Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[SoFIFA] Update parsing of player profile page #794

Merged
merged 2 commits into from
Jan 21, 2025
Merged

[SoFIFA] Update parsing of player profile page #794

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
e2a9540
fix(SoFIFA): update parsing of player profile page
probberechts Jan 21, 2025
e56c771
Merge branch 'master' into fix/iss-793
probberechts Jan 21, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
19 changes: 13 additions & 6 deletions soccerdata/sofifa.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,7 +10,11 @@
import pandas as pd
from lxml import html

from ._common import BaseRequestsReader, add_standardized_team_name, standardize_colnames
from ._common import (
BaseRequestsReader,
add_standardized_team_name,
standardize_colnames,
)
from ._config import DATA_DIR, NOCACHE, NOSTORE, TEAMNAME_REPLACEMENTS, logger

SO_FIFA_DATADIR = DATA_DIR / "SoFIFA"
Expand Down Expand Up @@ -108,7 +112,7 @@ def read_leagues(self) -> pd.DataFrame:
leagues.append(
{
"league_id": child["id"],
"league": f'[{child["nationName"]}] {child["value"]}',
"league": f"[{child['nationName']}] {child['value']}",
}
)
return (
Expand Down Expand Up @@ -462,15 +466,18 @@ def read_player_ratings(

# extract scores one-by-one
tree = html.parse(reader, parser=html.HTMLParser(encoding="utf8"))
node_player_name = tree.xpath("//div[contains(@class, 'profile')]/h1")[0]
# Extract what is before <br>
before_br = node_player_name.xpath("string(./text()[1])").strip()
# Extract what is after <br>
after_br = node_player_name.xpath("string(./br/following-sibling::text()[1])").strip()
scores = {
"player": tree.xpath("//div[contains(@class, 'profile')]/h1")[0].text.strip(),
"player": before_br if before_br else after_br,
**version.to_dict(),
}
for s in score_labels:
nodes = tree.xpath(
"(//li[not(self::script)] | //div | //p)"
f"[.//text()[contains(.,'{s}')]]"
"/em"
f"(//li[not(self::script)] | //div | //p)[.//text()[contains(.,'{s}')]]//em"
)
# for multiple matches, only accept first match
if len(nodes) >= 1:
Expand Down
Loading