cowidev.testing.incremental

cowidev.testing.incremental.africacdc

class cowidev.testing.incremental.africacdc.AfricaCDC

Bases: CountryTestBase

_base_url = 'https://services8.arcgis.com/vWozsma9VzGndzx7/ArcGIS/rest/services/DailyCOVIDDashboard_5July21_1/FeatureServer/0/'

_parse_data(data) → DataFrame

_parse_date() → str

_parse_metrics(df: list) → DataFrame

columns_use: list = ['Country', 'Tests_Conducted']

date: str = None

export()

increment_countries(df: DataFrame)

Exports data to the relevant csv and logs the confirmation.

location: str = 'ACDC'

pipe_date(df: DataFrame) → DataFrame

pipe_filter_columns(df: DataFrame) → DataFrame

pipe_filter_entries(df: DataFrame) → DataFrame

Gets valid entries:

• Countries not coming from OWID (avoid loop)

pipe_metadata(df: DataFrame) → DataFrame

Adds metadata to DataFrame

pipe_rename_countries(df: DataFrame) → DataFrame

Renames countries to match OWID naming convention.

pipeline(df: DataFrame)

Pipeline for data

read() → DataFrame

rename_columns: dict = {'Country': 'location', 'Tests_Conducted': 'Cumulative total'}

source_label: str = 'Africa Centres for Disease Control and Prevention'

property source_url

property source_url_date

source_url_ref: str = 'https://africacdc.org/covid-19/'

units: str = 'tests performed'

cowidev.testing.incremental.africacdc.main()

cowidev.testing.incremental.albania

class cowidev.testing.incremental.albania.Albania

Bases: object

_base_url = 'https://shendetesia.gov.al'

_get_link_and_date_from_element(elem: Tag) → tuple

Extract link and date from relevant element.

_get_relevant_element(soup: BeautifulSoup) → Tag

Get the relevant element in news feed.

_get_text_from_url(url: str) → str

Extract text from the url.

_num_max_pages = 3

_parse_data(soup: BeautifulSoup) → tuple

Get data from the source page.

_parse_date_from_element(elem: Tag) → str

Get date from relevant element.

_parse_link_from_element(elem: Tag) → str

Get link from relevant element.

_parse_metrics(text: str) → int

Get metrics from news text.

_url_subdirectory = 'category/lajme/page'

export()

location = 'Albania'

notes = ''

read() → Series

regex = {'count': '(\\d+) testime nga të cilat kanë rezultuar pozitivë me COVID19', 'date': '(\\d+\\/\\d+\\/\\d+)', 'title': 'COVID19/ Ministria e Shëndetësisë:'}

source_label = 'Ministry of Health and Social Protection'

units = 'tests performed'

cowidev.testing.incremental.albania.main()

cowidev.testing.incremental.antigua_barbuda

class cowidev.testing.incremental.antigua_barbuda.AntiguaBarbuda

Bases: CountryTestBase

_parse_data(soup: BeautifulSoup) → DataFrame

Parse data from soup

_parse_date(elem: Tag) → str

Parse date from element

_parse_metrics(elem: Tag) → int

Parse metrics from element

export()

Export data to csv

location: str = 'Antigua and Barbuda'

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

source_label: str = 'Ministry of Health'

source_url: str = 'https://covid19.gov.ag'

source_url_ref: str = 'https://covid19.gov.ag'

units: str = 'tests performed'

cowidev.testing.incremental.antigua_barbuda.main()

cowidev.testing.incremental.azerbaijan

class cowidev.testing.incremental.azerbaijan.Azerbaijan

Bases: CountryTestBase

_parse_data(soup: BeautifulSoup) → DataFrame

Parse data from soup

_parse_metrics(elem: Tag) → int

Parse metrics from element

export()

Export data to csv

location: str = 'Azerbaijan'

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

source_label: str = 'Cabinet of Ministers of Azerbaijan'

source_url: str = 'https://koronavirusinfo.az/az/page/statistika/azerbaycanda-cari-veziyyet'

source_url_ref: str = 'https://koronavirusinfo.az/az/page/statistika/azerbaycanda-cari-veziyyet'

units: str = 'tests performed'

cowidev.testing.incremental.azerbaijan.main()

cowidev.testing.incremental.bahamas

class cowidev.testing.incremental.bahamas.Bahamas

Bases: CountryTestBase

_base_url: str = 'https://www.bahamas.gov.bs'

_parse_data(soup: BeautifulSoup) → DataFrame

Parse data from soup

_parse_date(soup: BeautifulSoup) → str

Parse date from soup

_parse_link(soup: BeautifulSoup) → str

Parse the article url from soup

_parse_metrics(table: DataFrame) → int

Parse metrics from table

_parse_pdf_table() → DataFrame

Parse pdf table from link

column_to_check: str = 'Total # of RT-'

export()

Export data to csv

location: str = 'Bahamas'

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

regex: dict = {'title': 'COVID-19 Report Update'}

source_label: str = 'Ministry of Health and Wellness'

