hdx-python-scraper 2.6.0__tar.gz → 2.6.2__tar.gz

{hdx_python_scraper-2.6.0 → hdx_python_scraper-2.6.2}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hdx-python-scraper
-Version: 2.6.0
+Version: 2.6.2
 Summary: HDX Python scraper utilities to assemble data from multiple sources
 Project-URL: Homepage, https://github.com/OCHA-DAP/hdx-python-scraper
 Author-email: Michael Rans <rans@email.com>
@@ -26,7 +26,7 @@ Classifier: Programming Language :: Python :: 3.12
 Classifier: Topic :: Software Development :: Libraries :: Python Modules
 Requires-Python: >=3.8
 Requires-Dist: gspread
-Requires-Dist: hdx-python-api>=6.3.7
+Requires-Dist: hdx-python-api>=6.3.8
 Requires-Dist: hdx-python-country>=3.8.8
 Requires-Dist: hdx-python-utilities>=3.8.3
 Requires-Dist: regex

{hdx_python_scraper-2.6.0 → hdx_python_scraper-2.6.2}/pyproject.toml

@@ -34,7 +34,7 @@ classifiers = [
 requires-python = ">=3.8"
 
 dependencies = [
-    "hdx-python-api>=6.3.7",
+    "hdx-python-api>=6.3.8",
     "hdx-python-country>=3.8.8",
     "hdx-python-utilities>=3.8.3",
     "gspread",

{hdx_python_scraper-2.6.0 → hdx_python_scraper-2.6.2}/requirements.txt

@@ -52,7 +52,7 @@ google-auth-oauthlib==1.2.1
     # via gspread
 gspread==6.1.4
     # via hdx-python-scraper (pyproject.toml)
-hdx-python-api==6.3.7
+hdx-python-api==6.3.8
     # via hdx-python-scraper (pyproject.toml)
 hdx-python-country==3.8.8
     # via
@@ -63,7 +63,7 @@ hdx-python-utilities==3.8.3
     #   hdx-python-scraper (pyproject.toml)
     #   hdx-python-api
     #   hdx-python-country
-humanize==4.11.0
+humanize==4.12.0
     # via frictionless
 identify==2.6.7
     # via pre-commit
@@ -218,7 +218,7 @@ shellingham==1.5.4
     # via typer
 simpleeval==1.0.3
     # via frictionless
-simplejson==3.19.3
+simplejson==3.20.1
     # via ckanapi
 six==1.17.0
     # via
@@ -240,7 +240,7 @@ tenacity==9.0.0
     # via hdx-python-country
 text-unidecode==1.3
     # via python-slugify
-typeguard==4.4.1
+typeguard==4.4.2
     # via inflect
 typer==0.15.1
     # via frictionless

{hdx_python_scraper-2.6.0 → hdx_python_scraper-2.6.2}/src/hdx/scraper/framework/_version.py

@@ -12,5 +12,5 @@ __version__: str
 __version_tuple__: VERSION_TUPLE
 version_tuple: VERSION_TUPLE
 
-__version__ = version = '2.6.0'
-__version_tuple__ = version_tuple = (2, 6, 0)
+__version__ = version = '2.6.2'
+__version_tuple__ = version_tuple = (2, 6, 2)

{hdx_python_scraper-2.6.0 → hdx_python_scraper-2.6.2}/src/hdx/scraper/framework/base_scraper.py

@@ -15,8 +15,8 @@ class BaseScraper(ABC):
         name (str): Name of scraper
         datasetinfo (Dict): Information about dataset
         headers (Dict[str, Tuple]): Headers to be oytput at each level_name
-        source_configuration (Dict): Configuration for sources. Defaults to empty dict (use defaults).
-        reader (str): Reader to use. Defaults to "" (datasetinfo reader falling back on name).
+        source_configuration (Dict): Configuration for sources. Default is empty dict (use defaults).
+        reader (str): Reader to use. Default is "" (datasetinfo reader falling back on name).
     """
 
     population_lookup = {}
@@ -49,7 +49,7 @@ class BaseScraper(ABC):
 
         Args:
             headers (Dict[str, Tuple]): Headers to be output at each level_name
-            source_configuration (Dict): Configuration for sources. Defaults to empty dict (use defaults).
+            source_configuration (Dict): Configuration for sources. Default is empty dict (use defaults).
 
