def main():
url = "https://vaccinocovid.iss.sm/"
soup = BeautifulSoup(
requests.get(url, verify=False).content, "html.parser")
for script in soup.find_all("script"):
if "new Chart" in str(script):
chart_data = str(script)
break
people_vaccinated = re.search(r"([\d,. ]+) [Vv]accinati",
chart_data).group(1)
people_vaccinated = vaxutils.clean_count(people_vaccinated)
people_fully_vaccinated = 0
total_vaccinations = people_vaccinated + people_fully_vaccinated
date = re.search(r"Dati aggiornati al (\d{2}/\d{2}/\d{4})",
chart_data).group(1)
date = vaxutils.clean_date(date, "%d/%m/%Y")
vaxutils.increment(location="San Marino",
total_vaccinations=total_vaccinations,
people_vaccinated=people_vaccinated,
people_fully_vaccinated=people_fully_vaccinated,
date=date,
source_url="https://vaccinocovid.iss.sm/",
vaccine="Sputnik V")
def main():
url = "https://vaccinare-covid.gov.ro/comunicate-oficiale/"
soup = BeautifulSoup(requests.get(url).content, "html.parser")
links = soup.find(class_="display-posts-listing").find_all("a",
class_="title")
for link in links:
if "Actualizare zilnică" in link.text:
url = link["href"]
break
soup = BeautifulSoup(requests.get(url).content, "html.parser")
date = soup.find(class_="post-date").find(class_="meta-text").text.strip()
date = vaxutils.clean_date(date, "%b %d, %Y")
main_text = soup.find(class_="entry-content-text").text
count = re.search(
r"Număr total de persoane vaccinate împotriva COVID-19 cu vaccinul Pfizer BioNTech \(începând cu data de 27 decembrie 2020\) – ([\d\.]+)",
main_text)
count = count.group(1)
count = vaxutils.clean_count(count)
vaxutils.increment(location="Romania",
total_vaccinations=count,
date=date,
source_url=url,
vaccine="Pfizer/BioNTech")
def main():
url = "https://vaccinare-covid.gov.ro/comunicate-oficiale/"
soup = BeautifulSoup(requests.get(url).content, "html.parser")
links = soup.find(class_="display-posts-listing").find_all("a", class_="title")
for link in links:
if "Actualizare zilnică" in link.text:
url = link["href"]
break
soup = BeautifulSoup(requests.get(url).content, "html.parser")
date = soup.find(class_="post-date").find(class_="meta-text").text.strip()
date = vaxutils.clean_date(date, "%b %d, %Y")
paragraphs = soup.find(class_="entry-content").find_all("p")
for paragraph in paragraphs:
if "Număr total de persoane vaccinate" in paragraph.text:
count = paragraph.find_all("strong")
count = "".join(c.text for c in count)
count = vaxutils.clean_count(count)
vaxutils.increment(
location="Romania",
total_vaccinations=count,
date=date,
source_url=url,
vaccine="Pfizer/BioNTech"
)
def main():
url = "https://www.gov.bm/sites/default/files/COVID-19%20Vaccination%20Updates.pdf"
os.system(f"curl {url} -o bermuda.pdf -s")
with open("bermuda.pdf", "rb") as pdfFileObj:
pdfReader = PyPDF2.PdfFileReader(pdfFileObj)
text = pdfReader.getPage(0).extractText()
regex = r"VACCINATION CENTRE(.*?)Total Vaccines Administered"
total_vaccinations = re.search(regex, text)
total_vaccinations = vaxutils.clean_count(total_vaccinations.group(1))
regex = r"As of (\w+ \d+, 20\d+)"
date = re.search(regex, text)
date = vaxutils.clean_date(date.group(1), "%B %d, %Y")
