Create a distinction between old style race and new style race 3rd try

first_cycling_api/combi.py

@@ -0,0 +1,57 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Sun May 14 15:39:13 2023
+
+@author: maxime
+"""
+from .race.race import RaceEdition
+
+def combi_results_startlist(race_id, year,**kwargs):
+    try:
+        r=RaceEdition(race_id=race_id,year=year)
+        t=r.results(**kwargs)
+
+        if t is None or ("results_table" in t.__dir__() and t.results_table is None):
+                #case of race not completed yet
+                r=RaceEdition(race_id=race_id,year=year)
+                kwargs.update(stage_num=1)
+                t=r.results(**kwargs)
+        if t is None or ("results_table" in t.__dir__() and (t.results_table is None or not "Inv name" in t.results_table.columns)):    
+            #fallback TTT
+            kwargs.update(stage_num=2)
+            t=r.results(**kwargs)
+
+        if "results_table" in t.__dir__():
+            results_table=t.results_table
+        else:
+            results_table=t
+
+        print(results_table)
+        print("Inv name" in results_table.columns)
+
+        start_list=r.startlist()
+
+        """ Convert HTML table from bs4 to pandas DataFrame. Return None if no data. """
+        # TODO for rider results, format dates nicely with hidden column we are throwing away
+
+        if "Inv name" in results_table.columns:
+            for i in results_table.index:
+                try:
+                    results_table.loc[i,"BIB"]=start_list.bib_df.loc[results_table.loc[i,"Inv name"]]["BIB"]
+                except:
+                    print(results_table.loc[i,"Inv name"] + " not found in the start list")
+                    results_table.loc[i,"BIB"]=0
+            t.results_table=results_table
+        else:
+            print("No Inv name in results_table, the stage may be a TTT")
+            return None
+
+        return t
+    except Exception as msg:
+        import sys
+        _, _, exc_tb = sys.exc_info()
+        print("line " + str(exc_tb.tb_lineno))
+        print(msg)
+
+

first_cycling_api/parser.py

@@ -75,18 +75,34 @@ def parse_table(table):
 			out_df[col] = out_df[col].astype(str).str.replace('.', '', regex=False).astype(int)
 
 	# Parse soup to add information hidden in tags/links
+
 	headers = [th.text for th in table.find_all('th')]
 	trs = [tr for tr in table.find_all('tr') if tr.th is None]
 
 	if 'Race.1' in out_df:
 		out_df = out_df.rename(columns={'Race': 'Race_Country', 'Race.1': 'Race'})
 		headers.insert(headers.index('Race'), 'Race_Country')
-
+
+	for col in out_df.columns: #problems with \nRider\n
+   		if "Rider" in col:
+   			out_df = out_df.rename(columns={col: 'Rider'})
+   			break
+	for i, col in enumerate(headers): #problems with \nRider\n
+   		if "Rider" in col:
+   			headers[i]='Rider'
+   			break
+
 	soup_df = pd.DataFrame([tr.find_all('td') for tr in trs], columns=headers)
 
 	# Add information hidden in tags
 	for col, series in soup_df.items():
 		if col in ('Rider', 'Winner', 'Second', 'Third'):
+			if col =="Rider":
+				out_df["Rider"]=out_df["Rider"].str.replace("[*]","",regex=False)
+				out_df["Rider"]=out_df["Rider"].str.replace("*","",regex=False)
+				out_df["Rider"]=out_df["Rider"].str.replace("  "," " ,regex=False)
+				out_df["Inv name"]=out_df["Rider"].str.lower()
+
 			out_df[col + '_ID'] = series.apply(lambda td: rider_link_to_id(td.a))
 			try:
 				out_df[col + '_Country'] = series.apply(lambda td: img_to_country_code(td.img))

first_cycling_api/race/endpoints.py

@@ -1,6 +1,6 @@
 from ..endpoints import ParsedEndpoint
 from ..parser import parse_table
-
+import pandas as pd
 
 class RaceEndpoint(ParsedEndpoint):
 	"""
@@ -48,7 +48,10 @@ def _get_victory_table(self):
 		victory_table = self.soup.find('table', {'class': 'tablesorter'})
 		self.table = parse_table(victory_table)
 
-
+class Standing():
+    def __init__(self, results_table):
+        self.results_table=results_table
+
 class RaceStageVictories(RaceEndpoint):
 	"""
 	Race stage victory table response. Extends RaceEndpoint.
@@ -86,14 +89,48 @@ def _parse_soup(self):
 		self._get_sidebar_information()
 
 	def _get_results_table(self):
-		results_table = self.soup.find('table', {'class': 'sortTabell'})
+		results_table = self.soup.find('table', {'class': 'sortTabell tablesorter'})
 		if not results_table:
-			results_table = self.soup.find('table', {'class': 'sortTabell2'})
-		self.results_table = parse_table(results_table)
 