source_url: str = 'https://www.bahamas.gov.bs/wps/portal/public/gov/government/news/!ut/p/b1/vZfJkqM4EIafpR6AsiQQgqNYbbMjwOCLwyvewAu2WZ5-XBPTMV3dPa45lI1ORGTGp_xzkdQb99LeuJzeNvn0sjmU0_3H_1ic8MB0KBUkRzJECgYxb_DYorwZwLtBdjcA__FR8NnfxEC8-_s29UkfeRbqjXppP7s22sHJDapM1tko9PXQnUehe92PiHixcwHpzV455OKSSxf2iQgj1TBGDm7ramRfJx1JS7nRrWbu7c6xGJ6yel0dCrnYggBXgCmRml0Pc7FE8z2Ty5tk8Ae7JcoQL1REy3S10QU85IOJ5-mic49bSy4wn825Zi2VYgPBPzE-COJRjBB_4S-A_6fxA8AX_qPe-OEWP3bwt8GjNH6VSLd_KJa97G5GfjKLEgAGENCQwQBILuxFvRQIE7Ztj4Nu14VbULdut3BZ5ADQxSDSUubOdFBdVOjocAh10Dq60EaRYTOwQ8y1_UUSxgpVOU-fnn8FeiiS70AVilaMAQPCs4Em9qS7ECTyKUbA9OCrgfxLJTV9Dzw9wk9FIwTfn8Nhb7yZFe_1vHgH75IsQkwkQZZEIAgS6SXbDBBNGtT6wJ-o1dWVTVwEYFNLRp4F62V8OcyZxbh9CH3On-rVVu-4mV4h61yPd7NAoZvT3rVnXRRKMvCahTkw2Db3g4Oe2lZnBH3BrXWzTgsaJ8Ar2hvHcd5YvRS5m17Xx2V_OYzLhJumHe5OS1_g-dt6tmvNOYG-k11QMuYWFc-z0aoKkRgZZxMKocFWWRpF81Vl-qfL2s3f3h4La1q_12oXoEivkaPXHdwmbqT5gRvvWndhQaYNWmAnAxZltRPfBe4GHbv8EJauHcZmj7tRNfCzgZ-bA1DyYuAfavXJQPHVwGdJGiggYLbMU0AxBoM-iggxYx5g_tURvrpKxVfnUPz-Kv00UXlZJhLEkiBBCUEo9ZJhVsjajtaGPl6F2ZJcyyVix62eVXRzoYBN4nJhmdwti87lSpkgz-ycW07VzbZfcGjYikEXzAJM6K3MjaE6XS5n_WmrHW3zZnt93DqTMY2Si4tnkkayUhGLaHE8-9N0WjoypzbqTVeVEkz44KupKJHfC5yEjrNVrPttooE7hBwtjd3IsJjsQcdO7mcQ6FgMHXcbWmybIeey-iHOPJ9W2Rd3FJN_NvDXqSi-GoifBTQ9J1A_JI2UD0n5fp-KNu_p8NXA78_hp47CAsRYhkgWEUEEko-OaolWDWrt_mgahkiCR5EMpuE1cFZqvhueA5aWh8WaobNU5te95zadt_S5DAf64OTOpjNxEtjtjpLY3NDriCUnLSnIfOvIKjuUOlj5zc7FrWKfV81yhfmDhZrQxEgvjfR8PRX16XStbC297BS8kEHa3GdGTO_ddSzim2XZYtivofTv4ovbH5b0s0n99heUoIvF/dl4/d5/L2dBISEvZ0FBIS9nQSEh/'

source_url_ref: str = None

units: str = 'tests performed'

cowidev.testing.incremental.bahamas.main()

cowidev.testing.incremental.bahrain

class cowidev.testing.incremental.bahrain.Bahrain

Bases: object

_parse_data()

export()

location: str = 'Bahrain'

notes: str = ''

source_label: str = 'Ministry of Health'

source_url: str = 'https://www.moh.gov.bh/COVID19'

testing_type: str = 'PCR only'

units: str = 'units unclear'

cowidev.testing.incremental.bahrain.main()

cowidev.testing.incremental.bangladesh

class cowidev.testing.incremental.bangladesh.Bangladesh

Bases: object

_parse_data()

export()

location: str = 'Bangladesh'

notes: str = ''

source_label: str = 'Government of Bangladesh'

source_url: str = 'https://dghs-dashboard.com/pages/covid19.php'

units: str = 'tests performed'

cowidev.testing.incremental.bangladesh.main()

cowidev.testing.incremental.barbados

class cowidev.testing.incremental.barbados.Barbados

Bases: CountryTestBase

_parse_data(soup: BeautifulSoup) → DataFrame

Parse data from soup

_parse_date(soup: BeautifulSoup) → str

Parse date from soup

_parse_metrics(soup: BeautifulSoup) → int

Parse metrics from soup

export()

Export data to csv

location: str = 'Barbados'

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

regex: dict = {'count': 'has conducted (\\d+) tests', 'title': 'COVID-19 Update'}

source_label: str = 'Ministry of Health'

source_url: str = 'https://gisbarbados.gov.bb/top-stories/'

source_url_ref: str = None

units: str = 'tests performed'

cowidev.testing.incremental.barbados.main()

cowidev.testing.incremental.belarus

class cowidev.testing.incremental.belarus.Belarus

Bases: CountryTestBase

_parse_data(soup: BeautifulSoup) → DataFrame

Parse data from soup

_parse_date(soup: BeautifulSoup) → str

Parse date from soup

_parse_metrics(elem: Tag) → int

Parse metrics from element

export()

Export data to csv

location: str = 'Belarus'

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

regex: dict = {'date': '\\d{1,2}\\.\\d{1,2}\\.\\d{4}г.', 'element': 'ПРОВЕДЕНО ТЕСТОВ'}

source_label: str = 'Ministry of health'

source_url: str = 'https://stopcovid.belta.by/'

source_url_ref: str = 'https://stopcovid.belta.by/'

units: str = 'tests performed'

cowidev.testing.incremental.belarus.main()

cowidev.testing.incremental.belize

class cowidev.testing.incremental.belize.Belize

Bases: CountryTestBase

_parse_data(soup: BeautifulSoup) → DataFrame

Parse data from soup

_parse_date(soup: BeautifulSoup) → str

Parse date from soup

_parse_metrics(elem: Tag) → int

Parse metrics from element

export()

Export data to csv

location: str = 'Belize'

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

regex: dict = {'element': 'Tests Completed'}

source_label: str = 'Ministry of Health and Wellness'

source_url: str = 'https://sib.org.bz/covid-19/by-the-numbers/'

source_url_ref: str = 'https://sib.org.bz/covid-19/by-the-numbers/'

units: str = 'tests performed'

cowidev.testing.incremental.belize.main()

cowidev.testing.incremental.benin

class cowidev.testing.incremental.benin.Benin

Bases: CountryTestBase

export()

location: str = 'Benin'

cowidev.testing.incremental.benin.main()

cowidev.testing.incremental.bulgaria

class cowidev.testing.incremental.bulgaria.Bulgaria

Bases: object

_parse_count(soup)

_parse_data()

export()

location: str = 'Bulgaria'

source_label: str = 'Bulgaria COVID-10 Information Portal'

source_url: str = 'https://coronavirus.bg/bg/statistika'

units: str = 'tests performed'

cowidev.testing.incremental.bulgaria.main()

cowidev.testing.incremental.cambodia

class cowidev.testing.incremental.cambodia.Cambodia

Bases: CountryTestBase

export()

location: str = 'Cambodia'

cowidev.testing.incremental.cambodia.main()

cowidev.testing.incremental.cape_verde

class cowidev.testing.incremental.cape_verde.CapeVerde

Bases: object

_get_relevant_element(soup: BeautifulSoup) → Tag

Get the relevant element from the source page.

_get_text_from_url(url: str) → str

Extract text from the url.

_parse_data(soup: BeautifulSoup) → dict

Get data from the source page.

_parse_date(text: str) → str

Get date from relevant element.

_parse_link_from_element(elem: Tag) → str

Get link from relevant element.

