feat(scrapers): update all scrapers to provide time & memory limit
This commit is contained in:
parent
e8157a5491
commit
aedbccffb4
4 changed files with 327 additions and 183 deletions
|
|
@ -1,18 +1,49 @@
|
|||
#!/usr/bin/env python3
|
||||
|
||||
import json
|
||||
import re
|
||||
import sys
|
||||
from dataclasses import asdict
|
||||
|
||||
import requests
|
||||
from bs4 import BeautifulSoup, Tag
|
||||
|
||||
from .models import MetadataResult, ProblemSummary, TestCase, TestsResult
|
||||
|
||||
|
||||
def extract_problem_limits(soup: BeautifulSoup) -> tuple[int, int]:
|
||||
timeout_ms = None
|
||||
memory_mb = None
|
||||
|
||||
paragraphs = soup.find_all("p")
|
||||
for p in paragraphs:
|
||||
text = p.get_text()
|
||||
if "Time Limit:" in text and "Memory Limit:" in text:
|
||||
time_match = re.search(r"Time Limit:\s*(\d+)\s*sec", text)
|
||||
if time_match:
|
||||
seconds = int(time_match.group(1))
|
||||
timeout_ms = seconds * 1000
|
||||
|
||||
memory_match = re.search(r"Memory Limit:\s*(\d+)\s*MiB", text)
|
||||
if memory_match:
|
||||
memory_mb = int(memory_match.group(1))
|
||||
break
|
||||
|
||||
if timeout_ms is None:
|
||||
raise ValueError("Could not find valid timeout in problem constraints")
|
||||
|
||||
if memory_mb is None:
|
||||
raise ValueError("Could not find valid memory limit in problem constraints")
|
||||
|
||||
return timeout_ms, memory_mb
|
||||
|
||||
|
||||
def parse_problem_url(contest_id: str, problem_letter: str) -> str:
|
||||
task_id: str = f"{contest_id}_{problem_letter}"
|
||||
return f"https://atcoder.jp/contests/{contest_id}/tasks/{task_id}"
|
||||
|
||||
|
||||
def extract_problem_from_row(row, contest_id: str) -> dict[str, str] | None:
|
||||
def extract_problem_from_row(row, contest_id: str) -> ProblemSummary | None:
|
||||
cells = row.find_all("td")
|
||||
if len(cells) < 2:
|
||||
return None
|
||||
|
|
@ -34,10 +65,10 @@ def extract_problem_from_row(row, contest_id: str) -> dict[str, str] | None:
|
|||
if not problem_letter or not task_name:
|
||||
return None
|
||||
|
||||
return {"id": problem_letter.lower(), "name": task_name}
|
||||
return ProblemSummary(id=problem_letter.lower(), name=task_name)
|
||||
|
||||
|
||||
def scrape_contest_problems(contest_id: str) -> list[dict[str, str]]:
|
||||
def scrape_contest_problems(contest_id: str) -> list[ProblemSummary]:
|
||||
try:
|
||||
contest_url = f"https://atcoder.jp/contests/{contest_id}/tasks"
|
||||
headers = {
|
||||
|
|
@ -53,13 +84,13 @@ def scrape_contest_problems(contest_id: str) -> list[dict[str, str]]:
|
|||
return []
|
||||
|
||||
rows = task_table.find_all("tr")[1:]
|
||||
problems: list[dict[str, str]] = []
|
||||
problems: list[ProblemSummary] = []
|
||||
for row in rows:
|
||||
problem = extract_problem_from_row(row, contest_id)
|
||||
if problem:
|
||||
problems.append(problem)
|
||||
|
||||
problems.sort(key=lambda x: x["id"])
|
||||
problems.sort(key=lambda x: x.id)
|
||||
return problems
|
||||
|
||||
except Exception as e:
|
||||
|
|
@ -95,7 +126,7 @@ def extract_test_case_from_headers(sample_headers, i: int) -> tuple[str, str] |
|
|||
return (input_text, output_text)
|
||||
|
||||
|
||||
def scrape(url: str) -> list[tuple[str, str]]:
|
||||
def scrape(url: str) -> list[TestCase]:
|
||||
try:
|
||||
headers = {
|
||||
"User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
|
||||
|
|
@ -109,12 +140,13 @@ def scrape(url: str) -> list[tuple[str, str]]:
|
|||
"h3", string=lambda x: x and "sample" in x.lower() if x else False
|
||||
)
|
||||
|
||||
tests: list[tuple[str, str]] = []
|
||||
tests: list[TestCase] = []
|
||||
i = 0
|
||||
while i < len(sample_headers):
|
||||
test_case = extract_test_case_from_headers(sample_headers, i)
|
||||
if test_case:
|
||||
tests.append(test_case)
|
||||
input_text, output_text = test_case
|
||||
tests.append(TestCase(input=input_text, expected=output_text))
|
||||
i += 2
|
||||
else:
|
||||
i += 1
|
||||
|
|
@ -128,64 +160,55 @@ def scrape(url: str) -> list[tuple[str, str]]:
|
|||
|
||||
def main() -> None:
|
||||
if len(sys.argv) < 2:
|
||||
print(
|
||||
json.dumps(
|
||||
{
|
||||
"success": False,
|
||||
"error": "Usage: atcoder.py metadata <contest_id> OR atcoder.py tests <contest_id> <problem_letter>",
|
||||
}
|
||||
)
|
||||
result = MetadataResult(
|
||||
success=False,
|
||||
error="Usage: atcoder.py metadata <contest_id> OR atcoder.py tests <contest_id> <problem_letter>",