         Returns:
              None
@@ -73,7 +73,7 @@ class BaseScraper(ABC):
         {"national": [("#food-prices", "2022-07-15", "WFP", "https://data.humdata.org/dataset/global-wfp-food-prices"), ...]
 
         Args:
-            source_configuration (Dict): Configuration for sources. Defaults to empty dict (use defaults).
+            source_configuration (Dict): Configuration for sources. Default is empty dict (use defaults).
 
         Returns:
              None
@@ -252,8 +252,8 @@ class BaseScraper(ABC):
 
         Args:
             hxltag (str): HXL hashtag to use for source
-            datasetinfo (Optional[Dict]): Information about dataset. Defaults to None (use self.datasetinfo).
-            key (Optional[str]): Key under which to add source. Defaults to None (use scraper name).
+            datasetinfo (Optional[Dict]): Information about dataset. Default is None (use self.datasetinfo).
+            key (Optional[str]): Key under which to add source. Default is None (use scraper name).
 
         Returns:
             None
@@ -288,8 +288,8 @@ class BaseScraper(ABC):
 
         Args:
             hxltags (ListTuple[str]): HXL hashtags to use for sources
-            datasetinfo (Optional[Dict]): Information about dataset. Defaults to None (use self.datasetinfo).
-            key (Optional[str]): Key under which to add source. Defaults to None (use scraper name).
+            datasetinfo (Optional[Dict]): Information about dataset. Default is None (use self.datasetinfo).
+            key (Optional[str]): Key under which to add source. Default is None (use scraper name).
             suffix_attributes (Optional[ListTuple]): List of suffix attributes to append to HXL hashtags eg. iso3 codes
 
         Returns:

{hdx_python_scraper-2.6.0 → hdx_python_scraper-2.6.2}/src/hdx/scraper/framework/outputs/base.py

@@ -29,7 +29,7 @@ class BaseOutput:
         Args:
             tabname (str): Tab to update
             values (Union[List, DataFrame]): Values in a list of lists or a DataFrame
-            hxltags (Optional[Dict]): HXL tag mapping. Defaults to None.
+            hxltags (Optional[Dict]): HXL tag mapping. Default is None.
             **kwargs (Any): Keyword arguments
 
         Returns:
@@ -57,7 +57,7 @@ class BaseOutput:
         Args:
             key (str): Key in JSON to update
             df (DataFrame): Dataframe containing rows
-            hxltags (Optional[Dict]): HXL tag mapping. Defaults to None.
+            hxltags (Optional[Dict]): HXL tag mapping. Default is None.
 
         Returns:
             None
@@ -77,7 +77,7 @@ class BaseOutput:
             key (str): Key to update
             countryiso (str): Country to use as subkey
             rows (List[Dict]): List of dictionaries
-            hxltags (Optional[Dict]): HXL tag mapping. Defaults to None.
+            hxltags (Optional[Dict]): HXL tag mapping. Default is None.
 
         Returns:
             None

{hdx_python_scraper-2.6.0 → hdx_python_scraper-2.6.2}/src/hdx/scraper/framework/outputs/excelfile.py

@@ -43,7 +43,7 @@ class ExcelFile(BaseOutput):
         Args:
             tabname (str): Tab to update
             values (Union[List, DataFrame]): Values in a list of lists or a DataFrame
-            hxltags (Optional[Dict]): HXL tag mapping. Defaults to None.
+            hxltags (Optional[Dict]): HXL tag mapping. Default is None.
 