vaxutils.increment(
location="Bermuda",
total_vaccinations=total_vaccinations,
date=date,
source_url=url,
vaccine="Pfizer/BioNTech"
)
os.remove("bermuda.pdf")
def main():
url = "https://www.terviseamet.ee/et/uudised"
soup = BeautifulSoup(requests.get(url).content, "html.parser")
for h2 in soup.find_all("h2", class_="views-field-title"):
if "COVID-19 blogi" in h2.text:
url = "https://www.terviseamet.ee" + h2.find("a")["href"]
break
soup = BeautifulSoup(requests.get(url).content, "html.parser")
date = soup.find(class_="field-name-post-date").text
date = vaxutils.clean_date(date, "%d.%m.%Y")
count = soup.find(
string=re.compile(r"Eestis on COVID-19 vastu vaktsineerimisi"))
count = re.search(r"tehtud ([\d\s]+) inimesele", count).group(1)
count = vaxutils.clean_count(count)
vaxutils.increment(location="Estonia",
total_vaccinations=count,
date=date,
source_url=url,
vaccine="Pfizer/BioNTech")
def main():
url = "https://data.public.lu/fr/datasets/covid-19-rapports-journaliers/#_"
# Locate newest pdf
html_page = urllib.request.urlopen(url)
soup = BeautifulSoup(html_page, "html.parser")
pdf_path = soup.find(
"a", class_="btn-primary")["href"] # Get path to newest pdf
# Fetch data
dfs_from_pdf = tabula.read_pdf(pdf_path, pages="all")
df = pd.DataFrame(dfs_from_pdf[2]) # Hardcoded table location
total_vaccinations = df.loc[df["Unnamed: 0"] ==
"Nombre de doses administrées",
"Unnamed: 1"].values[0]
total_vaccinations = vaxutils.clean_count(total_vaccinations)
date = re.search(r"\d\d\.\d\d\.202\d", df.columns[1]).group(0)
date = vaxutils.clean_date(date, "%d.%m.%Y")
vaxutils.increment(location="Luxembourg",
total_vaccinations=total_vaccinations,
date=date,
source_url=pdf_path,
vaccine="Pfizer/BioNTech")
def main():
url = "https://data.public.lu/fr/datasets/covid-19-rapports-journaliers/#_"
# Locate newest pdf
soup = BeautifulSoup(requests.get(url).content, "html.parser")
pdf_path = soup.find(
"a", class_="btn-primary")["href"] # Get path to newest pdf
# Fetch data
dfs_from_pdf = tabula.read_pdf(pdf_path, pages="all")
df = pd.DataFrame(dfs_from_pdf[2]) # Hardcoded table location
values = sorted(
pd.to_numeric(df["Unnamed: 2"].str.replace(
r"[^\d]", "", regex=True)).dropna().astype(int))
assert len(values) == 3
total_vaccinations = values[2]
people_vaccinated = values[1]
people_fully_vaccinated = values[0]
date = df["Unnamed: 1"].str.replace("Journée du ", "").values[0]
date = vaxutils.clean_date(date, "%d.%m.%Y")
vaxutils.increment(location="Luxembourg",
total_vaccinations=total_vaccinations,
people_vaccinated=people_vaccinated,
people_fully_vaccinated=people_fully_vaccinated,
date=date,
source_url=pdf_path,
vaccine="Moderna, Oxford/AstraZeneca, Pfizer/BioNTech")
def main():
url = "https://esriportugal.maps.arcgis.com/apps/opsdashboard/index.html#/acf023da9a0b4f9dbb2332c13f635829"
# Options for Chrome WebDriver
op = Options()
# op.add_argument("--headless")
with webdriver.Chrome(options=op) as driver:
driver.get(url)
time.sleep(4)
for box in driver.find_elements_by_class_name("indicator-top-text"):
if "Total de Vacinas Administradas" in box.text:
