normalize method names/args

rscraping/_functions.py

@@ -70,7 +70,7 @@ def parse_race_image(
     header_data = processor.retrieve_header_data(path=path, header_size=header_size)
     df = processor.retrieve_tabular_dataframe(path=path, header_size=header_size)
 
-    return parser.parse_races_from(
+    return parser.parse_races(
         data=df,
         file_name=os.path.splitext(os.path.basename(path))[0],
         header=header_data,

rscraping/clients/_client.py

@@ -100,12 +100,12 @@ def validate_url(self, url: str):
 
     @override
     @staticmethod
-    def get_race_details_url(race_id: str, **kwargs) -> str:
+    def get_races_url(year: int, **kwargs) -> str:
         raise NotImplementedError
 
     @override
     @staticmethod
-    def get_races_url(year: int, **kwargs) -> str:
+    def get_race_details_url(race_id: str, **kwargs) -> str:
         raise NotImplementedError
 
     @override
@@ -114,13 +114,13 @@ def get_lineup_url(race_id: str, **kwargs) -> str:
         raise NotImplementedError
 
     @override
-    def get_race_ids_by_rower(self, rower_id: str, **kwargs) -> Generator[str, Any, Any]:
+    def get_race_ids_by_club(self, club_id: str, year: int, **kwargs) -> Generator[str, Any, Any]:
         raise NotImplementedError
 
     @override
-    def get_lineup_by_race_id(self, race_id: str, **kwargs) -> Generator[Lineup, Any, Any]:
+    def get_race_ids_by_rower(self, rower_id: str, **kwargs) -> Generator[str, Any, Any]:
         raise NotImplementedError
 
     @override
-    def get_race_ids_by_club(self, club_id: str, year: int, **kwargs) -> Generator[str, Any, Any]:
+    def get_lineup_by_race_id(self, race_id: str, **kwargs) -> Generator[Lineup, Any, Any]:
         raise NotImplementedError

rscraping/clients/_protocol.py

@@ -66,40 +66,40 @@ def get_race_by_url(self, url: str, race_id: str, **kwargs) -> Race | None:
         """
         ...
 
-    def get_race_ids_by_year(self, year: int, **kwargs) -> Generator[str, Any, Any]:
+    def get_race_names_by_year(self, year: int, **kwargs) -> Generator[RaceName, Any, Any]:
         """
-        Find the race IDs for a given year.
+        Find the race names for a given year.
 
         Args:
-            year (int): The year for which to generate race IDs.
+            year (int): The year for which to generate race names.
             **kwargs: Additional keyword arguments.
 
-        Yields: str: Race IDs.
+        Yields: RaceName: Race names.
         """
         ...
 
-    def get_race_ids_by_club(self, club_id: str, year: int, **kwargs) -> Generator[str, Any, Any]:
+    def get_race_ids_by_year(self, year: int, **kwargs) -> Generator[str, Any, Any]:
         """
-        Find the race IDs for a given club and year.
+        Find the race IDs for a given year.
 
         Args:
-            club_id (str): The ID of the club.
             year (int): The year for which to generate race IDs.
             **kwargs: Additional keyword arguments.
 
         Yields: str: Race IDs.
         """
         ...
 
-    def get_race_names_by_year(self, year: int, **kwargs) -> Generator[RaceName, Any, Any]:
+    def get_race_ids_by_club(self, club_id: str, year: int, **kwargs) -> Generator[str, Any, Any]:
         """
-        Find the race names for a given year.
+        Find the race IDs for a given club and year.
 
         Args:
-            year (int): The year for which to generate race names.
+            club_id (str): The ID of the club.
+            year (int): The year for which to generate race IDs.
             **kwargs: Additional keyword arguments.
 
