barrett/cp.nvim
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

fix scraper

Browse source
This commit is contained in:
Barrett Ruth 2025-09-15 10:52:28 -04:00
parent beb87e853c
commit 5db19acc53
2 changed files with 28 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

12
lua/cp/scrape.lua
View file

@ -74,9 +74,9 @@ function M.scrape_contest_metadata(platform, contest_id)
local args local args
if platform == "cses" then if platform == "cses" then
args = { "uv", "run", scraper_path, "metadata" } args = { "uv", "run", "--directory", plugin_path, scraper_path, "metadata" }
else else
args = { "uv", "run", scraper_path, "metadata", contest_id } args = { "uv", "run", "--directory", plugin_path, scraper_path, "metadata", contest_id }
end end
local result = vim.system(args, { local result = vim.system(args, {
@ -152,9 +152,9 @@ function M.scrape_problem(ctx)
local args local args
if ctx.contest == "cses" then if ctx.contest == "cses" then
args = { "uv", "run", scraper_path, "tests", ctx.contest_id } args = { "uv", "run", "--directory", plugin_path, scraper_path, "tests", ctx.contest_id }
else else
args = { "uv", "run", scraper_path, "tests", ctx.contest_id, ctx.problem_id } args = { "uv", "run", "--directory", plugin_path, scraper_path, "tests", ctx.contest_id, ctx.problem_id }
end end
local result = vim.system(args, { local result = vim.system(args, {
@ -188,8 +188,8 @@ function M.scrape_problem(ctx)
local combined_input = data.test_cases[1].input:gsub("\r", "") local combined_input = data.test_cases[1].input:gsub("\r", "")
local combined_output = data.test_cases[1].output:gsub("\r", "") local combined_output = data.test_cases[1].output:gsub("\r", "")
vim.fn.writefile(vim.split(combined_input, "\n"), ctx.input_file) vim.fn.writefile(vim.split(combined_input, "\n", true), ctx.input_file)
vim.fn.writefile(vim.split(combined_output, "\n"), ctx.expected_file) vim.fn.writefile(vim.split(combined_output, "\n", true), ctx.expected_file)
end end
return { return {

31
scrapers/codeforces.py
View file

@ -25,12 +25,24 @@ def scrape(url: str) -> list[tuple[str, str]]:
for inp_section in input_sections: for inp_section in input_sections:
inp_pre = inp_section.find("pre") inp_pre = inp_section.find("pre")
if inp_pre: if inp_pre:
all_inputs.append(inp_pre.get_text().strip().replace("\r", "")) divs = inp_pre.find_all("div")
if divs:
lines = [div.get_text().strip() for div in divs]
text = "\n".join(lines)
else:
text = inp_pre.get_text().replace("\r", "")
all_inputs.append(text)
for out_section in output_sections: for out_section in output_sections:
out_pre = out_section.find("pre") out_pre = out_section.find("pre")
if out_pre: if out_pre:
all_outputs.append(out_pre.get_text().strip().replace("\r", "")) divs = out_pre.find_all("div")
if divs:
lines = [div.get_text().strip() for div in divs]
text = "\n".join(lines)
else:
text = out_pre.get_text().replace("\r", "")
all_outputs.append(text)
if all_inputs and all_outputs: if all_inputs and all_outputs:
combined_input = "\n".join(all_inputs) combined_input = "\n".join(all_inputs)
@ -103,11 +115,12 @@ def main() -> None:
print(json.dumps(result)) print(json.dumps(result))
sys.exit(1) sys.exit(1)
mode: str = sys.argv[1] mode: str = sys.argv[1]
if mode == "metadata": if mode == "metadata":
if len(sys.argv) != 3: if len(sys.argv) != 3:
result = { result: dict[str, str | bool] = {
"success": False, "success": False,
"error": "Usage: codeforces.py metadata <contest_id>", "error": "Usage: codeforces.py metadata <contest_id>",
} }
@ -118,14 +131,14 @@ def main() -> None:
problems: list[dict[str, str]] = scrape_contest_problems(contest_id) problems: list[dict[str, str]] = scrape_contest_problems(contest_id)
if not problems: if not problems:
result = { result: dict[str, str | bool] = {
"success": False, "success": False,
"error": f"No problems found for contest {contest_id}", "error": f"No problems found for contest {contest_id}",
} }
print(json.dumps(result)) print(json.dumps(result))
sys.exit(1) sys.exit(1)
result = { result: dict[str, str | bool | list] = {
"success": True, "success": True,
"contest_id": contest_id, "contest_id": contest_id,
"problems": problems, "problems": problems,
@ -134,7 +147,7 @@ def main() -> None:
elif mode == "tests": elif mode == "tests":
if len(sys.argv) != 4: if len(sys.argv) != 4:
result = { result: dict[str, str | bool] = {
"success": False, "success": False,
"error": "Usage: codeforces.py tests <contest_id> <problem_letter>", "error": "Usage: codeforces.py tests <contest_id> <problem_letter>",
} }
@ -149,7 +162,7 @@ def main() -> None:
tests: list[tuple[str, str]] = scrape_sample_tests(url) tests: list[tuple[str, str]] = scrape_sample_tests(url)
if not tests: if not tests:
result = { result: dict[str, str | bool] = {
"success": False, "success": False,
"error": f"No tests found for {contest_id} {problem_letter}", "error": f"No tests found for {contest_id} {problem_letter}",
"problem_id": problem_id, "problem_id": problem_id,
@ -162,7 +175,7 @@ def main() -> None:
for input_data, output_data in tests: for input_data, output_data in tests:
test_cases.append({"input": input_data, "output": output_data}) test_cases.append({"input": input_data, "output": output_data})
result = { result: dict[str, str | bool | list] = {
"success": True, "success": True,
"problem_id": problem_id, "problem_id": problem_id,
"url": url, "url": url,
@ -171,7 +184,7 @@ def main() -> None:
print(json.dumps(result)) print(json.dumps(result))
else: else:
result = { result: dict[str, str | bool] = {
"success": False, "success": False,
"error": f"Unknown mode: {mode}. Use 'metadata' or 'tests'", "error": f"Unknown mode: {mode}. Use 'metadata' or 'tests'",
} }