         Returns:
             None

{hdx_python_scraper-2.6.0 → hdx_python_scraper-2.6.2}/src/hdx/scraper/framework/outputs/googlesheets.py

@@ -60,7 +60,7 @@ class GoogleSheets(BaseOutput):
         Args:
             tabname (str): Tab to update
             values (Union[List, DataFrame]): Values in a list of lists or a DataFrame
-            hxltags (Optional[Dict]): HXL tag mapping. Defaults to None.
+            hxltags (Optional[Dict]): HXL tag mapping. Default is None.
             limit (Optional[int]): Maximum number of rows to output
 
         Returns:

{hdx_python_scraper-2.6.0 → hdx_python_scraper-2.6.2}/src/hdx/scraper/framework/outputs/json.py

@@ -53,7 +53,7 @@ class JsonFile(BaseOutput):
         Args:
             key (str): Key in JSON to update
             df (DataFrame): Dataframe containing rows
-            hxltags (Optional[Dict]): HXL tag mapping. Defaults to None.
+            hxltags (Optional[Dict]): HXL tag mapping. Default is None.
 
         Returns:
             None
@@ -75,7 +75,7 @@ class JsonFile(BaseOutput):
             key (str): Key in JSON to update
             countryiso (str): Country to use as subkey
             rows (List[Dict]): List of dictionaries
-            hxltags (Optional[Dict]): HXL tag mapping. Defaults to None.
+            hxltags (Optional[Dict]): HXL tag mapping. Default is None.
 
         Returns:
             None
@@ -121,7 +121,7 @@ class JsonFile(BaseOutput):
         Args:
             key (str): Key in JSON to update
             df (DataFrame): Dataframe containing rows
-            hxltags (Optional[Dict]): HXL tag mapping. Defaults to None.
+            hxltags (Optional[Dict]): HXL tag mapping. Default is None.
 
         Returns:
             None
@@ -147,7 +147,7 @@ class JsonFile(BaseOutput):
         Args:
             tabname (str): Tab to update
             values (Union[List, DataFrame]): Values in a list of lists or a DataFrame
-            hxltags (Optional[Dict]): HXL tag mapping. Defaults to None.
+            hxltags (Optional[Dict]): HXL tag mapping. Default is None.
 
         Returns:
             None
@@ -187,7 +187,7 @@ class JsonFile(BaseOutput):
         """Save JSON file and any addition subsets of that JSON defined in the additional configuration
 
         Args:
-            folder (Optional[str]): Folder to save to. Defaults to None.
+            folder (Optional[str]): Folder to save to. Default is None.
             **kwargs: Variables to use when evaluating template arguments
 
         Returns:

{hdx_python_scraper-2.6.0 → hdx_python_scraper-2.6.2}/src/hdx/scraper/framework/runner.py

@@ -27,9 +27,9 @@ class Runner:
 
     Args:
         countryiso3s (ListTuple[str]): List of ISO3 country codes to process
-        today (datetime): Value to use for today. Defaults to now_utc().
+        today (datetime): Value to use for today. Default is now_utc().
         error_handler (ErrorHandler): ErrorHandler object that logs errors on exit
-        scrapers_to_run (Optional[ListTuple[str]]): Scrapers to run. Defaults to None (all scrapers).
+        scrapers_to_run (Optional[ListTuple[str]]): Scrapers to run. Default is None (all scrapers).
     """
 
     def __init__(
@@ -117,12 +117,12 @@ class Runner:
             name (str): Name of scraper
             datasetinfo (Dict): Information about dataset
             level (str): Can be national, subnational or single
-            adminlevel (Optional[AdminLevel]): AdminLevel object from HDX Python Country. Defaults to None.
-            level_name (Optional[str]): Customised level_name name. Defaults to None (level_name).
-            source_configuration (Dict): Configuration for sources. Defaults to empty dict (use defaults).
+            adminlevel (Optional[AdminLevel]): AdminLevel object from HDX Python Country. Default is None.
+            level_name (Optional[str]): Customised level_name name. Default is None (level_name).
+            source_configuration (Dict): Configuration for sources. Default is empty dict (use defaults).
             suffix (Optional[str]): Suffix to add to the scraper name
             force_add_to_run (bool): Whether to force include the scraper in the next run
-            countryiso3s (Optional[List[str]]): Override list of country iso3s. Defaults to None.
+            countryiso3s (Optional[List[str]]): Override list of country iso3s. Default is None.
 