count_text = box.find_element_by_xpath("..").text
elif "Dados relativos ao boletim da DGS de" in box.text:
date_text = box.find_element_by_xpath("..").text
count = re.search(r"\n([\d\s]+$)", count_text).group(1)
count = vaxutils.clean_count(count)
date = re.search(r"\n([\d/]+$)", date_text).group(1)
date = vaxutils.clean_date(date, "%d/%m/%Y")
vaxutils.increment(location="Portugal",
total_vaccinations=count,
date=date,
source_url=url,
vaccine="Pfizer/BioNTech")
def main():
url = "https://data.public.lu/fr/datasets/covid-19-rapports-journaliers/#_"
# Locate newest pdf
soup = BeautifulSoup(requests.get(url).content, "html.parser")
pdf_path = soup.find(
"a", class_="btn-primary")["href"] # Get path to newest pdf
# Fetch data
dfs_from_pdf = tabula.read_pdf(pdf_path, pages="all")
df = pd.DataFrame(dfs_from_pdf[2]) # Hardcoded table location
people_vaccinated = df.loc[df["Unnamed: 0"] ==
"Personnes vaccinées - Dose 1",
"Unnamed: 2"].values[0]
people_vaccinated = vaxutils.clean_count(people_vaccinated)
people_fully_vaccinated = df.loc[df["Unnamed: 0"] ==
"Personnes vaccinées - Dose 2",
"Unnamed: 2"].values[0]
people_fully_vaccinated = vaxutils.clean_count(people_fully_vaccinated)
total_vaccinations = people_vaccinated + people_fully_vaccinated
date = df["Unnamed: 1"].str.replace("Journée du ", "").values[0]
date = vaxutils.clean_date(date, "%d.%m.%Y")
vaxutils.increment(location="Luxembourg",
total_vaccinations=total_vaccinations,
people_vaccinated=people_vaccinated,
people_fully_vaccinated=people_fully_vaccinated,
date=date,
source_url=pdf_path,
vaccine="Pfizer/BioNTech")
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 = vaxutils.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": vaxutils.clean_count(people_vaccinated),
"people_fully_vaccinated":
vaxutils.clean_count(people_fully_vaccinated),
"date": date,
}
return pd.Series(data=data)
def main():
url = "https://covid19.gov.im/general-information/latest-updates/"
soup = BeautifulSoup(requests.get(url).content, "html.parser")
vax_box = soup.find(string=re.compile("Total first vaccinations")).parent.parent
date = vax_box.find("strong").text
date = vaxutils.clean_date(date, "%d %B %Y")
for p in vax_box.find_all("p"):
if "Total first vaccinations" in p.text:
data = p.text
people_vaccinated, people_fully_vaccinated = re.search(r"Total first vaccinations:\xa0 ([\d,]+)Total second vaccinations:\xa0 ([\d,]+)", data).groups()
people_vaccinated = vaxutils.clean_count(people_vaccinated)
people_fully_vaccinated = vaxutils.clean_count(people_fully_vaccinated)
total_vaccinations = people_vaccinated + people_fully_vaccinated
vaxutils.increment(
location="Isle of Man",
total_vaccinations=total_vaccinations,
people_vaccinated=people_vaccinated,
people_fully_vaccinated=people_fully_vaccinated,
date=date,
source_url=url,
vaccine="Pfizer/BioNTech"
)
def main():
op = Options()
op.add_argument("--headless")
with webdriver.Chrome(options=op) as driver:
url = "https://app.powerbi.com/view?r=eyJrIjoiMzg4YmI5NDQtZDM5ZC00ZTIyLTgxN2MtOTBkMWM4MTUyYTg0IiwidCI6ImFmZDBhNzVjLTg2NzEtNGNjZS05MDYxLTJjYTBkOTJlNDIyZiIsImMiOjh9"
driver.get(url)
