinations,
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated,
"date": self.parse_date(soup)
})
def parse_data_news_page(self, soup: BeautifulSoup):
people_vaccinated = re.search(self.regex["people_vaccinated"],
soup.text)
people_fully_vaccinated = re.search(
self.regex["people_fully_vaccinated"], soup.text)
metrics = {}
if people_vaccinated:
metrics["people_vaccinated"] = clean_count(
people_vaccinated.group(1))
if people_fully_vaccinated:
metrics["people_fully_vaccinated"] = clean_count(
people_fully_vaccinated.group(1))
return metrics
def _parse_metrics(self, text: str):
metrics = re.search(self.regex_vax, text).groups()
people_vaccinated = clean_count(metrics[0])
people_fully_vaccinated = clean_count(metrics[1])
total_vaccinations = clean_count(metrics[2])
if total_vaccinations != people_vaccinated + people_fully_vaccinated:
raise ValueError(
"total_vaccinations != people_vaccinated + people_fully_vaccinated"
)
return {
"total_vaccinations": total_vaccinations,
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated,
}
def parse_infogram_vaccinations(infogram_data: dict) -> int:
total_vaccinations = clean_count(
_get_infogram_value(infogram_data,
"4f66ed81-151f-4b97-aa3c-4927bde058b2"))
people_vaccinated = clean_count(
_get_infogram_value(infogram_data,
"4048eac1-24ba-4e24-b081-61dfa0281a0e"))
people_fully_vaccinated = clean_count(
_get_infogram_value(infogram_data,
"50a2486f-7dca-4afd-a551-bd24665d7314"))
return {
"total_vaccinations": total_vaccinations,
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated
}
def parse_data(self, soup):
regex = (
r"s’han administrat un total de ([\d\.]+) vacunes, ([\d\.]+) persones (?:han rebut|tenen) una dosi del "
r"vaccí,? i ([\d\.]+) (persones )?(en )?tenen les dues")
match = re.search(regex, soup.text)
# Metrics
total_vaccinations = clean_count(match.group(1))
people_vaccinated = clean_count(match.group(2))
people_fully_vaccinated = clean_count(match.group(3))
# people_fully_vaccinated = total_vaccinations - people_vaccinated
return pd.Series({
"total_vaccinations": total_vaccinations,
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated,
"date": self.parse_date(soup)
})
def connect_parse_data(source: str) -> pd.Series:
headers = {
"User-Agent":
"Mozilla/5.0 (Macintosh; Intel Mac OS X 10.16; rv:86.0) Gecko/20100101 Firefox/86.0",
"Accept":
"text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
"Accept-Language": "fr,fr-FR;q=0.8,en-US;q=0.5,en;q=0.3",
"Accept-Encoding": "gzip, deflate, br",
"Connection": "keep-alive",
"Upgrade-Insecure-Requests": "1",
"Pragma": "no-cache",
"Cache-Control": "no-cache",
}
soup = BeautifulSoup(
requests.get(source, headers=headers).content, "html.parser")
total_vaccinations = soup.find(class_="repart-stlucia").text
total_vaccinations = clean_count(total_vaccinations)
date = soup.find(class_="h2-blue").text
date = re.search(r"\w+ +\d+, +202\d", date).group(0)
date = clean_date(date, "%B %d, %Y")
data = {
"total_vaccinations": total_vaccinations,
"date": date,
}
return pd.Series(data=data)
def parse_data(soup: BeautifulSoup) -> pd.Series:
# Get path to newest pdf
links = soup.find(class_="rt-article").find_all("a")
for link in links:
if "sitrep-sl-en" in link["href"]:
pdf_path = "https://www.epid.gov.lk" + link["href"]
break
tf = tempfile.NamedTemporaryFile()
with open(tf.name, mode="wb") as f:
f.write(requests.get(pdf_path).content)
with open(tf.name, mode="rb") as f:
reader = PyPDF2.PdfFileReader(f)
page = reader.getPage(0)
text = page.extractText().replace("\n", "")
regex = r"COVID-19\s+Total\s+Vaccinated\s+(\d+)"
total_vaccinations = re.search(regex, text).group(1)
total_vaccinations = clean_count(total_vaccinations)
people_vaccinated = total_vaccinations
regex = r"Situation Report\s+([\d\.]{10})"
date = re.search(regex, text).group(1)
date = clean_date(date, "%d.%m.%Y")
return pd.Series(data={
"total_vaccinations": total_vaccinations,
"people_vaccinated": people_vaccinated,
"date": date,
"source_url": pdf_path,
})
def _parse_stats(self, df: pd.DataFrame) -> int:
if df.shape[1] != 4 or df.iloc[0, 0] != "廠牌" or df.iloc[
0, 1] != "劑次" or not (df.iloc[-1, 0] == "總計"
or df.iloc[-2, 0] == "總計"):
raise ValueError(f"Table 1: format has changed!")
num_dose1 = df[df[1] == "第 1劑"].tail(1).values[0][-1]
num_dose1 = clean_count(num_dose1)
num_dose2 = df[df[1] == "第 2劑"].tail(1).values[0][-1]
num_dose2 = clean_count(num_dose2)
return {
"total_vaccinations": (num_dose1 + num_dose2),
"people_vaccinated": num_dose1,
}
def parse_total_vaccinations(soup: BeautifulSoup) -> str:
return clean_count(
soup
.find(class_="counter-box-content", string=re.compile("Vaccines Administered"))
.parent
.find(class_="display-counter")["data-value"]
)
def parse_data(self, soup: BeautifulSoup) -> pd.Series:
data = {}
match = re.search(self.regex["title"], soup.text)
if match:
# date
date_str = match.group(1)
data["date"] = clean_date(f"{date_str} {datetime.now().year}",
"%d de %B %Y",
lang="es")
# vaccinations
data["total_vaccinations"] = clean_count(match.group(2))
match = re.search(self.regex["data"], soup.text)
if match:
data["people_vaccinated"] = clean_count(match.group(1))
data["people_fully_vaccinated"] = clean_count(match.group(3))
return pd.Series(data)
def parse_metric(soup: BeautifulSoup, description: str) -> int:
value = (
soup.find("strong", string=description)
.parent.parent.parent.parent
.find_all("tr")[-1]
.text
)
return clean_count(value)