_parse_metrics(text: str) → int

Get metrics from the text.

export()

Export data to CSV.

location = 'Cape Verde'

read() → Series

Read data from source.

regex = {'count': '(?:total|totais) (?:de|dos|das) (\\d+) (?:resultados|amostras)', 'date': '(\\d+) (?:de )?(\\w+) de (20\\d+)'}

source_label = 'Government of Cape Verde'

source_url = 'https://covid19.cv/category/boletim-epidemiologico/'

units = 'tests performed'

cowidev.testing.incremental.cape_verde.main()

cowidev.testing.incremental.croatia

class cowidev.testing.incremental.croatia.Croatia

Bases: CountryTestBase

_get_relevant_element(driver: WebDriver) → WebElement

Get the relevant element

_get_text_from_element(elem: WebElement) → str

Extract text from the element.

_parse_data(driver: WebDriver) → dict

Get data from the source page.

_parse_date_from_text(text: str) → str

Get date from text.

_parse_metrics(text: str) → int

Get metrics from text.

export()

location: str = 'Croatia'

read() → Series

Read data from source.

regex = {'count': 'Do danas je ukupno testirano ([\\d\\.]+) osoba', 'date': 'Objavljeno: ([\\d\\.]{10})'}

source_label: str = 'Government of Croatia'

source_url_ref: str = 'https://www.koronavirus.hr/najnovije/ukupno-dosad-382-zarazene-osobe-u-hrvatskoj/35'

units: str = 'people tested'

cowidev.testing.incremental.croatia.main()

cowidev.testing.incremental.el_salvador

class cowidev.testing.incremental.el_salvador.ElSalvador

Bases: CountryTestBase

_get_data_id_from_source(source_url: str) → str

Get Data ID from source

_load_data(data_id: str) → DataFrame

Load data from source

export()

Export data to csv

location: str = 'El Salvador'

pipe_date(df: DataFrame) → DataFrame

Clean date

pipe_merge(df: DataFrame) → DataFrame

pipe_numeric(df: DataFrame) → DataFrame

Clean numeric columns

pipe_positive(df: DataFrame) → DataFrame

pipe_pr(df: DataFrame) → DataFrame

Calculate Positive Rate

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

regex: dict = {'element': 'window\\.infographicData=({.*})', 'title': "\\'PRUEBAS REALIZADAS\\'\\, \\'CASOS POSITIVOS\\'"}

rename_columns: dict = {'CASOS POSITIVOS': 'positive', 'PRUEBAS REALIZADAS': 'Daily change in cumulative total'}

source_label: str = 'Government of El Salvador'

source_url: str = 'https://e.infogram.com/'

source_url_ref: str = 'https://covid19.gob.sv/'

units: str = 'tests performed'

cowidev.testing.incremental.el_salvador.main()

cowidev.testing.incremental.emro

class cowidev.testing.incremental.emro.EMRO

Bases: CountryTestBase

_base_url: str = 'http://www.emro.who.int'

_parse_data(soup: BeautifulSoup) → DataFrame

Parses data from soup

_parse_date(df_list: list) → str

Parses date from DataFrame list

_parse_metrics(df_list: list) → DataFrame

Parses metrics from DataFrame list

_parse_pdf_table() → list

Parses pdf table

_parse_pdf_url(soup: BeautifulSoup) → str

Parses pdf url from soup

property area: list

Areas of pdf to be extracted

Returns:

[[y1, x1, y2, x2], …]

Return type:

list

For more info see: https://github.com/tabulapdf/tabula-java/wiki/Using-the-command-line-tabula-extractor-tool

columns_to_check: dict = {'date': 'Table 1: Epidemiological situation in the Eastern Mediterranean Region', 'tests': 'Total Tests'}

columns_use: list = ['Country', 'Total Tests']

date: str = None

export()

Exports data to csv.

increment_countries(df: DataFrame)

Exports data to the relevant csv and logs the confirmation.

location: str = 'EMRO'

pipe_filter_entries(df: DataFrame) → DataFrame

Gets valid entries:

• Countries not coming from OWID (avoid loop)

pipe_metadata(df: DataFrame) → DataFrame

Adds metadata to DataFrame

pipe_rename_countries(df: DataFrame) → DataFrame

Renames countries to match OWID naming convention.

pipeline(df: DataFrame)

Pipeline for data

read() → DataFrame

Reads data from source.

regex: dict = {'date': '(\\d{1,2} \\w+ 20\\d{2})'}

rename_columns: dict = {'Country': 'location', 'Total Tests': 'Cumulative total'}

source_label: str = 'WHO Regional Office for the Eastern Mediterranean'

source_url: str = 'http://www.emro.who.int/health-topics/corona-virus/situation-reports.html'

units: str = 'tests performed'

cowidev.testing.incremental.emro.main()

cowidev.testing.incremental.equatorial_guinea

class cowidev.testing.incremental.equatorial_guinea.EquatorialGuinea

Bases: CountryTestBase

export()

location: str = 'Equatorial Guinea'

cowidev.testing.incremental.equatorial_guinea.main()

cowidev.testing.incremental.faeroe_islands

class cowidev.testing.incremental.faeroe_islands.FaeroeIslands

Bases: object

_parse_data() → Series

export()

location: str = 'Faeroe Islands'

notes: str = ''

source_label: str = 'The Government of the Faeroe Islands'

source_url: str = 'https://corona.fo/json/stats'

source_url_ref: str = 'https://corona.fo/api'

units: str = 'people tested'

cowidev.testing.incremental.faeroe_islands.main()

cowidev.testing.incremental.fiji

class cowidev.testing.incremental.fiji.Fiji

Bases: object

__element = None

_get_list_of_elements(soup: BeautifulSoup) → None

Get the relevant elements list from the source page.

_get_relevant_element_and_year() → tuple

Get the relevant element and year from the element list.

_get_text_from_url(url: str) → str

Extract text from the url.

_num_max_pages = 3

_num_rows_per_page = 3

_parse_data(soup: BeautifulSoup) → tuple

Get data from the source page.

_parse_date_from_text(year: str, text: str) → str

Get date from relevant element.

_parse_link_from_element(elem: Tag) → str

Get link from relevant element.

_parse_metrics(text: str) → int

Get metrics from news text.

export()

Export data to csv.

location = 'Fiji'

notes = ''

read() → Series

Read data from source.

regex = {'count': 'tests since 2020 are (\\d+,\\d+)', 'date': 'tests have been reported for (\\w+ \\d+)', 'title': 'COVID-19 Update', 'year': '\\d{4}'}

source_label = 'Fiji Ministry of Health & Medical Services'

source_url = 'https://www.health.gov.fj/page/'

units = 'tests performed'

cowidev.testing.incremental.fiji.main()

cowidev.testing.incremental.georgia

class cowidev.testing.incremental.georgia.Georgia

Bases: object

_base_url = 'https://agenda.ge'

_get_link_and_date_from_element(elem: Tag) → tuple

Extract link and date from relevant element.

