Update

Author: jaebradley

basketball_reference_web_scraper/contracts/__init__.py

@@ -0,0 +1,28 @@
+import dataclasses
+import enum
+from typing import Optional, Dict
+
+
+@dataclasses.dataclass(frozen=True)
+class PlayerData:
+    name: str
+    identifier: str
+
+
+class SalaryOption(enum.Enum):
+    PLAYER = "player"
+    TEAM = "team"
+
+
+@dataclasses.dataclass(frozen=True)
+class SeasonSalaryData:
+    value: str
+    season_identifier: str
+    option: Optional[SalaryOption]
+
+
+@dataclasses.dataclass(frozen=True)
+class RowData:
+    player: PlayerData
+    team_id: str
+    salary_by_season: Dict[str, Optional[SeasonSalaryData]]

basketball_reference_web_scraper/contracts/data.py

@@ -0,0 +1,54 @@
+import enum
+from typing import Dict, Any, Optional
+
+from lxml.etree import Element
+
+from .data import PlayerData
+
+
+class Column(enum.Enum):
+    PLAYER = "player"
+    TEAM = "team_id"
+    FIRST_SEASON_SALARY = "y1"
+    SECOND_SEASON_SALARY = "y2"
+    THIRD_SEASON_SALARY = "y3"
+    FOURTH_SEASON_SALARY = "y4"
+    FIFTH_SEASON_SALARY = "y5"
+    SIXTH_SEASON_SALARY = "y6"
+
+
+class SingleCellFinder:
+    def __init__(self, column: Column):
+        self.column = column
+
+    def find(self, row: Element) -> Optional[Element]:
+        matching_cells = row.xpath(f'./td[@data-stat="{self.column.value}"]')
+        if 1 == len(matching_cells):
+            return matching_cells[0]
+
+
+class SingleCellValueReader:
+    def __init__(self, cell_finder: SingleCellFinder, cell_reader):
+        self.cell_finder = cell_finder
+        self.cell_reader = cell_reader
+
+    def read(self, row: Element):
+        cell = self.cell_finder.find(row=row)
+        if cell:
+            return self.cell_reader.read(cell=cell)
+
+
+class RowDataReader:
+    def __init__(self, cell_readers_by_column: Dict[Column, SingleCellValueReader]):
+        self.cell_readers_by_column = cell_readers_by_column
+
+    def read(self, row: Element) -> Dict[Column, Optional[Any]]:
+        return dict(map(lambda e: [e[0], e[1].read(row=row)], self.cell_readers_by_column.items()))
+
+
+class PlayerDataCellReader:
+    def __init__(self, player_identifier_attribute_name):
+        self.player_identifier_attribute_name = player_identifier_attribute_name
+
+    def read(self, cell: Element) -> PlayerData:
+        return PlayerData(name=cell.text_content(), identifier=cell.get(self.player_identifier_attribute_name))

basketball_reference_web_scraper/contracts/readers.py

@@ -1,8 +1,12 @@
 import re
+from typing import Dict, Set, Tuple
 
 from lxml import html
 from lxml.html import HtmlComment
 
+from basketball_reference_web_scraper.contracts.readers import RowDataReader, Column, PlayerDataCellReader, \
+    SingleCellValueReader, SingleCellFinder
+
 
 class BasicBoxScoreRow:
     def __init__(self, html):
@@ -1231,10 +1235,37 @@ def losses(self):
         return None
 
 
+class PlayerContractsTableReader:
+    def __init__(self, row_reader):
+        self.row_reader = row_reader
+
+    @property
+    def column_names_by_identifier(self) -> Dict[str, str]:
+        return dict(
+            filter(lambda value: 1 == len(value[1]),
+                   map(lambda expected_header_identifier: (
+                       expected_header_identifier,
+                       self.html.xpath(f'.//th[@scope="col"]/[@data-stat="{expected_header_identifier}]')),
+                       Column)))
+
+    def rows(self, table):
+        for row_html in table.xpath('./tbody/tr[not[@class]]'):
+            yield PlayerContractsTableReader.row_reader.read(row=row_html)
+
+
 class PlayerContractsRow:
     def __init__(self, html):
         self.html = html
 
+    def retrieve_cell(self, statistic_identifier: str, attributes: Set[str]) -> Tuple[str, Dict[str, str]]:
+        matching_cells = self.html.xpath(f'.//td[@data-stat="{statistic_identifier}')
+
+        if 1 == len(matching_cells):
+            cell = matching_cells[0]
+            return cell.text_content(), dict(map(lambda attribute: [attribute, cell.get(attribute)], attributes))
+
+        raise ValueError(f"expected exactly one matching cell for statistic identifier {statistic_identifier}")
+
     @property
     def player_name(self):
         matching_cells = self.html.xpath('.//td[@data-stat="player"]')