-        Yields: RaceName: Race names.
+        Yields: str: Race IDs.
         """
         ...
 

rscraping/clients/lgt.py

@@ -133,6 +133,35 @@ def get_race_by_url(self, url: str, race_id: str, **kwargs):
         kwargs["results_selector"] = self.get_results_selector(race_id)
         return super().get_race_by_url(url, race_id, **kwargs)
 
+    @override
+    def get_race_names_by_year(self, year: int, **_) -> Generator[RaceName, Any, Any]:
+        """
+        Find the race names for a given year and gender. Uses the unchecked IDs found in get_race_ids_by_year to
+        find them.
+
+        Args:
+            year (int): The year for which to generate race names.
+            **kwargs: Additional keyword arguments.
+
+        Yields: RaceName: Race names.
+        """
+        today = date.today().year
+        if today == year:
+            race_names = self._html_parser.parse_race_names(selector=self.get_calendar_selector())
+            if race_names:
+                yield from race_names
+                return
+
+        for id in self.get_race_ids_by_year(year, is_female=self._is_female):
+            if id in self._excluded_ids:
+                pass
+
+            url = self.get_race_details_url(id)
+            selector = Selector(requests.get(url=url, headers=HTTP_HEADERS()).content.decode("utf-8"))
+            if self._html_parser.is_valid_race(selector):
+                name = self._html_parser.get_name(selector)
+                yield RaceName(race_id=id, name=whitespaces_clean(name).upper())
+
     @override
     def get_race_ids_by_year(self, year: int, **_) -> Generator[str, Any, Any]:
         """
@@ -192,35 +221,6 @@ def get_race_ids_by_year(self, year: int, **_) -> Generator[str, Any, Any]:
 
         return (str(r) for r in range(lower_race_id, (upper_race_id + 1)) if r not in self._excluded_ids)
 
-    @override
-    def get_race_names_by_year(self, year: int, **_) -> Generator[RaceName, Any, Any]:
-        """
-        Find the race names for a given year and gender. Uses the unchecked IDs found in get_race_ids_by_year to
-        find them.
-
-        Args:
-            year (int): The year for which to generate race names.
-            **kwargs: Additional keyword arguments.
-
-        Yields: RaceName: Race names.
-        """
-        today = date.today().year
-        if today == year:
-            race_names = self._html_parser.parse_race_names(selector=self.get_calendar_selector())
-            if race_names:
-                yield from race_names
-                return
-
-        for id in self.get_race_ids_by_year(year, is_female=self._is_female):
-            if id in self._excluded_ids:
-                pass
-
-            url = self.get_race_details_url(id)
-            selector = Selector(requests.get(url=url, headers=HTTP_HEADERS()).content.decode("utf-8"))
-            if self._html_parser.is_valid_race(selector):
-                name = self._html_parser.get_name(selector)
-                yield RaceName(race_id=id, name=whitespaces_clean(name).upper())
-
     @override
     def get_lineup_by_race_id(self, race_id: str, **_) -> Generator[Lineup, Any, Any]:
         if race_id in self._excluded_ids:

rscraping/clients/tabular.py

@@ -108,26 +108,26 @@ def validate_url(self, url: str):
         if not pattern.match(url):
             raise ValueError(f"invalid {url=}")
 
+    def get_races(self, **kwargs) -> Generator[Race, Any, Any]:
+        return self._parser.parse_races(self._df, is_female=self._is_female, url=self._url)
+
     @override
     def get_race_by_id(self, race_id: str, *_, **kwargs) -> Race | None:
         race_row = self._df.iloc[int(race_id) - 1]
-        return self._parser.parse_race_serie(race_row, is_female=self._is_female, url=self._url)
+        return self._parser.parse_race(race_row, is_female=self._is_female, url=self._url)
 
     @override
     def get_race_by_url(self, *_, race_id: str, **kwargs) -> Race | None:
         return self.get_race_by_id(race_id=race_id, **kwargs)
 
-    def get_races(self, **kwargs) -> Generator[Race, Any, Any]:
-        return self._parser.parse_races_from(self._df, is_female=self._is_female, url=self._url)
+    @override
+    def get_race_names_by_year(self, year: int, *_, **kwargs) -> Generator[RaceName, Any, Any]:
+        return self._parser.parse_race_names(self._df, year)
 
     @override
     def get_race_ids_by_year(self, year: int, *_, **kwargs) -> Generator[str, Any, Any]:
         return self._parser.parse_race_ids(self._df, year)
 
-    @override
-    def get_race_names_by_year(self, year: int, *_, **kwargs) -> Generator[RaceName, Any, Any]:
-        return self._parser.parse_race_names(self._df, year)
-
     ################################################
     ############## PRIVATE METHODS #################
     ################################################

rscraping/clients/traineras.py

@@ -64,23 +64,29 @@ def validate_url(self, url: str):
         if not pattern.match(url):
             raise ValueError(f"invalid {url=}")
 