_get_relevant_element(soup: BeautifulSoup) → Tag

Get the relevant element in news feed.

_get_text_from_url(url: str) → str

Extract text from the url.

_num_max_pages = 3

_parse_data(soup: BeautifulSoup) → tuple

Get data from the source page.

_parse_date_from_element(elem: Tag) → str

Get date from relevant element.

_parse_link_from_element(elem: Tag) → str

Get link from relevant element.

_parse_metrics(text: str) → int

Get metrics from news text.

_url_query_pt1 = 'https://agenda.ge/ajax/get-nodes?pageOptions%5Btag%5D=&pageOptions%5Byear%5D=2022&pageOptions%5Btype%5D=news&pageOptions%5Blang%5D=en&listOptions%5Byear%5D=all&listOptions%5Bmonth%5D=0&listOptions%5Bday%5D=0&listOptions%5Bpage%5D='

_url_query_pt2 = '&listOptions%5Bcount%5D=16&listOptions%5Brange%5D=all&listOptions%5Brows%5D=4&listOptions%5Bcolumns%5D=4&listOptions%5Brubric%5D=&listOptions%5Bcategory%5D='

export()

location = 'Georgia'

notes = ''

read() → Series

regex = {'count': '(\\d+) tests .*? 24 hours', 'date': '(\\d+ \\w+ \\d+)', 'title': '(Georgia reports)|(coronavirus)'}

source_label = 'Government of Georgia'

units = 'tests performed'

cowidev.testing.incremental.georgia.main()

cowidev.testing.incremental.gibraltar

class cowidev.testing.incremental.gibraltar.Gibraltar

Bases: CountryTestBase

_parse_data(soup: BeautifulSoup) → DataFrame

Parse data from soup

_parse_date(text: str) → str

Parse date from text

_parse_metrics(text: str) → int

Parse metrics from text

export()

Export data to csv

location: str = 'Gibraltar'

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

regex: dict = {'count': 'Results received: ([\\d,]+)', 'date': 'valid as of (\\d{1,2})\\w+ (\\w+ 20\\d{2})'}

source_label: str = 'The Department of Public Health'

source_url: str = 'https://healthygibraltar.org/news/update-on-wuhan-coronavirus/'

source_url_ref: str = 'https://healthygibraltar.org/news/update-on-wuhan-coronavirus/'

units: str = 'tests performed'

cowidev.testing.incremental.gibraltar.main()

cowidev.testing.incremental.greece

class cowidev.testing.incremental.greece.Greece

Bases: CountryTestBase

_parse_data(soup: BeautifulSoup) → DataFrame

Parse data from soup

_parse_date(soup: BeautifulSoup) → str

Parse date from soup

_parse_metrics(elem: Tag) → int

Parse metrics from element

export()

Export data to csv

location: str = 'Greece'

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

regex: dict = {'date': 'elementor-element-5b9d061', 'element': 'elementor-element-9df72a6'}

source_label: str = 'National Organization of Public Health'

source_url: str = 'https://covid19.gov.gr/'

source_url_ref: str = 'https://covid19.gov.gr/'

units: str = 'samples tested'

cowidev.testing.incremental.greece.main()

cowidev.testing.incremental.haiti

class cowidev.testing.incremental.haiti.Haiti

Bases: CountryTestBase

_extract_text_from_url() → str

Extracts text from pdf.

_parse_data(soup: BeautifulSoup) → DataFrame

Parses data from soup.

_parse_date(link: str) → str

Gets date from link.

_parse_metrics(text: str) → DataFrame

Parses metrics from data.

export()

Exports data to CSV.

location: str = 'Haiti'

pipe_date(df: DataFrame) → DataFrame

Pipes date.

pipeline(df: DataFrame) → DataFrame

Pipeline for data.

read() → DataFrame

Reads data from source.

regex: dict = {'date': '(\\d{1,2}\\-\\d{1,2}\\-20\\d{2})', 'metrics': 'INDICATEURS ([\\d,]+)', 'title': 'surveillance du nouveau Coronavirus \\(COVID-19\\)'}

source_label: str = 'Ministry of Public Health and Population'

source_url: dict = 'https://www.mspp.gouv.ht/documentation/'

source_url_ref: str = None

units: str = 'tests performed'

cowidev.testing.incremental.haiti.main()

cowidev.testing.incremental.iran

class cowidev.testing.incremental.iran.Iran

Bases: object

_base_url = 'https://irangov.ir'

_get_link_and_date_from_element(elem: Tag) → tuple

Extract link and date from relevant element.

_get_relevant_element(soup: BeautifulSoup) → Tag

Get the relevant element in news feed.

_get_text_from_url(url: str) → str

Extract text from the url.

_num_max_pages = 3

_parse_data(soup: BeautifulSoup) → tuple

Get data from the source page.

_parse_date_from_element(elem: Tag) → str

Get date from relevant element.

_parse_link_from_element(elem: Tag) → str

Get link from relevant element.

_parse_metrics(text: str) → int

Get metrics from news text.

_url_subdirectory = 'ministry-of-health-and-medical-education'

export()

location = 'Iran'

notes = ''

read() → Series

regex = {'count': '(\\d+) COVID-19 tests have been taken across the country so far', 'date': '(\\d+\\-\\d+\\-\\d+)', 'title': "Health Ministry's Updates on COVID-19"}

source_label = 'Ministry of Health and Medical Education'

units = 'tests performed'

cowidev.testing.incremental.iran.main()

cowidev.testing.incremental.jordan

class cowidev.testing.incremental.jordan.Jordan

Bases: CountryTestBase

_df_builder(count: str) → DataFrame

Builds dataframe from the text data

_request() → dict

Requests data from source.

_week_to_date(week: int) → str

Converts week to date.

export()

Exports data to CSV.

property headers

Headers for the request

location: str = 'Jordan'

notes: str = ''

payload(week: str | None = None) → dict

Request payload

pipe_date(df: DataFrame) → DataFrame

Pipes date.

pipeline(df: DataFrame) → DataFrame

Pipeline for data.

read() → DataFrame

Reads the data from the source

source_label: str = 'Ministry of Health'

source_url: str = 'https://wabi-west-europe-d-primary-api.analysis.windows.net/public/reports/querydata?synchronous=true'

source_url_ref: str = 'https://corona.moh.gov.jo/ar'

units: str = 'tests performed'

week: str = 33

cowidev.testing.incremental.jordan.main()

cowidev.testing.incremental.kosovo

class cowidev.testing.incremental.kosovo.Kosovo

Bases: CountryTestBase

_parse_data(driver: WebDriver) → DataFrame

Parse data from source

_parse_date(date: str) → str

Parse date from soup

export()

Export data to csv

location: str = 'Kosovo'

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

regex: dict = {'count': 'Gjithsej të testuar', 'date': 'Përditësimi i fundit:'}

source_label: str = 'National Institute of Public Health of Kosovo'

source_url: str = 'https://datastudio.google.com/embed/u/0/reporting/2e546d77-8f7b-4c35-8502-38533aa0e9e8/page/tI3oB'

source_url_ref: str = 'https://datastudio.google.com/embed/u/0/reporting/2e546d77-8f7b-4c35-8502-38533aa0e9e8'

units: str = 'tests performed'

cowidev.testing.incremental.kosovo.main()

cowidev.testing.incremental.laos

class cowidev.testing.incremental.laos.Laos

Bases: object

_get_relevant_element(soup: BeautifulSoup) → Tag

Gets element from the soup.

