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 = clean_date(date, "%d %b %Y")
return date
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 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 = 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_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 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 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
date = clean_date(date.replace("Updated ", ""), "%d %b, %Y")
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(data: dict) -> pd.Series:
date = 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 = 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(data: dict) -> pd.Series:
date = clean_date(data["updated"], "%Y/%m/%d")
people_vaccinated = data["progress"]
people_fully_vaccinated = data["completed"]
return pd.Series(data={
"date": date,
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated,
"vaccine": ", ".join(_get_vaccine_names(data, translate=True)),
})
def connect_parse_data(source: str) -> pd.Series:
sheet = open_google_sheet(source)
date = sheet.get('C44').first().strip()
total_vaccinations = int(sheet.get('K16').first().strip().replace(',', ''))
people_fully_vaccinated = int(sheet.get('K27').first().strip().replace(',', ''))
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 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 = clean_date(date.replace("Updated ", ""), "%d %b, %Y")
data = {
"total_vaccinations": clean_count(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", "")
covishield_data = re.search(r"Covishield Vaccine (\d+) (\d+)", text)
covishield_dose1 = clean_count(covishield_data.group(1))
covishield_dose2 = clean_count(covishield_data.group(2))
sinopharm_data = re.search(
r"Sinopharm Vaccine \(Chinese Nationals\) (\d+) (\d+)", text)
sinopharm_dose1 = clean_count(sinopharm_data.group(1))
sinopharm_dose2 = clean_count(sinopharm_data.group(2))
total_vaccinations = covishield_dose1 + covishield_dose2 + sinopharm_dose1 + sinopharm_dose2
people_vaccinated = covishield_dose1 + sinopharm_dose1
people_fully_vaccinated = covishield_dose2 + sinopharm_dose2
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,
"people_fully_vaccinated": people_fully_vaccinated,
"date": date,
"source_url": pdf_path,
})
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 = 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 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 = 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 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 = clean_date(date, "%d.%m.%y")
people_vaccinated = re.search(
r"([\d\s]+) чел\. \([\d\.]+% от населения\) - привито хотя бы одним компонентом вакцины",
text).group(1)
people_vaccinated = clean_count(people_vaccinated)
people_fully_vaccinated = re.search(
r"([\d\s]+) чел\. \([\d\.]+% от населения\) - полностью привито",
text).group(1)
people_fully_vaccinated = clean_count(people_fully_vaccinated)
total_vaccinations = re.search(r"([\d\s]+) шт\. - всего прививок сделано",
text).group(1)
total_vaccinations = clean_count(total_vaccinations)
return pd.Series({
"total_vaccinations": total_vaccinations,
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated,
"date": date,
})
def read(source: str) -> pd.Series:
soup = get_soup(source)
counters = soup.find_all(class_="counter")
people_partially_vaccinated = clean_count(counters[0].text)
people_fully_vaccinated = clean_count(counters[1].text)
total_vaccinations = clean_count(counters[2].text)
people_vaccinated = people_partially_vaccinated + people_fully_vaccinated
date = soup.find("span", id="last-update").text
date = re.search(r"\d+.*202\d", date).group(0)
date = clean_date(date, "%d %B, %Y")
data = {
"total_vaccinations": total_vaccinations,
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated,
"date": date,
"source_url": source,
}
return pd.Series(data=data)
def read(source: str) -> pd.Series:
soup = get_soup(source)
for block in soup.find(class_="main").find_all(class_="w3-center"):