+    @override
+    def get_race_names_by_year(self, year: int, **_) -> Generator[RaceName, Any, Any]:
+        self.validate_year(year)
+        for page in self.get_pages(year):
+            yield from self._html_parser.parse_race_names(page, is_female=self._is_female, category=self._category)
+
     @override
     def get_race_ids_by_year(self, year: int, **_) -> Generator[str, Any, Any]:
         self.validate_year(year)
         for page in self.get_pages(year):
             yield from self._html_parser.parse_race_ids(page, is_female=self._is_female, category=self._category)
 
+    @override
+    def get_race_ids_by_club(self, club_id: str, year: int, **kwargs) -> Generator[str, Any, Any]:
+        content = requests.get(url=self.get_club_races_url(club_id, year), headers=HTTP_HEADERS())
+        content = content.content.decode("utf-8")
+        return self._html_parser.parse_club_race_ids(Selector(content))
+
     @override
     def get_race_ids_by_rower(self, rower_id: str, year: str | None = None, **_) -> Generator[str, Any, Any]:
         content = requests.get(url=self.get_rower_url(rower_id), headers=HTTP_HEADERS()).content.decode("utf-8")
         yield from self._html_parser.parse_rower_race_ids(Selector(content), year=year)
 
-    @override
-    def get_race_names_by_year(self, year: int, **_) -> Generator[RaceName, Any, Any]:
-        self.validate_year(year)
-        for page in self.get_pages(year):
-            yield from self._html_parser.parse_race_names(page, is_female=self._is_female, category=self._category)
-
     @override
     def get_lineup_by_race_id(self, race_id: str, **_) -> Generator[Lineup, Any, Any]:
         content = requests.get(url=self.get_race_details_url(race_id), headers=HTTP_HEADERS()).content.decode("utf-8")
@@ -92,12 +98,6 @@ def get_lineup_by_race_id(self, race_id: str, **_) -> Generator[Lineup, Any, Any
             lineup = requests.get(url=url, headers=HTTP_HEADERS()).content.decode("utf-8")
             yield self._html_parser.parse_lineup(Selector(lineup))
 
-    @override
-    def get_race_ids_by_club(self, club_id: str, year: int, **kwargs) -> Generator[str, Any, Any]:
-        content = requests.get(url=self.get_club_races_url(club_id, year), headers=HTTP_HEADERS())
-        content = content.content.decode("utf-8")
-        return self._html_parser.parse_club_race_ids(Selector(content))
-
     def get_pages(self, year: int) -> Generator[Selector, Any, Any]:
         """
         Generate Selector objects for each page of races in a specific year.

rscraping/parsers/df/_parser.py

@@ -1,6 +1,10 @@
 from abc import ABC
+from collections.abc import Generator
+from typing import Any, override
 
-from rscraping.data.models import Datasource
+from pandas import DataFrame
+
+from rscraping.data.models import Datasource, Race
 
 from ._protocol import DataFrameParserProtocol
 
@@ -19,3 +23,7 @@ def __new__(cls, source: str, **_) -> "DataFrameParser":  # pragma: no cover
         final_obj = object.__new__(subclass)
 
         return final_obj
+
+    @override
+    def parse_races(self, data: DataFrame, **kwargs) -> Generator[Race, Any, Any]:
+        raise NotImplementedError

rscraping/parsers/df/_protocol.py

@@ -7,4 +7,4 @@
 
 
 class DataFrameParserProtocol(Protocol):
-    def parse_races_from(self, data: DataFrame, *_, **kwargs) -> Generator[Race, Any, Any]: ...
+    def parse_races(self, data: DataFrame, **kwargs) -> Generator[Race, Any, Any]: ...

rscraping/parsers/df/inforemo.py

@@ -1,7 +1,7 @@
 import re
 from collections.abc import Generator
 from datetime import date, datetime
-from typing import Any
+from typing import Any, override
 
 import inquirer
 from pandas import DataFrame, Series
@@ -37,14 +37,14 @@ class InforemoDataFrameParser(DataFrameParser, source=Datasource.INFOREMO):
         GENDER_MIX: ["MIXTO"],
     }
 