_get_text_from_element(elem: Tag) → str

Gets text from element.

_parse_data(soup: BeautifulSoup) → dict

Gets data from the source page.

_parse_date(text: str) → str

Gets date from the text.

_parse_metrics(text: str) → int

Gets metrics from the text.

_source_url = 'https://www.covid19.gov.la/index.php'

export()

Exports data to csv.

location = 'Laos'

notes = ''

read() → Series

Reads data from source.

regex = {'date': 'ຂໍ້ມູນ ເວລາ .*? (\\d+\\/\\d+\\/\\d+)', 'tests': 'ຮັບການກວດມື້ນີ້ (\\d+)'}

source_label = 'Ministry of Health'

units = 'tests performed'

cowidev.testing.incremental.laos.main()

cowidev.testing.incremental.lebanon

class cowidev.testing.incremental.lebanon.Lebanon

Bases: object

_parse_count(soup: str) → str

_parse_date(soup: str) → str

export()

location = 'Lebanon'

notes = ''

read()

regex = {'date': '([A-Za-z]+ \\d+)'}

source_label = 'Lebanon Ministry of Health'

source_url = 'https://corona.ministryinfo.gov.lb/'

units = 'tests performed'

cowidev.testing.incremental.lebanon.main()

cowidev.testing.incremental.libya

class cowidev.testing.incremental.libya.Libya

Bases: object

_get_relevant_element(soup: BeautifulSoup) → Tag

Get the relevant element in soup.

_parse_data(soup: BeautifulSoup) → dict

Get data from the source page.

_parse_date_from_soup(soup: BeautifulSoup) → str

Get date from soup.

_parse_metrics(elem: Tag) → int

Get metrics from element.

export()

location = 'Libya'

notes = ''

read() → Series

Read data from source.

regex = {'date': '(\\d+ \\/ \\d+ \\/ \\d+.)', 'samples': 'عدد العينات'}

source_label = 'Libya National Centre for Disease Control'

source_url = 'https://ncdc.org.ly/Ar'

units = 'samples tested'

cowidev.testing.incremental.libya.main()

cowidev.testing.incremental.maldives

class cowidev.testing.incremental.maldives.Maldives

Bases: CountryTestBase

_parse_data(data: dict) → DataFrame

Parse data.

export()

Export data to CSV.

location: str = 'Maldives'

pipeline(df: DataFrame) → DataFrame

Pipeline for data.

read() → DataFrame

Read data from source.

regex: dict = {'date': '(\\d{1,2}\\/\\d{1,2}\\/20\\d{2})'}

source_label: str = 'Maldives Health Protection Agency'

source_url: str = 'https://covid19.health.gov.mv/v2_data.json'

source_url_ref: str = 'https://covid19.health.gov.mv/en'

units: str = 'samples tested'

cowidev.testing.incremental.maldives.main()

cowidev.testing.incremental.moldova

class cowidev.testing.incremental.moldova.Moldova

Bases: object

_get_relevant_element(soup: BeautifulSoup) → Tag

Get the relevant element in news feed.

_get_text_from_url(url: str) → str

Extract text from the url.

_parse_data(soup: BeautifulSoup) → tuple

Get data from the source page.

_parse_date_from_text(text: str) → str

Get date from text.

_parse_metrics(text: str) → int

Get metrics from news text.

export()

Export data to CSV.

location = 'Moldova'

notes = ''

read() → Series

Read data from source.

regex = {'count': '((\\d+)) teste.|(\\d+) de teste', 'date': '(\\d+\\/\\d+\\/\\d+)', 'title': '(cazuri noi de COVID-19)|(cazuri de COVID-19)|(cazuri de COVID-19,)'}

source_label = 'Ministry of Health of the Republic of Moldova'

source_url = 'https://msmps.gov.md/media/comunicate/'

units = 'tests performed'

cowidev.testing.incremental.moldova.main()

cowidev.testing.incremental.mongolia

class cowidev.testing.incremental.mongolia.Mongolia

Bases: object

export()

location = 'Mongolia'

notes = ''

read()

source_label = 'Ministry of Health'

source_url = 'https://e-mongolia.mn/shared-api/api/covid-stat/daily'

source_url_ref = 'https://www1.e-mongolia.mn/covid-19'

units = 'samples tested'

cowidev.testing.incremental.mongolia.main()

cowidev.testing.incremental.morocco

class cowidev.testing.incremental.morocco.Morocco

Bases: CountryTestBase

_parse_data(soup: BeautifulSoup) → DataFrame

Parse data from soup

_parse_date(soup: BeautifulSoup) → str

Parse date from soup

_parse_metrics(soup: BeautifulSoup) → int

Parse metrics from soup

export()

Export data to csv

location: str = 'Morocco'

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

regex: dict = {'count': '\\s+', 'date': '00 (\\d{1,2}\\-\\d{2}\\-20\\d{2})'}

source_label: str = 'Ministry of Health'

source_url: str = 'http://www.covidmaroc.ma/Pages/AccueilAR.aspx'

source_url_ref: str = 'http://www.covidmaroc.ma/Pages/AccueilAR.aspx'

units: str = 'people tested'

cowidev.testing.incremental.morocco.main()

cowidev.testing.incremental.myanmar

class cowidev.testing.incremental.myanmar.Myanmar

Bases: CountryTestBase

_parse_date(soup: BeautifulSoup) → str

Parse date from soup

export()

Export data to csv

location: str = 'Myanmar'

pipe_metrics(df: DataFrame) → DataFrame

Parse metrics from source

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

regex: dict = {'date': 'as of (\\d{1,2}\\-\\d{1,2}\\-20\\d{2})'}

source_label: str = 'Ministry of Health'

source_url: str = 'https://services7.arcgis.com/AB2LoFxJT2bJUJYC/arcgis/rest/services/CaseCount_130720/FeatureServer/0/query?f=json&where=1%3D1&returnGeometry=false&spatialRel=esriSpatialRelIntersects&outFields=*&outStatistics=%5B%7B%22statisticType%22%3A%22sum%22%2C%22onStatisticField%22%3A%22Tested%22%2C%22outStatisticFieldName%22%3A%22value%22%7D%5D&resultType=standard'

source_url_ref: str = 'https://mohs.gov.mm/Main/content/publication/2019-ncov'

units: str = 'samples tested'

cowidev.testing.incremental.myanmar.main()

cowidev.testing.incremental.nepal

class cowidev.testing.incremental.nepal.Nepal

Bases: CountryTestBase

_extract_text_from_url() → str

Extracts text from pdf.