         Returns:
             str: scraper name (including suffix if set)
@@ -173,12 +173,12 @@ class Runner:
         Args:
             configuration (Dict): Mapping from scraper name to information about datasets
             level (str): Can be national, subnational or single
-            adminlevel (Optional[AdminLevel]): AdminLevel object from HDX Python Country. Defaults to None.
-            level_name (Optional[str]): Customised level_name name. Defaults to None (level_name).
-            source_configuration (Dict): Configuration for sources. Defaults to empty dict (use defaults).
+            adminlevel (Optional[AdminLevel]): AdminLevel object from HDX Python Country. Default is None.
+            level_name (Optional[str]): Customised level_name name. Default is None (level_name).
+            source_configuration (Dict): Configuration for sources. Default is empty dict (use defaults).
             suffix (Optional[str]): Suffix to add to the scraper name
             force_add_to_run (bool): Whether to force include the scraper in the next run
-            countryiso3s (Optional[List[str]]): Override list of country iso3s. Defaults to None.
+            countryiso3s (Optional[List[str]]): Override list of country iso3s. Default is None.
 
         Returns:
             List[str]: scraper names (including suffix if set)
@@ -277,10 +277,10 @@ class Runner:
             input_level (str): Input level to aggregate like national or subnational
             output_level (str): Output level of aggregated data like regional
             adm_aggregation (Union[Dict, List]): Mapping from input admins to aggregated output admins
-            source_configuration (Dict): Configuration for sources. Defaults to empty dict (use defaults).
-            names (Optional[ListTuple[str]]): Names of scrapers. Defaults to None.
-            overrides (Dict[str, Dict]): Dictionary mapping scrapers to level mappings. Defaults to {}.
-            aggregation_scrapers (List["Aggregator"]): Other aggregations needed. Defaults to [].
+            source_configuration (Dict): Configuration for sources. Default is empty dict (use defaults).
+            names (Optional[ListTuple[str]]): Names of scrapers. Default is None.
+            overrides (Dict[str, Dict]): Dictionary mapping scrapers to level mappings. Default is {}.
+            aggregation_scrapers (List["Aggregator"]): Other aggregations needed. Default is [].
 
         Returns:
             Optional["Aggregator"]: scraper or None
@@ -347,10 +347,10 @@ class Runner:
             input_level (str): Input level to aggregate like national or subnational
             output_level (str): Output level of aggregated data like regional
             adm_aggregation (Union[Dict, List]): Mapping from input admins to aggregated output admins
-            source_configuration (Dict): Configuration for sources. Defaults to empty dict (use defaults).
-            names (Optional[ListTuple[str]]): Names of scrapers. Defaults to None.
-            overrides (Dict[str, Dict]): Dictionary mapping scrapers to level mappings. Defaults to {}.
-            aggregation_scrapers (List["Aggregator"]): Other aggregations needed. Defaults to [].
+            source_configuration (Dict): Configuration for sources. Default is empty dict (use defaults).
+            names (Optional[ListTuple[str]]): Names of scrapers. Default is None.
+            overrides (Dict[str, Dict]): Dictionary mapping scrapers to level mappings. Default is {}.
+            aggregation_scrapers (List["Aggregator"]): Other aggregations needed. Default is [].
             force_add_to_run (bool): Whether to force include the scraper in the next run
 
