hkjc 0.3.21__py3-none-any.whl → 0.3.22__py3-none-any.whl

hkjc/historical.py

@@ -15,12 +15,21 @@ HKJC_HORSE_URL_TEMPLATE = "https://racing.hkjc.com/racing/information/English/Ho
 incidents = ['DISQ', 'DNF', 'FE', 'ML', 'PU', 'TNP', 'TO',
              'UR', 'VOID', 'WR', 'WV', 'WV-A', 'WX', 'WX-A', 'WXNR']
 
+REQUEST_TIMEOUT = 10
+
+HTML_HEADERS = {
+    "Origin": "https://racing.hkjc.com",
+    "Referer": "https://racing.hkjc.com",
+    "Content-Type": "text/plain",
+    "Accept": "*/*",
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/141.0.0.0 Safari/537.36",
+}
 
 @ttl_cache(maxsize=100, ttl=3600)
 def _soupify(url: str) -> BeautifulSoup:
     """Fetch and parse a webpage and return BeautifulSoup object
     """
-    response = requests.get(url, timeout=180)
+    response = requests.get(url, timeout=REQUEST_TIMEOUT, headers=HTML_HEADERS)
     response.raise_for_status()
     return BeautifulSoup(response.content, 'html.parser')
 
@@ -43,6 +52,9 @@ def _soupify_horse_page(horse_no: str) -> BeautifulSoup:
 def _classify_running_style(df: pl.DataFrame, running_pos_col="RunningPosition") -> pl.DataFrame:
     """Classify running style based on RunningPosition column
     """
+    if df.height == 0:
+        return df
+    
     # Split the RunningPosition column into separate columns and convert to integers
     df = df.with_columns(
         pl.col(running_pos_col)
@@ -77,9 +89,9 @@ def _extract_horse_data(horse_no: str) -> pl.DataFrame:
     table = soup.find('table', class_='bigborder')
     horse_data = _parse_html_table(table).filter(
         pl.col('Date') != '')  # Remove empty rows
-    horse_data = _classify_running_style(horse_data)
-
-    horse_data = horse_data.with_columns(pl.lit(horse_no).alias('HorseNo'))
+    if horse_data.height > 0:
+        horse_data = _classify_running_style(horse_data)
+        horse_data = horse_data.with_columns(pl.lit(horse_no).alias('HorseNo'))
 
     return horse_data
 
@@ -87,6 +99,9 @@ def _extract_horse_data(horse_no: str) -> pl.DataFrame:
 def _clean_horse_data(df: pl.DataFrame) -> pl.DataFrame:
     """ Clean and convert horse data to suitable data types
     """
+    if df.height == 0:
+        return df
+    
     df = df.with_columns(
         pl.col('Pla').str.split(' ').list.first().alias('Pla')
     ).filter(~pl.col('Pla').is_in(incidents))
@@ -105,7 +120,8 @@ def _clean_horse_data(df: pl.DataFrame) -> pl.DataFrame:
           .with_columns(
         (
             pl.col("FinishTime").str.splitn(".", 2).struct.field("field_0").cast(pl.Int64) * 60 +
-            pl.col("FinishTime").str.splitn(".", 2).struct.field("field_1").cast(pl.Float64)
+            pl.col("FinishTime").str.splitn(
+                ".", 2).struct.field("field_1").cast(pl.Float64)
         ).cast(pl.Float64).round(2).alias("FinishTime")
     ))
 