_parse_data(links: dict) → DataFrame

Parses data from link.

_parse_date(link: str) → str

Get date from link.

_parse_metrics(text: str) → DataFrame

Parses metrics from data.

export()

Exports data to CSV.

location: str = 'Nepal'

pipe_date(df: DataFrame) → DataFrame

Pipes date.

pipe_pr(df: DataFrame) → DataFrame

Calculate Positive Rate

pipeline(df: DataFrame) → DataFrame

Pipeline for data.

read() → DataFrame

Reads data from source.

regex: dict = {'date': '(\\d{1,2}\\-\\d{1,2}\\-20\\d{2})', 'metrics': 'PCR \\| Antigen (\\d+) (\\d+) PCR \\| Antigen (\\d+) (\\d+)'}

source_label: str = 'Ministry of Health and Population'

source_url: dict = {'api': 'https://covid19.mohp.gov.np/covid/api/ministryrelease', 'base': 'https://covid19.mohp.gov.np/covid/englishSituationReport/'}

source_url_ref: str = None

units: str = 'samples tested'

cowidev.testing.incremental.nepal.main()

cowidev.testing.incremental.new_zealand

class cowidev.testing.incremental.new_zealand.NewZealand

Bases: object

_parse_date()

_parse_metric()

export()

location = 'New Zealand'

notes = ''

read()

source_label = 'Ministry of Health'

source_url = 'https://www.health.govt.nz/our-work/diseases-and-conditions/covid-19-novel-coronavirus/covid-19-data-and-statistics/covid-19-testing-data'

units = 'tests performed'

cowidev.testing.incremental.new_zealand.main()

cowidev.testing.incremental.nicaragua

class cowidev.testing.incremental.nicaragua.Nicaragua

Bases: CountryTestBase

_base_url: str = 'http://www.minsa.gob.ni/index.php/repository/func-download'

_extract_text_from_url(link) → str

Extracts text from pdf.

_get_download_url(soup: BeautifulSoup) → str

_parse_data(soup: BeautifulSoup) → DataFrame

Parse data from soup

_parse_date(soup: BeautifulSoup) → Iterator

parses the date from the week number.

export()

location: str = 'Nicaragua'

pipeline(df: DataFrame) → DataFrame

read() → DataFrame

Read data from source

regex: dict = {'title': 'Boletín Epidemiológico de la Semana No. '}

source_label: str = 'Ministry of Health'

source_url_ref: str = 'http://www.minsa.gob.ni/index.php/repository/Descargas-MINSA/COVID-19/Boletines-Epidemiol%C3%B3gico/Boletines-2022/'

units: str = 'tests performed'

cowidev.testing.incremental.nicaragua.main()

cowidev.testing.incremental.north_macedonia

class cowidev.testing.incremental.north_macedonia.NorthMacedonia

Bases: CountryTestBase

_parse_data(soup: BeautifulSoup) → DataFrame

Parse data from soup

_parse_date(soup: BeautifulSoup) → str

Parse date from soup

_parse_metrics(soup: BeautifulSoup) → int

Parse metrics from soup

export()

Export data to csv

location: str = 'North Macedonia'

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

regex: dict = {'count': 'Досега во земјата се направени вкупно (\\d+)', 'date': '(\\d{1,2}.\\d{2}.\\d{4})'}

source_label: str = 'Ministry of Health'

source_url: str = 'https://koronavirus.gov.mk/vesti'

source_url_ref: str = 'https://koronavirus.gov.mk/vesti'

units: str = 'tests performed'

cowidev.testing.incremental.north_macedonia.main()

cowidev.testing.incremental.pakistan

class cowidev.testing.incremental.pakistan.Pakistan

Bases: object

_get_relevant_element(soup: BeautifulSoup) → Tag

Get the relevant element from soup.

_parse_data(soup: BeautifulSoup) → dict

Get data from the source page.

_parse_date_from_soup(soup: BeautifulSoup) → str

Get date from soup.

_parse_metrics(elem: Tag) → int

Get metrics from element.

export()

Export data to csv.

location = 'Pakistan'

notes = ''

read() → Series

Read data from source.

regex = {'count': 'Total Tests', 'date': '(\\d+ \\w+, \\d+)', 'header': 'Pakistan statistics '}

source_label = 'Government of Pakistan'

source_url = 'http://www.covid.gov.pk/'

units = 'tests performed'

cowidev.testing.incremental.pakistan.main()

cowidev.testing.incremental.palau

class cowidev.testing.incremental.palau.Palau

Bases: CountryTestBase

_parse_data(soup: BeautifulSoup) → tuple

Gets pdf url

_parse_metrics(text: str) → tuple

Get metrics from report text.

export()

location: str = 'Palau'

read() → Series

regex: dict = {'count': '((\\d+),(\\d+))COVID-19 Testsconducted \\(since', 'date': '(\\d{1,2} \\w+ 20\\d{2})'}

source_label: str = 'Ministry of Health and Human Services'

source_url: str = 'http://www.palauhealth.org/'

source_url_ref: str = ''

units: str = 'tests performed'

cowidev.testing.incremental.palau.main()

cowidev.testing.incremental.papua_new_guinea

class cowidev.testing.incremental.papua_new_guinea.PapuaNewGuinea

Bases: object

_parse_count(soup: str) → str

_parse_date(soup: str) → str

export()

location = 'Papua New Guinea'

notes = ''

read()

regex = {'date': '\\d{1,2}[a-z]{2} [A-Za-z]+ \\d{4}'}

source_label = 'Ministry of Health'

source_url = 'https://covid19.info.gov.pg/'

source_url_ref = 'https://covid19.info.gov.pg/'

units = 'people tested'

cowidev.testing.incremental.papua_new_guinea.main()

cowidev.testing.incremental.paraguay

class cowidev.testing.incremental.paraguay.Paraguay

Bases: CountryTestBase

_parse_data(url: str) → DataFrame

Parse data from url

_parse_date(t_scraper: TableauScraper) → str

Parse date from TableauScraper

_parse_metrics(t_scraper: TableauScraper) → int

Parse metrics from TableauScraper

export()

Export data to csv

location: str = 'Paraguay'

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

source_label: str = 'Ministry of Public Health and Social Welfare'

source_url: str = 'https://public.tableau.com/views/COVID-19PYTableauPublic/COVID-19Prensa'

source_url_ref: str = 'https://www.mspbs.gov.py/reporte-covid19.html'

units: str = 'tests performed'

cowidev.testing.incremental.paraguay.main()

cowidev.testing.incremental.russia

class cowidev.testing.incremental.russia.Russia

Bases: object

_base_url = 'https://rospotrebnadzor.ru'

_get_link_from_element(elem: Tag) → str

Get link from relevant element.