if block.find("p").text == "ΣΥΝΟΛΟ ΕΜΒΟΛΙΑΣΜΩΝ":
total_vaccinations = clean_count(block.find_all("p")[1].text)
date = re.search(r"[\d/]{8,10}", block.find_all("p")[2].text)
date = clean_date(date.group(0), "%d/%m/%Y")
if block.find("p").text == "ΣΥΝΟΛΟ 1ης ΔΟΣΗΣ":
people_vaccinated = clean_count(block.find_all("p")[1].text)
if block.find("p").text == "ΣΥΝΟΛΟ 2ης ΔΟΣΗΣ":
people_fully_vaccinated = clean_count(block.find_all("p")[1].text)
data = {
"total_vaccinations": total_vaccinations,
"people_vaccinated": people_vaccinated,
"people_fully_vaccinated": people_fully_vaccinated,
"date": date,
"source_url": source,
}
return pd.Series(data=data)
def parse_data(soup: BeautifulSoup) -> pd.Series:
# Get Newest PDF Report Link
latest_report_link = soup.find("div",
class_="col-lg-12",
id="content-detail").find("a")["href"]
tf = tempfile.NamedTemporaryFile()
with open(tf.name, mode="wb") as f:
f.write(requests.get(latest_report_link).content)
with open(tf.name, mode="rb") as f:
viewer = SimplePDFViewer(f)
viewer.render()
raw_text = "".join(viewer.canvas.strings)
special_char_replace = {
'\uf701': u'\u0e34',
'\uf702': u'\u0e35',
'\uf703': u'\u0e36',
'\uf704': u'\u0e37',
'\uf705': u'\u0e48',
'\uf706': u'\u0e49',
'\uf70a': u'\u0e48',
'\uf70b': u'\u0e49',
'\uf70e': u'\u0e4c',
'\uf710': u'\u0e31',
'\uf712': u'\u0e47',
'\uf713': u'\u0e48',
'\uf714': u'\u0e49'
}
# Correct Thai Sprcial Character Error
special_char_replace = dict(
(re.escape(k), v) for k, v in special_char_replace.items())
pattern = re.compile("|".join(special_char_replace.keys()))
text = pattern.sub(lambda m: special_char_replace[re.escape(m.group(0))],
raw_text)
total_vaccinations_regex = r"ผู้ที่ได้รับวัคซีนสะสม .{1,100} ทั้งหมด[^\d]+([\d,]+) โดส"
total_vaccinations = re.search(total_vaccinations_regex, text).group(1)
total_vaccinations = clean_count(total_vaccinations)
people_vaccinated_regex = r"ผู้ได้รับวัคซีนเข็มที่ 1 .{1,3}นวน[^\d]+([\d,]+) ร.{1,3}ย"
people_vaccinated = re.search(people_vaccinated_regex, text).group(1)
people_vaccinated = clean_count(people_vaccinated)
people_fully_vaccinated_regex = (
r"นวนผู้ได้รับวัคซีนครบต.{1,2}มเกณฑ์ \(ได้รับวัคซีน 2 เข็ม\) .{1,3}นวน[^\d]+([\d,]+)"
)
people_fully_vaccinated = re.search(people_fully_vaccinated_regex,
text).group(1)
people_fully_vaccinated = clean_count(people_fully_vaccinated)
thai_date_regex = r"\( ข้อมูล ณ วันที่ (.{1,30}) เวล(.{1,3}) (.{1,10}) น. \)"
thai_date = re.search(thai_date_regex, text).group(1).replace("ำ", "า")
thai_date_replace = {
"มกราคม": "January",
"กุมภาพันธ์": "February",
"มีนาคม": "March",
"เมษายน": "April",
"พฤษภาคม": "May",
"มิถุนายน": "June",
"กรกฎาคม": "July",
"สิงหาคม": "August",
"กันยายน": "September",
"ตุลาคม": "October",
"พฤศจิกายน": "November",
"ธันวาคม": "December",
"2563": "2020",
"2564": "2021",
"2565": "2022",
"2566": "2023",
"2567": "2024"
}
# Replace Thai Date Format with Standard Date Time Format
thai_date_replace = dict(
(re.escape(k), v) for k, v in thai_date_replace.items())
pattern = re.compile("|".join(thai_date_replace.keys()))
date = pattern.sub(lambda m: thai_date_replace[re.escape(m.group(0))],
thai_date)
date = 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,
"source_url": latest_report_link,
})
def parse_date(soup) -> str:
date_raw = soup.find(class_="download").text
regex = r"(\d{4})\sCOVID-19疫苗日報表"
date_str = re.search(regex, date_raw).group(1)
date_str = clean_date("2021" + date_str, "%Y%m%d")
return date_str
def parse_date(df: pd.DataFrame) -> str:
date = re.search(r"Dati aggiornati al (\d{2}/\d{2}/\d{4})", df).group(1)
return clean_date(date, "%d/%m/%Y")
def parse_date(df: dict) -> str:
date = df["Unnamed: 1"].str.replace("Journée du ", "").values[0]
date = clean_date(date, "%d.%m.%Y")
return date
def parse_date(soup: BeautifulSoup) -> str:
date = re.search(r"Data applies to: Week ending (\d[\w\s]+\d{4})",
soup.text).group(1)
date = str(date)
return clean_date(date, "%d %B %Y")
def parse_date(soup: BeautifulSoup) -> str:
date = soup.find(class_="field-name-post-date").text
date = clean_date(date, "%d.%m.%Y")
return date