@@ -134,6 +150,9 @@ def get_horse_data(horse_no: str) -> pl.DataFrame:
 def _clean_race_data(df: pl.DataFrame) -> pl.DataFrame:
     """ Clean and convert horse data to suitable data types
     """
+    if df.height == 0:
+        return df
+    
     df = df.with_columns(
         pl.col('Pla').str.split(' ').list.first().alias('Pla')
     ).filter(~pl.col('Pla').is_in(incidents))
@@ -150,7 +169,8 @@ def _clean_race_data(df: pl.DataFrame) -> pl.DataFrame:
     df = df.with_columns(
         (
             pl.col("FinishTime").str.splitn(":", 2).struct.field("field_0").cast(pl.Int64) * 60 +
-            pl.col("FinishTime").str.splitn(":", 2).struct.field("field_1").cast(pl.Float64)
+            pl.col("FinishTime").str.splitn(
+                ":", 2).struct.field("field_1").cast(pl.Float64)
         ).cast(pl.Float64).round(2).alias("FinishTime")
     )
 

hkjc/live.py

@@ -7,6 +7,8 @@ import requests
 from cachetools.func import ttl_cache
 import numpy as np
 
+from .utils import _try_int
+
 HKJC_LIVEODDS_ENDPOINT = "https://info.cld.hkjc.com/graphql/base/"
 
 RACEMTG_PAYLOAD = {
@@ -241,25 +243,29 @@ query racing($date: String, $venueCode: String, $oddsTypes: [OddsType], $raceNo:
 }""",
 }
 
+JSON_HEADERS = {
+    "Origin": "https://bet.hkjc.com",
+    "Referer": "https://bet.hkjc.com",
+    "Content-Type": "application/json",
+    "Accept": "application/json",
+    "User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/141.0.0.0 Safari/537.36",
+}
+
+REQUEST_TIMEOUT = 30
+
 
 @ttl_cache(maxsize=12, ttl=1000)
-def _fetch_live_races(date: str=None, venue_code: str=None) -> dict:
+def _fetch_live_races(date: str = None, venue_code: str = None) -> dict:
     """Fetch live race data from HKJC GraphQL endpoint."""
     payload = RACEMTG_PAYLOAD.copy()
     payload["variables"] = payload["variables"].copy()
     payload["variables"]["date"] = date
     payload["variables"]["venueCode"] = venue_code
 
-    headers = {
-        "Origin": "https://bet.hkjc.com",
-        "Referer": "https://bet.hkjc.com",
-        "Content-Type": "application/json",
-        "Accept": "application/json",
-        "User-Agent": "python-hkjc-fetch/0.1",
-    }
+    headers = JSON_HEADERS
 
     r = requests.post(HKJC_LIVEODDS_ENDPOINT, json=payload,
-                      headers=headers, timeout=10)
+                      headers=headers, timeout=REQUEST_TIMEOUT)
     if r.status_code != 200:
         raise RuntimeError(f"Request failed: {r.status_code} - {r.text}")
 
@@ -279,9 +285,9 @@ def _fetch_live_races(date: str=None, venue_code: str=None) -> dict:
         runners = [{'No': runner['no'],
                     'Name': runner['name_en'],
                     'Dr': runner['barrierDrawNumber'],
-                    'Rtg': int(runner['currentRating']),
-                    'Wt': int(runner['currentWeight']),
-                    'Handicap': int(runner['handicapWeight']),
+                    'Rtg': _try_int(runner['currentRating']),
+                    'Wt': _try_int(runner['currentWeight']),
+                    'Handicap': _try_int(runner['handicapWeight']),
                     'HorseNo': runner['horse']['code']
                     } for runner in race['runners'] if runner['status'] != "Standby"]
         race_info['Races'][race_num] = {
@@ -307,16 +313,10 @@ def _fetch_live_odds(date: str, venue_code: str, race_number: int, odds_type: Tu
     payload["variables"]["raceNo"] = race_number
     payload["variables"]["oddsTypes"] = odds_type
 
-    headers = {
-        "Origin": "https://bet.hkjc.com",
-        "Referer": "https://bet.hkjc.com",
-        "Content-Type": "application/json",
-        "Accept": "application/json",
-        "User-Agent": "python-hkjc-fetch/0.1",
-    }
+    headers = JSON_HEADERS
 
     r = requests.post(HKJC_LIVEODDS_ENDPOINT, json=payload,
-                      headers=headers, timeout=10)
+                      headers=headers, timeout=REQUEST_TIMEOUT)
     if r.status_code != 200:
         raise RuntimeError(f"Request failed: {r.status_code} - {r.text}")
 