_get_relevant_element(soup: BeautifulSoup) → Tag

Get the relevant element in news feed.

_get_text_and_date_from_url(url: str) → tuple

Extract text from the url.

_num_max_pages = 3

_parse_data(soup: BeautifulSoup) → tuple

Get data from the source page.

_parse_date(soup: BeautifulSoup) → str

Get date from relevant element.

_parse_metrics(text: str) → int

Get metrics from news text.

_url_subdirectory = '/about/info/news/?PAGEN_1='

export()

location = 'Russia'

notes = ''

read() → Series

regex = {'count': 'проведено (\\d+).* исследовани', 'date': '(\\d+ \\d+ \\d+)', 'title': 'Информационный бюллетень о ситуации'}

source_label = 'Government of the Russian Federation'

units = 'tests performed'

cowidev.testing.incremental.russia.main()

cowidev.testing.incremental.saint_kitts_nevis

class cowidev.testing.incremental.saint_kitts_nevis.SaintKittsNevis

Bases: CountryTestBase

_parse_data(soup: BeautifulSoup) → DataFrame

Parse data from soup

_parse_date(soup: BeautifulSoup) → str

Parse date from soup

_parse_metrics(elem: Tag) → int

Parse metrics from element

export()

Export data to csv

location: str = 'Saint Kitts and Nevis'

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

regex: dict = {'element': 'No. of Persons Tested'}

source_label: str = 'Ministry of Health'

source_url: str = 'https://covid19.gov.kn/src/stats2/'

source_url_ref: str = 'https://covid19.gov.kn/src/stats2/'

units: str = 'people tested'

cowidev.testing.incremental.saint_kitts_nevis.main()

cowidev.testing.incremental.saint_lucia

class cowidev.testing.incremental.saint_lucia.SaintLucia

Bases: CountryTestBase

_parse_data(soup: BeautifulSoup) → DataFrame

Parse data from soup

_parse_date(soup: BeautifulSoup) → str

Parse date from soup

_parse_metrics(soup: BeautifulSoup) → int

Parse metrics from soup

export()

Export data to csv

location: str = 'Saint Lucia'

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

regex: dict = {'date': 'As of .*? (\\w+ \\d{1,2}, 20\\d{2})'}

source_label: str = 'Ministry of Health and Wellness'

source_url_ref: str = 'https://www.covid19response.lc/'

units: str = 'tests performed'

cowidev.testing.incremental.saint_lucia.main()

cowidev.testing.incremental.saint_vincent_and_the_grenadines

class cowidev.testing.incremental.saint_vincent_and_the_grenadines.SaintVincentAndTheGrenadines

Bases: CountryTestBase

_extract_text_from_pdf() → str

Extract text from pdf.

_parse_data(soup: BeautifulSoup) → DataFrame

Parse data from soup.

_parse_date(text: str) → str

Get date from text.

_parse_link(soup: BeautifulSoup, regex: str) → str

Parse link from soup.

_parse_metrics(text: str) → DataFrame

Parse metrics from data.

export()

Export data to CSV.

location: str = 'Saint Vincent and the Grenadines'

pipeline(df: DataFrame) → DataFrame

Pipeline for data.

read() → DataFrame

Read data from source.

regex: dict = {'ag': 'today  Total Rapid Ag \\(.*?\\)  [\\d,]+  ([\\d,]+)', 'date': '(\\w+ \\d{1,2} 20\\d{2})', 'pcr': 'Total PCR Tests done  ([\\d,]+)', 'pdf': 'Please click for full details', 'title': 'COVID-19 Report'}

source_label: str = 'Ministry of Health, Wellness and the Environment'

source_url: dict = 'http://health.gov.vc/health/index.php/c'

source_url_ref: str = None

units: str = 'tests performed'

cowidev.testing.incremental.saint_vincent_and_the_grenadines.main()

cowidev.testing.incremental.singapore

class cowidev.testing.incremental.singapore.Singapore

Bases: CountryTestBase

_build_df(data: dict) → DataFrame

_load_last_date() → str

Loads the last date from the datafile.

_parse_data() → list

_read_art()

_read_pcr()

export()

Exports data to csv.

location: str = 'Singapore'

read() → DataFrame

Reads data from source.

source_label: str = 'Ministry of Health Singapore'

source_url: str = 'https://www.moh.gov.sg/covid-19/statistics'

units: str = 'samples tested'

cowidev.testing.incremental.singapore.main()

cowidev.testing.incremental.suriname

class cowidev.testing.incremental.suriname.Suriname

Bases: CountryTestBase

export()

Export data to csv

location: str = 'Suriname'

pipe_pr(df: DataFrame) → DataFrame

Calculate Positive Rate

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

source_label: str = 'Directorate National Security'

source_url: str = 'https://covid-19.sr/'

source_url_ref: str = 'https://covid-19.sr/'

units: str = 'tests performed'

cowidev.testing.incremental.suriname.main()

cowidev.testing.incremental.sweden

class cowidev.testing.incremental.sweden.Sweden

Bases: CountryTestBase

_build_df(data: dict) → DataFrame

Builds dataframe from data.

_get_relevant_element(soup: BeautifulSoup) → Tag

Gets element from the soup.

_get_text_from_element(elem: Tag) → str

Gets text from element.

_get_week_num_from_element(elem: Tag) → int

Gets week number from element.

_load_last_date() → str

Loads the last date from the datafile.

_parse_data(soup: BeautifulSoup) → list

Gets data from the source page.

_parse_date(week_num) → Iterator

parses the date from the week number.

_parse_metrics(text: str, week_num) → int

Gets metrics from the text.

export()

Exports data to csv.

location: str = 'Sweden'

notes: str = ''

read() → DataFrame

Reads data from source.

regex = {'title': 'Antalet testade individer och genomförda test per', 'week': '[vV]ecka (\\d+)'}

source_label: str = 'Swedish Public Health Agency'

source_url: str = 'https://www.folkhalsomyndigheten.se/smittskydd-beredskap/utbrott/aktuella-utbrott/covid-19/statistik-och-analyser/antalet-testade-for-covid-19/'

units: str = 'tests performed'

cowidev.testing.incremental.sweden.main()

cowidev.testing.incremental.syria

class cowidev.testing.incremental.syria.Syria

Bases: CountryTestBase

_get_link_and_date_from_element(elem: Tag) → tuple

Extract link and date from relevant element.