# Wait for the desired element to load. If nothing is found after 25 seconds, returns.
timeout = 25
try:
element_present = EC.presence_of_element_located(
(By.CLASS_NAME, "value"))
data = WebDriverWait(driver, timeout).until(element_present).text
except TimeoutException:
return
count = vaxutils.clean_count(data)
try:
element_present = EC.presence_of_element_located(
(By.CLASS_NAME, "title"))
data = WebDriverWait(driver, timeout).until(element_present).text
except TimeoutException:
return
date = vaxutils.clean_date(data, "%m/%d/%Y %H:%M:%S %p")
vaxutils.increment(location="Italy",
total_vaccinations=count,
date=date,
source_url=url,
vaccine="Pfizer/BioNTech")
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 = vaxutils.clean_count(total_vaccinations)
date = soup.find(class_="h2-blue").text
date = re.search(r"\w+ \d+, 202\d", date).group(0)
date = vaxutils.clean_date(date, "%B %d, %Y")
data = {
"total_vaccinations": total_vaccinations,
"date": date,
}
return pd.Series(data=data)
def main():
url = "https://www.terviseamet.ee/et/uudised"
soup = BeautifulSoup(requests.get(url).content, "html.parser")
for h2 in soup.find_all("h2", class_="views-field-title"):
if "COVID-19 blogi" in h2.text:
url = "https://www.terviseamet.ee" + h2.find("a")["href"]
break
soup = BeautifulSoup(requests.get(url).content, "html.parser")
text = soup.find(class_="node-published").text
people_vaccinated, people_fully_vaccinated = re.search(
r"Eestis on COVID-19 vastu vaktsineerimisi tehtud ([\d\s]+) inimesele, kaks doosi on saanud ([\d\s]+) inimest",
text).groups()
people_vaccinated = vaxutils.clean_count(people_vaccinated)
people_fully_vaccinated = vaxutils.clean_count(people_fully_vaccinated)
total_vaccinations = people_vaccinated + people_fully_vaccinated
date = soup.find(class_="field-name-post-date").text
date = vaxutils.clean_date(date, "%d.%m.%Y")
vaxutils.increment(location="Estonia",
total_vaccinations=total_vaccinations,
people_vaccinated=people_vaccinated,
people_fully_vaccinated=people_fully_vaccinated,
date=date,
source_url=url,
vaccine="Pfizer/BioNTech")
def main():
data = {
"location": "Guatemala",
"source_url":
"https://gtmvigilanciacovid.shinyapps.io/3869aac0fb95d6baf2c80f19f2da5f98",
"vaccine": "Moderna",
}
with webdriver.Chrome() as driver:
driver.get(data["source_url"])
time.sleep(2)
driver.find_element_by_class_name("fa-syringe").click()
time.sleep(4)
date = driver.find_element_by_class_name("logo").text
dose1 = driver.find_element_by_id(
"dosisaplicadas").find_element_by_tag_name("h3").text
data["people_vaccinated"] = vaxutils.clean_count(dose1)
data["people_fully_vaccinated"] = 0
data["total_vaccinations"] = data["people_vaccinated"] + data[
"people_fully_vaccinated"]
date = re.search(r"\d+/\d+/202\d", date).group(0)
data["date"] = vaxutils.clean_date(date, "%d/%m/%Y")
vaxutils.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 parse_date(soup: BeautifulSoup) -> str:
for h3 in soup.find_all("h3"):
if "Vaccination Data" in h3.text:
break
date = re.search(r"as of (\d+ \w+ \d+)", h3.text).group(1)
date = vaxutils.clean_date(date, "%d %b %Y")
return date
def main():
url = "https://www.gov.je/Health/Coronavirus/Vaccine/Pages/VaccinationStatistics.aspx"
soup = BeautifulSoup(requests.get(url).content, "html.parser")
table = soup.find(class_="govstyleTable-default")
df = pd.read_html(str(table))[0]
total_vaccinations = int(df.loc[df[0] == "Total number of doses",
1].values[0])
people_vaccinated = int(
df.loc[df[0] == "Total number of first dose vaccinations",
1].values[0])
people_fully_vaccinated = int(
df.loc[df[0] == "Total number of second dose vaccinations",
1].values[0])
date = re.search(r"Data applies to: Week ending (\d[\w\s]+\d{4})",
soup.text).group(1)
date = vaxutils.clean_date(date, "%d %B %Y")
vaxutils.increment(location="Jersey",
total_vaccinations=total_vaccinations,
people_vaccinated=people_vaccinated,
people_fully_vaccinated=people_fully_vaccinated,
date=date,
source_url=url,
vaccine="Oxford/AstraZeneca, Pfizer/BioNTech")
def parse_data(data: dict) -> pd.Series:
sheet_id = data["sheetNames"].index("Vakcinisani ukupno")
total_vaccinations = vaxutils.clean_count(data["data"][sheet_id][0][0])
date = vaxutils.clean_date(data["data"][1][0][0], "%d.%m.%Y.")