         Returns:
@@ -398,9 +398,9 @@ class Runner:
             input_level (str): Input level to aggregate like national or subnational
             output_level (str): Output level of aggregated data like regional
             adm_aggregation (Union[Dict, ListTuple]): Mapping from input admins to aggregated output admins
-            source_configuration (Dict): Configuration for sources. Defaults to empty dict (use defaults).
+            source_configuration (Dict): Configuration for sources. Default is empty dict (use defaults).
             names (Optional[ListTuple[str]]): Names of scrapers
-            overrides (Dict[str, Dict]): Dictionary mapping scrapers to level mappings. Defaults to {}.
+            overrides (Dict[str, Dict]): Dictionary mapping scrapers to level mappings. Default is {}.
             force_add_to_run (bool): Whether to force include the scraper in the next run
 
         Returns:
@@ -437,7 +437,7 @@ class Runner:
 
         Args:
             datasetinfo (Dict): Information about dataset
-            folder (str): Folder to which to download. Defaults to "".
+            folder (str): Folder to which to download. Default is "".
             force_add_to_run (bool): Whether to force include the scraper in the next run
 
         Returns:
@@ -460,7 +460,7 @@ class Runner:
 
         Args:
             configuration (Dict): Mapping from scraper name to information about datasets
-            folder (str): Folder to which to download. Defaults to "".
+            folder (str): Folder to which to download. Default is "".
             force_add_to_run (bool): Whether to force include the scraper in the next run
 
         Returns:
@@ -662,9 +662,9 @@ class Runner:
         are run first. If scraper run fails and fallbacks have been set up, use them.
 
         Args:
-            what_to_run (Optional[ListTuple[str]]): Run only these scrapers. Defaults to None (run all).
+            what_to_run (Optional[ListTuple[str]]): Run only these scrapers. Default is None (run all).
             force_run (bool): Force run even if any scraper marked as already run
-            prioritise_scrapers (Optional[ListTuple[str]]): Scrapers to run first. Defaults to None.
+            prioritise_scrapers (Optional[ListTuple[str]]): Scrapers to run first. Default is None.
 
         Returns:
             None
@@ -718,7 +718,7 @@ class Runner:
             levels (Optional[ListTuple[str]]): Levels to get like national, subnational or single
             headers (Optional[ListTuple[str]]): Headers to get
             hxltags (Optional[ListTuple[str]]): HXL hashtags to get
-            overrides (Dict[str, Dict]): Dictionary mapping scrapers to level mappings. Defaults to {}.
+            overrides (Dict[str, Dict]): Dictionary mapping scrapers to level mappings. Default is {}.
 
 
         Returns:
@@ -789,11 +789,11 @@ class Runner:
         lists.
 
         Args:
-            names (Optional[ListTuple[str]]): Names of scrapers. Defaults to None (all scrapers).
+            names (Optional[ListTuple[str]]): Names of scrapers. Default is None (all scrapers).
             levels (Optional[ListTuple[str]]): Levels to get like national, subnational or single
-            overrides (Dict[str, Dict]): Dictionary mapping scrapers to level mappings. Defaults to {}.
-            has_run (bool): Only get results for scrapers marked as having run. Defaults to True.
-            should_overwrite_sources (Optional[bool]): Whether to overwrite sources. Defaults to None (class default).
+            overrides (Dict[str, Dict]): Dictionary mapping scrapers to level mappings. Default is {}.
+            has_run (bool): Only get results for scrapers marked as having run. Default is True.
+            should_overwrite_sources (Optional[bool]): Whether to overwrite sources. Default is None (class default).
 
         Returns:
             Dict[str, Dict]: Results dictionary that maps each level to headers, values, sources, fallbacks.
@@ -897,8 +897,8 @@ class Runner:
             adms (ListTuple[str]): Admin units
             headers (ListTuple[ListTuple]): Additional headers in the form (list of headers, list of HXL hashtags)
             row_fns (ListTuple[Callable[[str], str]]): Functions to populate additional columns
-            names (Optional[ListTuple[str]]): Names of scrapers. Defaults to None (all scrapers).
-            overrides (Dict[str, Dict]): Dictionary mapping scrapers to level mappings. Defaults to {}.
+            names (Optional[ListTuple[str]]): Names of scrapers. Default is None (all scrapers).
+            overrides (Dict[str, Dict]): Dictionary mapping scrapers to level mappings. Default is {}.
 