-		# Load all classification standings after stage
-		divs = self.soup.find_all('div', {'class': "tab-content"})
-		self.standings = {div['id']: parse_table(div.table) for div in divs}
+		    results_table = self.soup.find('table', {'class': 'sortTabell2 tablesorter'})
+
+		if results_table: #old race type
+		    self.results_table = parse_table(results_table)
+
+    		# Load all classification standings after stage
+		    divs = self.soup.find_all('div', {'class': "tab-content dummy"})
+		    self.standings = {div['id']: Standing(parse_table(div.table)) for div in divs} #may not work and require the use of l=classification num  
+
+		else: #new race type
+		    divs = self.soup.find_all('div', {'class': "tab-content"}) #includes also tab-content results
+		    self.standings= {div['id']: Standing(parse_table(div.table)) for div in divs}
+
+		    self.results_table = self.standings[divs[0]['id']].results_table #first appearing is the result 
+
 
 	def _get_sidebar_information(self): # TODO
 		return
+
+class RaceEditionStartlist(RaceEndpoint): 
+    def _parse_soup(self):
+        super()._parse_soup()
+        self._get_results_table()
+
+    def _get_results_table(self):    
+        tables = self.soup.find_all('table', {'class': 'tablesorter'})
+
+        arr=[]
+
+        for t in tables:
+           sub_df=pd.read_html(str(t), decimal=',')[0]
+           sub_df.columns=["BIB","Inv name"]
+           sub_df["Inv name"]=sub_df["Inv name"].str.lower()
+           sub_df["Inv name"]=sub_df["Inv name"].str.replace("[*]","",regex=False)
+           sub_df["Inv name"]=sub_df["Inv name"].str.replace(" *","",regex=False)
+           sub_df["Inv name"]=sub_df["Inv name"].str.replace("*","",regex=False)
+           sub_df["Inv name"]=sub_df["Inv name"].str.replace("  "," " ,regex=False)
+
+           arr.append(sub_df)
+
+        bib_df =pd.concat(arr)
+        self.bib_df = bib_df.set_index(bib_df["Inv name"])

first_cycling_api/race/race.py

@@ -1,5 +1,5 @@
 from ..objects import FirstCyclingObject
-from .endpoints import RaceEndpoint, RaceVictoryTable, RaceStageVictories, RaceEditionResults
+from .endpoints import RaceEndpoint, RaceVictoryTable, RaceStageVictories, RaceEditionResults, RaceEditionStartlist
 from ..api import fc
 from ..constants import Classification
 
@@ -161,7 +161,7 @@ def startlist(self):
 		-------
 		RaceEndpoint
 		"""
-		return self._get_endpoint(k=8)
+		return self._get_endpoint(k=8,endpoint=RaceEditionStartlist)
 
 	def startlist_extended(self):
 		"""

tests/test_combi.py

@@ -0,0 +1,83 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+"""
+Created on Sun May 14 16:26:19 2023
+
+@author: maxime
+"""
+
+from first_cycling_api.combi import combi_results_startlist
+import numpy as np
+
+def test_combi_2019_amstel(): 
+    t = combi_results_startlist(9,2019)
+
+    assert len(t.results_table) == 175
+    assert t.results_table['Rider'].iloc[0] == 'van der Poel Mathieu'
+    assert t.results_table['BIB'].iloc[0] ==181
+
+def test_2022_TdF():
+    t = combi_results_startlist(17,2022)
+
+    assert len(t.results_table) == 176
+    assert t.results_table['Rider'].iloc[0] == 'Vingegaard Jonas'
+    assert t.results_table['BIB'].iloc[0] == 18
+
+    t = combi_results_startlist(17,2022,classification_num=1)
+    assert len(t.results_table) == 176
+    assert t.results_table['Rider'].iloc[0] == 'Vingegaard Jonas'
+    assert t.results_table['BIB'].iloc[0] == 18
+
+    t = combi_results_startlist(17,2022,classification_num=2)
+    assert len(t.results_table) == 26
+    assert t.results_table['Rider'].iloc[0] == "Pogacar Tadej"
+    assert t.results_table['Time'].iloc[0] == "79:36:03"
+
+
+
+def test_combi_2023_itzulia(): 
+    t = combi_results_startlist(14244,2023,stage_num=1)
+
+    assert len(t.results_table) == 113
+    assert t.results_table['Rider'].iloc[0] == 'Vollering Demi'
+    assert t.results_table['BIB'].iloc[0] ==1
+
+    assert 'gc' in t.standings
+    assert 'point' in t.standings
+    assert 'mountain' in t.standings
+    assert 'youth' in t.standings
+
+    t = combi_results_startlist(14244,2023,stage_num=1,classification_num=1)
+    assert t.results_table['Rider'].iloc[0] == 'Vollering Demi'
+    assert t.results_table['BIB'].iloc[0] ==1
+
+    t = combi_results_startlist(14244,2023,stage_num=1,classification_num=3)
+    assert t.results_table['Rider'].iloc[0] == 'Vollering Demi'
+    assert t.results_table['BIB'].iloc[0] ==1
+
+def test_combi_2023_gracia(): 
+    t = combi_results_startlist(9549,2023,stage_num=3)
+
+    assert len(t.results_table) == 128
+    assert t.results_table['Rider'].iloc[0] == 'Rissveds Jenny'
+    assert t.results_table['BIB'].iloc[0] ==73
+
+    assert 'gc' in t.standings
+    assert 'point' in t.standings
+    assert 'mountain' in t.standings
+    assert 'youth' in t.standings
+
+    #t = combi_results_startlist(9549,2023,stage_num=3,classification_num=3)
+    #assert t.results_table['Rider'].iloc[0] == 'Wlodarczyk Dominika'
+
+def test_giro_donne_2001():
+    t = combi_results_startlist(9064,2001,stage_num=1)
+    assert len(t.results_table) == 10
+
+    #t = combi_results_startlist(9064,2001,stage_num=1,classification_num=3) #not existing
+    #assert t==None
+
+
+
+
+