data = {"date": date, "total_vaccinations": total_vaccinations}
return pd.Series(data=data)
def parse_data(data: dict) -> pd.Series:
date = vaxutils.clean_date(data["updated"], "%Y/%m/%d")
total_vaccinations = data["progress"]
return pd.Series(data={
"date": date,
"total_vaccinations": total_vaccinations,
})
def parse_data(soup: BeautifulSoup) -> pd.Series:
numbers = soup.find_all(class_="odometer")
date = re.search(r"[\d\.]{10}", soup.find(class_="counter").text).group(0)
date = vaxutils.clean_date(date, "%d.%m.%Y")
return pd.Series(data={
"total_vaccinations": int(numbers[0]["data-count"]),
"people_vaccinated": int(numbers[1]["data-count"]),
"people_fully_vaccinated": int(numbers[2]["data-count"]),
"date": date
})
def parse_data(soup: BeautifulSoup) -> pd.Series:
data = pd.Series(dtype="int")
spans = soup.find("table").find_all("span")
data["people_vaccinated"] = int(re.sub(r"[^\d]", "", spans[-3].text))
data["people_fully_vaccinated"] = int(re.sub(r"[^\d]", "", spans[-2].text))
data["total_vaccinations"] = data["people_vaccinated"] + data["people_fully_vaccinated"]
date = re.search(r"[\d-]{10}", spans[0].text).group(0)
data["date"] = vaxutils.clean_date(date, "%d-%m-%Y")
return data
def read(source: str) -> pd.Series:
soup = vaxutils.get_soup(source)
total_vaccinations = vaxutils.clean_count(soup.find(class_="stats-decoration-title").text)
people_vaccinated = total_vaccinations
people_fully_vaccinated = 0
date = re.search(r"\d+ \w+ 202\d", soup.find(class_="stats-decoration-text").text).group(0)
date = vaxutils.clean_date(date, "%d %B %Y")
return pd.Series(data={
"total_vaccinations": total_vaccinations,
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated,
"date": date,
})
def main():
url = "https://www.mohfw.gov.in/"
soup = BeautifulSoup(requests.get(url).content, "html.parser")
total_vaccinations = soup.find(class_="coviddata").text
total_vaccinations = vaxutils.clean_count(total_vaccinations)
date = soup.find(id="site-dashboard").find("h5").text
date = re.search(r"\d+\s\w+\s+202\d", date).group(0)
date = vaxutils.clean_date(date, "%d %B %Y")
vaxutils.increment(location="India",
total_vaccinations=total_vaccinations,
date=date,
source_url=url,
vaccine="Covaxin, Covishield")
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(5)
total_vaccinations = driver.find_element_by_id("counter1").text
date = driver.find_element_by_id("pupdateddate").text
date = vaxutils.clean_date(date.replace("Updated ", ""), "%d %b, %Y")
data = {
"total_vaccinations": vaxutils.clean_count(total_vaccinations),
"date": date,
}
return pd.Series(data=data)
def parse_data(soup: BeautifulSoup) -> pd.Series:
people_vaccinated = int(soup.find_all(class_="count")[0]["data-count"])
people_fully_vaccinated = int(soup.find_all(class_="count")[1]["data-count"])
assert people_vaccinated >= people_fully_vaccinated
total_vaccinations = people_vaccinated + people_fully_vaccinated
date = soup.find(class_="reportdate").text
date = re.search(r"\d+ \w+ 202\d", date).group(0)
date = vaxutils.clean_date(date, "%d %b %Y")
data = {
"total_vaccinations": total_vaccinations,
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated,
"date": date,
}
return pd.Series(data=data)
def main():
url = "https://covid19.gov.im/general-information/latest-updates/"
soup = BeautifulSoup(requests.get(url).content, "html.parser")
date = soup.find(class_="fa-syringe").parent.find("strong").text
date = vaxutils.clean_date(date, "%d %B %Y")
total_vaccinations = soup.find(class_="fa-syringe").parent.text
total_vaccinations = re.search(r"Total vaccinations:\s+(\d+)",
total_vaccinations).group(1)
total_vaccinations = vaxutils.clean_count(total_vaccinations)
vaxutils.increment(location="Isle of Man",
total_vaccinations=total_vaccinations,
date=date,
source_url=url,
vaccine="Pfizer/BioNTech")
def parse_data(soup: BeautifulSoup) -> pd.Series:
total_vaccinations = int(soup.find_all(class_="counter")[0].text)
people_vaccinated = int(soup.find_all(class_="counter")[1].text)
