TopDownHockey-Scraper 4.3.1__tar.gz → 5.0.0__tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Potentially problematic release.


This version of TopDownHockey-Scraper might be problematic. Click here for more details.

@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: TopDownHockey_Scraper
3
- Version: 4.3.1
3
+ Version: 5.0.0
4
4
  Summary: The TopDownHockey Scraper
5
5
  Home-page: https://github.com/TopDownHockey/TopDownHockey_Scraper
6
6
  Author: Patrick Bacon
@@ -1,6 +1,6 @@
1
1
  [metadata]
2
2
  name = TopDownHockey_Scraper
3
- version = 4.3
3
+ version = 5.0.0
4
4
  author = Patrick Bacon
5
5
  author_email = patrick.s.bacon@gmail.com
6
6
  description = A package built for scraping hockey data from EliteProspects, the NHL's HTML/API reports, and ESPN's XML reports.
@@ -9,7 +9,7 @@ with open("README.md", "r", encoding="utf-8") as fh:
9
9
 
10
10
  setup(
11
11
  name="TopDownHockey_Scraper", # Replace with your own username
12
- version="4.3.1",
12
+ version="5.0.0",
13
13
  author="Patrick Bacon",
14
14
  author_email="patrick.s.bacon@gmail.com",
15
15
  description="The TopDownHockey Scraper",
@@ -2011,15 +2011,17 @@ def scrape_espn_ids_single_game(game_date, home_team, away_team):
2011
2011
  soup_found = soup.find_all('a', {'class':['AnchorLink truncate',
2012
2012
  'AnchorLink Button Button--sm Button--anchorLink Button--alt mb4 w-100',
2013
2013
  'AnchorLink Button Button--sm Button--anchorLink Button--alt mb4 w-100 mr2'], 'href':[re.compile("/nhl/team/_/name/"), re.compile("game/_")]})
2014
+ game_sections = soup.find_all('section', class_ = 'Scoreboard bg-clr-white flex flex-auto justify-between')
2015
+
2014
2016
  at = []
2015
2017
  ht = []
2016
2018
  gids = []
2017
2019
  fax = pd.DataFrame()
2018
2020
  #print(str(i))
2019
- for i in range (0, ((len(soup_found)))):
2020
- away = soup_found[i]['href'].rsplit('/')[-1].split('-')[0].upper()
2021
- home = soup_found[i]['href'].rsplit('/')[-1].split('-')[-1].upper()
2022
- espnid = soup_found[i]['href'].rsplit('/')[-2]
2021
+ for i in range(0, len(game_sections)):
2022
+ away = game_sections[i].find_all('div', class_='ScoreCell__TeamName ScoreCell__TeamName--shortDisplayName db')[0].contents[0].upper()
2023
+ home = game_sections[i].find_all('div', class_='ScoreCell__TeamName ScoreCell__TeamName--shortDisplayName db')[1].contents[0].upper()
2024
+ espnid = game_sections[0]['id']
2023
2025
  at.append(away)
2024
2026
  ht.append(home)
2025
2027
  gids.append(espnid)
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.4
2
2
  Name: TopDownHockey_Scraper
3
- Version: 4.3.1
3
+ Version: 5.0.0
4
4
  Summary: The TopDownHockey Scraper
5
5
  Home-page: https://github.com/TopDownHockey/TopDownHockey_Scraper
6
6
  Author: Patrick Bacon