Skip to content

fixed encoding issues and added singular "visit" and "besuch" #1

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

Open
ByJuka wants to merge 1 commit into
base: main
Choose a base branch
from
Open

fixed encoding issues and added singular "visit" and "besuch" #1

Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
7 changes: 3 additions & 4 deletions scraper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,7 +66,7 @@ def __init__(self, input_dir: str, output_dir: str):

self.toplist_pattern = re.compile(r"\[(\d{2}:\d{2}:\d{2})].*?#(\d+)\s+([^\[]+)")
self.crate_open_pattern = re.compile(
r"\b(?:ffnest eine crate vom typ|you are opening a crate of the type) ([^\[]+)\b",
r"\b(?:öffnest eine crate vom typ|you are opening a crate of the type) ([^\[]+)\b",
re.IGNORECASE
)
self.crate_drop_pattern = re.compile(
Expand Down Expand Up @@ -115,7 +115,7 @@ def process_archive(self, archive: str) -> None:

try:
archive_path = os.path.join(self.input_dir, archive)
with gzip.open(archive_path, "rt", errors="replace") as log_file:
with gzip.open(archive_path, "rt", encoding="utf-8", errors="replace") as log_file:
for line in log_file:
self.process_line(line, date)
print(f"Finished {archive}")
Expand Down Expand Up @@ -158,12 +158,11 @@ def __handle_toplist(self, line: str, date_time: str) -> bool:
return False

category = OutputType.Unsorted
if "Besuche" in info or "visits" in info:
if "Besuch" in info or "visit" in info:
category = OutputType.Warp
elif "$" in info:
category = OutputType.Guild
elif "Level" in info:
info = info.replace("?", "★")
category = OutputType.Level
elif "Job-XP" in info or "Job XP" in info:
category = OutputType.Job
Expand Down