         Returns:
             List[List]: Rows for a given level
@@ -938,10 +938,10 @@ class Runner:
 
         Args:
             level (str): Level to get like national, subnational or single
-            names (Optional[ListTuple[str]]): Names of scrapers. Defaults to None (all scrapers).
-            overrides (Dict[str, Dict]): Dictionary mapping scrapers to level mappings. Defaults to {}.
-            has_run (bool): Only get results for scrapers marked as having run. Defaults to True.
-            use_hxl (bool): Whether keys should be HXL hashtags or column headers. Defaults to True.
+            names (Optional[ListTuple[str]]): Names of scrapers. Default is None (all scrapers).
+            overrides (Dict[str, Dict]): Dictionary mapping scrapers to level mappings. Default is {}.
+            has_run (bool): Only get results for scrapers marked as having run. Default is True.
+            use_hxl (bool): Whether keys should be HXL hashtags or column headers. Default is True.
 
         Returns:
             Tuple[Dict, Dict]: Tuple of (headers to values, headers to sources)
@@ -1059,7 +1059,7 @@ class Runner:
             names (Optional[ListTuple[str]]): Names of scrapers
             levels (Optional[ListTuple[str]]): Levels to get like national, subnational or single
             additional_sources (ListTuple[Dict]): Additional sources to add
-            should_overwrite_sources (Optional[bool]): Whether to overwrite sources. Defaults to None (class default).
+            should_overwrite_sources (Optional[bool]): Whether to overwrite sources. Default is None (class default).
 
         Returns:
             List[Tuple]: Sources in form (indicator, date, source, source_url)
@@ -1178,7 +1178,7 @@ class Runner:
 
         Args:
             names (Optional[ListTuple[str]]): Names of scrapers
-            has_run (bool): Only get results for scrapers marked as having run. Defaults to True.
+            has_run (bool): Only get results for scrapers marked as having run. Default is True.
 
         Returns:
             Dict: HAPI metadata for all datasets
@@ -1232,8 +1232,8 @@ class Runner:
         metadata is a dictionary.
 
         Args:
-            names (Optional[ListTuple[str]]): Names of scrapers. Defaults to None (all scrapers).
-            has_run (bool): Only get results for scrapers marked as having run. Defaults to True.
+            names (Optional[ListTuple[str]]): Names of scrapers. Default is None (all scrapers).
+            has_run (bool): Only get results for scrapers marked as having run. Default is True.
 
         Returns:
             Dict: Headers and values per admin level and HAPI metadata for all datasets

{hdx_python_scraper-2.6.0 → hdx_python_scraper-2.6.2}/src/hdx/scraper/framework/scrapers/aggregator.py

@@ -36,8 +36,8 @@ class Aggregator(BaseScraper):
         adm_aggregation (Union[Dict, ListTuple]): Mapping from input admins to aggregated output admins
         headers (Dict[str, Tuple]): Column headers and HXL hashtags
         use_hxl (bool): Whether to map from headers or from HXL tags
-        source_configuration (Dict): Configuration for sources. Defaults to empty dict (use defaults).
-        aggregation_scrapers (List["Aggregator"]): Other aggregations needed. Defaults to [].
+        source_configuration (Dict): Configuration for sources. Default is empty dict (use defaults).
+        aggregation_scrapers (List["Aggregator"]): Other aggregations needed. Default is [].
     """
 
     def __init__(
@@ -95,8 +95,8 @@ class Aggregator(BaseScraper):
             adm_aggregation (Union[Dict, ListTuple]): Mapping from input admins to aggregated output admins
             input_headers (Tuple[ListTuple, ListTuple]): Column headers and HXL hashtags
             runner(Runner): Runner object
-            source_configuration (Dict): Configuration for sources. Defaults to empty dict (use defaults).
-            aggregation_scrapers (List["Aggregator"]): Other aggregations needed. Defaults to [].
+            source_configuration (Dict): Configuration for sources. Default is empty dict (use defaults).
+            aggregation_scrapers (List["Aggregator"]): Other aggregations needed. Default is [].
 