@@ -354,7 +354,8 @@ def live_odds(date: str, venue_code: str, race_number: int, odds_type: List[str]
     N = len(race_info['Races'][race_number]['Runners'])
 
     if (race_info['Date'] != date) or (race_info['Venue'] != venue_code):
-        print(f"[WARNING] Requested {date} {venue_code} but server returned {race_info['Date']} {race_info['Venue']}.")
+        print(
+            f"[WARNING] Requested {date} {venue_code} but server returned {race_info['Date']} {race_info['Venue']}.")
         date = race_info['Date']
         venue_code = race_info['Venue']
 

hkjc/utils.py

@@ -4,6 +4,12 @@ from datetime import datetime as dt
 import bs4
 import re
 
+def _try_int(value: str) -> int:
+    try:
+        return int(value)
+    except:
+        return 0
+    
 
 def _validate_date(date_str: str) -> bool:
     # validate date format

{hkjc-0.3.21.dist-info → hkjc-0.3.22.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: hkjc
-Version: 0.3.21
+Version: 0.3.22
 Summary: Library for scrapping HKJC data and perform basic analysis
 Requires-Python: >=3.11
 Requires-Dist: beautifulsoup4>=4.14.2

{hkjc-0.3.21.dist-info → hkjc-0.3.22.dist-info}/RECORD

@@ -1,14 +1,14 @@
 hkjc/__init__.py,sha256=XSm9N6YbZ2SzyxjO9aR26ctB4Z1-VeBImuroSgncUfk,737
 hkjc/features.py,sha256=LicwtKBpMzpz_dSX9bjoCLLaRUu8oeZo1AloTe7v7sI,298
 hkjc/harville_model.py,sha256=WSA_1EcNOHKGraP6WVHJ3FXZPGrDrjKhJc_q70KKx80,20188
-hkjc/historical.py,sha256=aONchf7CMNs2B-WVDS_GWg8g0U0ZEH-FjbfhdJwc_N0,7683
-hkjc/live.py,sha256=CfMeHRQfhKSmhQaexM99sdP0KRbIEqg2DIvNPc1gohk,10696
+hkjc/historical.py,sha256=22qpMFI7IQ5bfXuGma5jJAtx8chRp4FE-XCIF4RqwTo,8238
+hkjc/live.py,sha256=YZgwSLDFq5v1yxNwjTtQxgU2ru4yvooxpjHksDar1TA,10691
 hkjc/processing.py,sha256=hQnHxl6HYlFOeSLSOCVsemgTKcwt9_tYUQI-itpvjUg,7188
 hkjc/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 hkjc/speedpro.py,sha256=Y2Z3GYGeePc4sM-ZnCHXCI1N7L-_j9nrMqS3CC5BBSo,2031
-hkjc/utils.py,sha256=4CA_FPf_U3GvzoLkqBX0qDPZgrSvKJKvbP7VWqd5FiA,6323
+hkjc/utils.py,sha256=uAiFmy5NXsADUiD1-MCPgs1hs4N3e7tVYtSREkxwKSQ,6425
 hkjc/strategy/place_only.py,sha256=lHPjTSj8PzghxncNBg8FI4T4HJigekB9a3bV7l7VtPA,2079
 hkjc/strategy/qpbanker.py,sha256=MQxjwsfhllKZroKS8w8Q3bi3HMjGc1DAyBIjNZAp3yQ,4805
-hkjc-0.3.21.dist-info/METADATA,sha256=YuIC0EvFVS3Z-8cwdzczMV7qQxMYvIKtO442iUQu5Jg,480
-hkjc-0.3.21.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-hkjc-0.3.21.dist-info/RECORD,,
+hkjc-0.3.22.dist-info/METADATA,sha256=gM8crCYg0Wq-W8GFa0Jyk6RYdT-3MUXrAXpl6ID7VcM,480
+hkjc-0.3.22.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+hkjc-0.3.22.dist-info/RECORD,,