-    def parse_races_from(
+    @override
+    def parse_races(
         self,
         data: DataFrame,
-        *_,
-        file_name: str,
-        header: str,
+        file_name: str = "",
+        header: str = "",
         manual_input: bool = False,
-        **__,
+        **_,
     ) -> Generator[Race, Any, Any]:
         name = self._try_find_race_name(header, manual_input=manual_input)
         t_date = self._try_find_race_date(header, manual_input=manual_input)

rscraping/parsers/df/tabular.py

@@ -1,6 +1,6 @@
 from collections.abc import Generator
 from datetime import date
-from typing import Any
+from typing import Any, override
 
 from pandas import DataFrame, Series
 
@@ -41,7 +41,20 @@
 
 
 class TabularDataFrameParser(DataFrameParserProtocol):
-    def parse_race_serie(self, row: Series, is_female: bool = False, url: str | None = None) -> Race | None:
+    @override
+    def parse_races(
+        self,
+        data: DataFrame,
+        is_female: bool = False,
+        url: str | None = None,
+        **__,
+    ) -> Generator[Race, Any, Any]:
+        for _, row in data.iterrows():
+            race = self.parse_race(row, is_female=is_female, url=url)
+            if race:
+                yield race
+
+    def parse_race(self, row: Series, is_female: bool = False, url: str | None = None) -> Race | None:
         if not isinstance(row, Series):
             return None
 
@@ -106,19 +119,6 @@ def parse_race_names(self, data: DataFrame, year: int) -> Generator[RaceName, An
         df = data[data[COLUMN_DATE].dt.year == year]
         return (RaceName(race_id=str(row.name), name=str(row[COLUMN_NAME])) for _, row in df.iterrows())
 
-    def parse_races_from(
-        self,
-        data: DataFrame,
-        *_,
-        is_female: bool = False,
-        url: str | None = None,
-        **__,
-    ) -> Generator[Race, Any, Any]:
-        for _, row in data.iterrows():
-            race = self.parse_race_serie(row, is_female=is_female, url=url)
-            if race:
-                yield race
-
     @staticmethod
     def _normalize_race_name(name: str, league: str | None, t_date: date) -> str:
         if all(n in name for n in ["ILLA", "SAMERTOLAMEU"]) and (

rscraping/parsers/html/act.py

@@ -110,8 +110,13 @@ def parse_race_ids(self, selector: Selector, **_) -> Generator[str, Any, Any]:
     def parse_race_names(self, selector: Selector, **_) -> Generator[RaceName, Any, Any]:
         hrefs = selector.xpath('//*[@id="col-a"]/div/section/div[5]/table/tbody/tr[*]/td[*]/a').getall()
         selectors = [Selector(h) for h in hrefs]
-        pairs = [(s.xpath("//*/@href").get("").split("r=")[-1], s.xpath("//*/text()").get("")) for s in selectors]
-        return (RaceName(race_id=p[0], name=whitespaces_clean(p[1]).upper()) for p in pairs)
+        return (
+            RaceName(
+                race_id=s.xpath("//*/@href").get("").split("r=")[-1],
+                name=whitespaces_clean(s.xpath("//*/text()").get("")).upper(),
+            )
+            for s in selectors
+        )
 
     @override
     def parse_lineup(self, *_, **__):

rscraping/parsers/html/arc.py

@@ -112,8 +112,13 @@ def parse_race_names(self, selector: Selector, **_) -> Generator[RaceName, Any,
             else selector.xpath('//*[@id="main"]/div[4]/table/tbody/tr[*]/td[2]/span/a').getall()
         )
         selectors = [Selector(h) for h in hrefs]
-        pairs = [(s.xpath("//*/@href").get("").split("/")[-2], s.xpath("//*/text()").get("")) for s in selectors]
-        return (RaceName(race_id=p[0], name=whitespaces_clean(p[1]).upper()) for p in pairs)
+        return (
+            RaceName(
+                race_id=s.xpath("//*/@href").get("").split("/")[-2],
+                name=whitespaces_clean(s.xpath("//*/text()").get("")).upper(),
+            )
+            for s in selectors
+        )
 
     def parse_club_ids(self, selector: Selector) -> Generator[str, Any, Any]:
         urls = (