         Returns:
             Optional["Aggregator"]: The aggregation scraper or None if it couldn't be created

{hdx_python_scraper-2.6.0 → hdx_python_scraper-2.6.2}/src/hdx/scraper/framework/scrapers/configurable_scraper.py

@@ -38,10 +38,10 @@ class ConfigurableScraper(BaseScraper):
         datasetinfo (Dict): Information about dataset
         level (str): Can be national, subnational or single
         countryiso3s (List[str]): List of ISO3 country codes to process
-        adminlevel (Optional[AdminLevel]): AdminLevel object from HDX Python Country. Defaults to None.
-        level_name (Optional[str]): Customised level_name name. Defaults to None (level).
-        source_configuration (Dict): Configuration for sources. Defaults to empty dict (use defaults).
-        today (datetime): Value to use for today. Defaults to now_utc().
+        adminlevel (Optional[AdminLevel]): AdminLevel object from HDX Python Country. Default is None.
+        level_name (Optional[str]): Customised level_name name. Default is None (level).
+        source_configuration (Dict): Configuration for sources. Default is empty dict (use defaults).
+        today (datetime): Value to use for today. Default is now_utc().
         error_handler (Optional[ErrorHandler]): ErrorHandler object that logs errors on exit
         **kwargs: Variables to use when evaluating template arguments in urls
     """

{hdx_python_scraper-2.6.0 → hdx_python_scraper-2.6.2}/src/hdx/scraper/framework/scrapers/resource_downloader.py

@@ -16,7 +16,7 @@ class ResourceDownloader(BaseScraper):
 
     Args:
         datasetinfo (Dict): Information about dataset
-        folder (str): Folder to which to download. Defaults to "".
+        folder (str): Folder to which to download. Default is "".
     """
 
     def __init__(self, datasetinfo, folder):

{hdx_python_scraper-2.6.0 → hdx_python_scraper-2.6.2}/src/hdx/scraper/framework/scrapers/rowparser.py

@@ -30,7 +30,7 @@ class RowParser:
         headers (List[str]): Row headers
         header_to_hxltag (Optional[Dict[str, str]]): Mapping from headers to HXL hashtags or None
         subsets (List[Dict]): List of subset definitions
-        maxdateonly (bool): Whether to only take the most recent date. Defaults to True.
+        maxdateonly (bool): Whether to only take the most recent date. Default is True.
     """
 
     def __init__(

{hdx_python_scraper-2.6.0 → hdx_python_scraper-2.6.2}/src/hdx/scraper/framework/scrapers/timeseries.py

@@ -19,7 +19,7 @@ class TimeSeries(BaseScraper):
         name (str): Name of scraper
         datasetinfo (Dict): Information about dataset
         outputs (Dict[str, BaseOutput]): Mapping from names to output objects
-        today (datetime): Value to use for today. Defaults to now_utc().
+        today (datetime): Value to use for today. Default is now_utc().
     """
 
     def __init__(

{hdx_python_scraper-2.6.0 → hdx_python_scraper-2.6.2}/src/hdx/scraper/framework/utilities/__init__.py

@@ -64,7 +64,7 @@ def get_startend_dates_from_time_period(
 
     Args:
         dataset (Dataset): Dataset object
-        today (Optional[datetime]): Date to use for today. Defaults to None (datetime.utcnow)
+        today (Optional[datetime]): Date to use for today. Default is None (datetime.utcnow)
 
     Returns:
         Optional[Dict]: Time period in form required for source_date

{hdx_python_scraper-2.6.0 → hdx_python_scraper-2.6.2}/src/hdx/scraper/framework/utilities/fallbacks.py

@@ -52,7 +52,7 @@ class Fallbacks:
         Args:
             fallbacks_path (str): Path to JSON fallbacks file
             levels_mapping (Dict[str,str]): Map keys from file to levels. Defaults in description.
-            sources_key (str): Key to use for sources. Defaults to "sources".
+            sources_key (str): Key to use for sources. Default is "sources".
             admin_name_mapping: HXL hashtags for different admin levels. Defaults in description.
 