_get_relevant_element(soup: BeautifulSoup) → Tag

Parses pdf url from soup

_parse_data(soup: BeautifulSoup) → tuple

Parses data from soup

_parse_date_from_element(elem: Tag) → str

Get date from relevant element.

_parse_link_from_element(elem: Tag) → str

Get link from relevant element.

_parse_metrics(text: str) → int

Get metrics from report text.

_parse_pdf_url(pdf_url: str) → str

Parses pdf text

export()

Export data to csv.

location: str = 'Syria'

read() → Series

Read data from source.

regex: dict = {'count': 'Total Test (\\d+) (\\d+)', 'date': '(\\d{1,2} \\w+ 20\\d{2})'}

source_label: str = 'WHO Syrian Arab Republic'

source_url: str = 'https://reliefweb.int/updates?advanced-search=%28C226%29_%28S1275%29_%28DT4642%29_%28T4595%29_%28F10%29'

units: str = 'tests performed'

cowidev.testing.incremental.syria.main()

cowidev.testing.incremental.timor

class cowidev.testing.incremental.timor.TimorLeste

Bases: CountryTestBase

_parse_data(soup: BeautifulSoup) → DataFrame

Parse data from soup

_parse_date(soup: BeautifulSoup) → str

Parse date from soup

_parse_metrics(elem: Tag) → int

Parse metrics from element

export()

Export data to csv

location: str = 'Timor'

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

regex: dict = {'date': '(\\w+ \\d{1,2}, \\d{4})', 'element': 'Komulativo Teste'}

source_label: str = 'Ministry of Health'

source_url: str = 'https://covid19.gov.tl/dashboard/'

source_url_ref: str = 'https://covid19.gov.tl/dashboard/'

units: str = 'tests performed'

cowidev.testing.incremental.timor.main()

cowidev.testing.incremental.togo

class cowidev.testing.incremental.togo.Togo

Bases: CountryTestBase

_parse_data(soup: BeautifulSoup) → DataFrame

Parse data from soup

_parse_date(soup: BeautifulSoup) → str

Parse date from soup

_parse_metrics(soup: BeautifulSoup) → int

Parse metrics from soup

export()

Export data to csv

location: str = 'Togo'

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

regex: dict = {'count': 'Nombre total ', 'date': '(\\d{1,2} \\w+ 20\\d{2})'}

source_label: str = 'Ministry of Health'

source_url: str = 'https://covid19.gouv.tg/'

source_url_ref: str = 'https://covid19.gouv.tg/'

units: str = 'tests performed'

cowidev.testing.incremental.togo.main()

cowidev.testing.incremental.tunisia

class cowidev.testing.incremental.tunisia.Tunisia

Bases: CountryTestBase

_parse_data(soup: BeautifulSoup) → DataFrame

Parse data from soup

_parse_date(soup: BeautifulSoup) → str

Parse date from soup

_parse_metrics(elem: Tag) → int

Parse metrics from element

export()

Export data to csv

location: str = 'Tunisia'

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

regex: dict = {'date': 'Chiffres clés mis à jour le '}

source_label: str = 'Tunisia Ministry of Health'

source_url: str = 'https://onmne.tn'

source_url_ref: str = 'https://onmne.tn'

units: str = 'people tested'

cowidev.testing.incremental.tunisia.main()

cowidev.testing.incremental.ukraine

class cowidev.testing.incremental.ukraine.Ukraine

Bases: object

_get_relevant_element(soup: BeautifulSoup) → Tag

Get the relevant element in news feed.

_parse_data(soup: BeautifulSoup) → tuple

Get data from the source page.

_parse_date(soup: BeautifulSoup) → str

Gets date from the source page.

_parse_metrics(elem: Tag) → int

Gets metrics from the element.

export()

Export data to csv.

location = 'Ukraine'

notes = ''

read() → Series

Read data from source.

regex = {'count': 'total of tests', 'date': 'Information as of (\\w+) (\\d{1,2})'}

source_label = 'Cabinet of Ministers of Ukraine'

source_url = 'https://covid19.gov.ua/en'

units = 'tests performed'

cowidev.testing.incremental.ukraine.main()

cowidev.testing.incremental.vanuatu

class cowidev.testing.incremental.vanuatu.Vanuatu

Bases: CountryTestBase

_base_url: str = 'https://covid19.gov.vu'

_parse_data(soup: BeautifulSoup) → DataFrame

Parse data from soup

_parse_date(tables: list) → str

Parse date from the list of tables

_parse_metrics(tables: list) → int

Parse metrics from the list of tables

_parse_pdf_tables() → list

Parse pdf tables from link

property area: list

Areas of pdf to be extracted :returns: [[y1, x1, y2, x2], …] :rtype: list

For more info see: https://github.com/tabulapdf/tabula-java/wiki/Using-the-command-line-tabula-extractor-tool

export()

Export data to csv

location: str = 'Vanuatu'

pipeline(df: DataFrame) → DataFrame

Pipeline for data processing

read() → DataFrame

Read data from source

regex: dict = {'date': '\\d{1,2}\\/\\d{2}\\/20\\d{2} - (\\d{1,2}\\/\\d{2}\\/20\\d{2})', 'title': 'Surveillance Report for Epi Week'}

source_label: str = 'Ministry of Health'

source_url: str = 'https://covid19.gov.vu/index.php/surveillance'

source_url_ref: str = None

units: str = 'people tested'

cowidev.testing.incremental.vanuatu.main()

cowidev.testing.incremental.vietnam

class cowidev.testing.incremental.vietnam.Vietnam

Bases: object

_get_relevant_link(soup: BeautifulSoup) → str

Get the relevant URL from the source page.

_get_text_from_url(url: str) → str

Extract text from URL.

_parse_data(soup: BeautifulSoup) → dict

Get data from the source page.

_parse_date_from_text(soup) → str

Get date from text.

_parse_metrics(text: str) → int

Get metrics from text.

base_url = 'https://covid19.gov.vn'

export()

Export data to CSV.

location = 'Vietnam'

read() → Series

Read data from source.

regex = {'count': 'mẫu tương đương (\\d+)', 'date': '(\\d{2}\\-\\d{2}\\-\\d{4})', 'title': 'Ngày'}

source_label = 'Ministry of Health of Vietnam'

source_url = 'https://covid19.gov.vn/ban-tin-covid-19.htm'

units = 'people tested'

cowidev.testing.incremental.vietnam.main()