people_fully_vaccinated = int(soup.find_all(class_="counter")[2].text)
assert total_vaccinations >= people_vaccinated
assert people_vaccinated >= people_fully_vaccinated
date = soup.find(class_="fuente").text
date = re.search(r"\d{2}-\d{2}-\d{4}", date).group(0)
date = vaxutils.clean_date(date, "%d-%m-%Y")
data = {
"total_vaccinations": total_vaccinations,
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated,
"date": date,
}
return pd.Series(data=data)
def main():
url = "https://vaccinare-covid.gov.ro/comunicate-oficiale/"
soup = BeautifulSoup(requests.get(url).content, "html.parser")
links = soup.find(class_="display-posts-listing").find_all("a",
class_="title")
for link in links:
if "Actualizare zilnică" in link.text:
url = link["href"]
break
soup = BeautifulSoup(requests.get(url).content, "html.parser")
date = soup.find(class_="post-date").find(class_="meta-text").text.strip()
date = vaxutils.clean_date(date, "%b %d, %Y")
main_text = soup.find(class_="entry-content-text").text
people_fully_vaccinated = re.findall(r"[\d.]+ persoane vaccinate cu 2 doz",
main_text)[1]
people_fully_vaccinated = people_fully_vaccinated.replace(
" persoane vaccinate cu 2 doz", "")
people_fully_vaccinated = vaxutils.clean_count(people_fully_vaccinated)
people_vaccinated = re.findall(r"[\d.]+ persoane vaccinate cu 1 doz",
main_text)[1]
people_vaccinated = people_vaccinated.replace(
" persoane vaccinate cu 1 doz", "")
people_vaccinated = vaxutils.clean_count(
people_vaccinated) + people_fully_vaccinated
total_vaccinations = people_vaccinated + people_fully_vaccinated
vaxutils.increment(location="Romania",
total_vaccinations=total_vaccinations,
people_vaccinated=people_vaccinated,
people_fully_vaccinated=people_fully_vaccinated,
date=date,
source_url=url,
vaccine="Pfizer/BioNTech")
def main():
url = "https://vaccinare-covid.gov.ro/comunicate-oficiale/"
soup = BeautifulSoup(requests.get(url).content, "html.parser")
links = soup.find(class_="display-posts-listing").find_all("a",
class_="title")
for link in links:
if "Actualizare zilnică" in link.text:
url = link["href"]
break
soup = BeautifulSoup(requests.get(url).content, "html.parser")
date = soup.find(class_="post-date").find(class_="meta-text").text.strip()
date = vaxutils.clean_date(date, "%b %d, %Y")
url = soup.find(class_="entry-content-text").find_all("a")[-1]["href"]
kwargs = {'pandas_options': {'dtype': str, 'header': None}}
dfs_from_pdf = tabula.read_pdf(url, pages="all", **kwargs)
df = dfs_from_pdf[0]
values = df[df[0] == "Total"].dropna()[2].str.split(" ")
values = [
vaxutils.clean_count(val) for val in pd.core.common.flatten(values)
]
assert len(values) == 2
people_fully_vaccinated = values[1]
one_dose_only = values[0]
people_vaccinated = one_dose_only + people_fully_vaccinated
total_vaccinations = people_fully_vaccinated + people_vaccinated
vaxutils.increment(location="Romania",
total_vaccinations=total_vaccinations,
people_vaccinated=people_vaccinated,
people_fully_vaccinated=people_fully_vaccinated,
date=date,
source_url=url,
vaccine="Moderna, Oxford/AstraZeneca, Pfizer/BioNTech")
def read(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")
text = soup.find("div", id="data").find("p").text
date = re.search(r"На сегодня \(([\d\.]{8})\)", text).group(1)
date = vaxutils.clean_date(date, "%d.%m.%y")
people_vaccinated = re.search(
r"([\d\s]+) чел\. \(.*% от населения\) - привито хотя бы одним компонентом вакцины",
text).group(1)
people_vaccinated = vaxutils.clean_count(people_vaccinated)
people_fully_vaccinated = re.search(
r"([\d\s]+) чел\. \(.*% от населения\) - полностью привито",
text).group(1)
people_fully_vaccinated = vaxutils.clean_count(people_fully_vaccinated)
total_vaccinations = re.search(r"([\d\s]+) шт\. - всего прививок сделано",
text).group(1)
total_vaccinations = vaxutils.clean_count(total_vaccinations)
return pd.Series({
"total_vaccinations": total_vaccinations,
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated,
"date": date,
})