         Returns:
@@ -86,7 +86,7 @@ class Fallbacks:
         Args:
             fallbacks_path (str): Path to JSON fallbacks file
             levels_mapping (Dict[str,str]): Map keys from file to levels. Defaults in description.
-            sources_key (str): Key to use for sources. Defaults to "sources".
+            sources_key (str): Key to use for sources. Default is "sources".
             admin_name_mapping: HXL hashtags for different admin levels. Defaults in description.
 
         Returns:

{hdx_python_scraper-2.6.0 → hdx_python_scraper-2.6.2}/src/hdx/scraper/framework/utilities/hapi_admins.py

@@ -9,21 +9,45 @@ def complete_admins(
     provider_adm_names: List,
     adm_codes: List,
     adm_names: List,
+    fuzzy_match: bool = True,
 ) -> Tuple[int, List[str]]:
+    """Use information from adm_codes to populate adm_names and from
+    provider_adm_names to populate adm_codes with outptu of the admin level
+    and arnings for unknown and mismatched p-codes. All provided lists
+    should be of the same length.
+
+    Args:
+        admins (List[AdminLevel]): List of AdminLevel objects
+        countryiso3 (str): Country ISO3 code
+        provider_adm_names (List): List of provider adm names
+        adm_codes (List): List of adm codes
+        adm_names (List): List of adm names
+        fuzzy_match (bool): Whether to use fuzzy matching. Default is True.
+
+    Returns:
+        Tuple[int, List[str]]: Admin level and warnings
+    """
+
     warnings = []
-    parent = None
+    child = None
     adm_level = len(provider_adm_names)
     for i, provider_adm_name in reversed(list(enumerate(provider_adm_names))):
         adm_code = adm_codes[i]
         if not provider_adm_name:
             provider_adm_name = ""
             provider_adm_names[i] = ""
-        if parent:
-            pcode = admins[i + 1].pcode_to_parent.get(parent)
+        if child:
+            pcode = admins[i + 1].pcode_to_parent.get(child)
             warntxt = "parent"
         elif provider_adm_name:
+            parent = admins[i].pcode_to_parent.get(adm_code)
+            if not parent and i > 0:
+                parent = adm_codes[i - 1]
             pcode, _ = admins[i].get_pcode(
-                countryiso3, provider_adm_name, parent=parent
+                countryiso3,
+                provider_adm_name,
+                parent=parent,
+                fuzzy_match=fuzzy_match,
             )
             warntxt = f"provider_adm{i + 1}_name"
         else:
@@ -39,7 +63,7 @@ def complete_admins(
                     warnings.append(f"PCode unknown {adm_code}->''")
                     adm_code = ""
             elif pcode and adm_code != pcode:
-                if parent:
+                if child:
                     warnings.append(
                         f"PCode mismatch {adm_code}->{pcode} ({warntxt})"
                     )
@@ -55,7 +79,7 @@ def complete_admins(
         adm_codes[i] = adm_code
         if adm_code:
             adm_names[i] = admins[i].pcode_to_name.get(adm_code, "")
-            parent = adm_code
+            child = adm_code
         else:
             adm_names[i] = ""
             if provider_adm_name == "":
@@ -69,6 +93,18 @@ def pad_admins(
     adm_names: List[str],
     adm_level: int = 2,
 ) -> None:
+    """Pad lists to size given in adm_level adding as many "" as needed.
+
+    Args:
+        provider_adm_names (List): List of provider adm names
+        adm_codes (List): List of adm codes
+        adm_names (List): List of adm names
+        adm_level (int): Admin level to which to pad. Default is 2.
+
+    Returns:
+        Tuple[int, List[str]]: Admin level and warnings
+    """
+
     for i in range(len(provider_adm_names), adm_level):
         provider_adm_names.append("")
         adm_codes.append("")