|
||||
)
|
||||
print(json.dumps(asdict(result)))
|
||||
sys.exit(1)
|
||||
|
||||
mode: str = sys.argv[1]
|
||||
|
||||
if mode == "metadata":
|
||||
if len(sys.argv) != 3:
|
||||
print(
|
||||
json.dumps(
|
||||
{
|
||||
"success": False,
|
||||
"error": "Usage: atcoder.py metadata <contest_id>",
|
||||
}
|
||||
)
|
||||
result = MetadataResult(
|
||||
success=False,
|
||||
error="Usage: atcoder.py metadata <contest_id>",
|
||||
)
|
||||
print(json.dumps(asdict(result)))
|
||||
sys.exit(1)
|
||||
|
||||
contest_id: str = sys.argv[2]
|
||||
problems: list[dict[str, str]] = scrape_contest_problems(contest_id)
|
||||
problems: list[ProblemSummary] = scrape_contest_problems(contest_id)
|
||||
|
||||
if not problems:
|
||||
print(
|
||||
json.dumps(
|
||||
{
|
||||
"success": False,
|
||||
"error": f"No problems found for contest {contest_id}",
|
||||
}
|
||||
)
|
||||
result = MetadataResult(
|
||||
success=False,
|
||||
error=f"No problems found for contest {contest_id}",
|
||||
)
|
||||
print(json.dumps(asdict(result)))
|
||||
sys.exit(1)
|
||||
|
||||
print(
|
||||
json.dumps(
|
||||
{
|
||||
"success": True,
|
||||
"contest_id": contest_id,
|
||||
"problems": problems,
|
||||
}
|
||||
)
|
||||
result = MetadataResult(
|
||||
success=True,
|
||||
error="",
|
||||
contest_id=contest_id,
|
||||
problems=problems,
|
||||
)
|
||||
print(json.dumps(asdict(result)))
|
||||
|
||||
elif mode == "tests":
|
||||
if len(sys.argv) != 4:
|
||||
print(
|
||||
json.dumps(
|
||||
{
|
||||
"success": False,
|
||||
"error": "Usage: atcoder.py tests <contest_id> <problem_letter>",
|
||||
}
|
||||
)
|
||||
tests_result = TestsResult(
|
||||
success=False,
|
||||
error="Usage: atcoder.py tests <contest_id> <problem_letter>",
|
||||
problem_id="",
|
||||
url="",
|
||||
tests=[],
|
||||
timeout_ms=0,
|
||||
memory_mb=0,
|
||||
)
|
||||
print(json.dumps(asdict(tests_result)))
|
||||
sys.exit(1)
|
||||
|
||||
test_contest_id: str = sys.argv[2]
|
||||
|
|
@ -193,46 +216,59 @@ def main() -> None:
|
|||
problem_id: str = f"{test_contest_id}_{problem_letter.lower()}"
|
||||
|
||||
url: str = parse_problem_url(test_contest_id, problem_letter)
|
||||
print(f"Scraping: {url}", file=sys.stderr)
|
||||
tests: list[TestCase] = scrape(url)
|
||||
|
||||
tests: list[tuple[str, str]] = scrape(url)
|
||||
if not tests:
|
||||
print(
|
||||
json.dumps(
|
||||
{
|
||||
"success": False,
|
||||
"error": f"No tests found for {test_contest_id} {problem_letter}",
|
||||
"problem_id": problem_id,
|
||||
"url": url,
|
||||
}
|
||||
)
|
||||
try:
|
||||
headers = {
|
||||
"User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
|
||||
}
|
||||
response = requests.get(url, headers=headers, timeout=10)
|
||||
response.raise_for_status()
|
||||
soup = BeautifulSoup(response.text, "html.parser")
|
||||
timeout_ms, memory_mb = extract_problem_limits(soup)
|
||||
except Exception as e:
|
||||
tests_result = TestsResult(
|
||||
success=False,
|
||||
error=f"Failed to extract constraints: {e}",
|
||||
problem_id=problem_id,
|
||||
url=url,
|
||||
tests=[],
|
||||
timeout_ms=0,
|
||||
memory_mb=0,
|
||||
)
|
||||
print(json.dumps(asdict(tests_result)))
|
||||
sys.exit(1)
|
||||
|
||||
test_list: list[dict[str, str]] = [
|
||||
{"input": i, "expected": o} for i, o in tests
|
||||
]
|
||||
|
||||
print(
|
||||
json.dumps(
|
||||
{
|
||||
"success": True,
|
||||
"problem_id": problem_id,
|
||||
"url": url,
|
||||
"tests": test_list,
|
||||
}
|
||||
if not tests:
|
||||
tests_result = TestsResult(
|
||||
success=False,
|
||||
error=f"No tests found for {test_contest_id} {problem_letter}",
|
||||
problem_id=problem_id,
|
||||
url=url,
|
||||
tests=[],
|
||||
timeout_ms=timeout_ms,
|
||||
memory_mb=memory_mb,
|
||||
)
|
||||
print(json.dumps(asdict(tests_result)))
|
||||
sys.exit(1)
|
||||
|
||||
tests_result = TestsResult(
|
||||
success=True,
|
||||
error="",
|
||||
problem_id=problem_id,
|
||||
url=url,
|
||||
tests=tests,
|
||||
timeout_ms=timeout_ms,
|
||||
memory_mb=memory_mb,
|
||||
)
|
||||
print(json.dumps(asdict(tests_result)))
|
||||
|
||||
else:
|
||||
print(
|
||||
json.dumps(
|
||||
{
|
||||
"success": False,
|
||||
"error": f"Unknown mode: {mode}. Use 'metadata' or 'tests'",
|
||||
}
|
||||
)
|
||||
result = MetadataResult(
|
||||
success=False,
|
||||
error=f"Unknown mode: {mode}. Use 'metadata' or 'tests'",
|
||||
)
|
||||
print(json.dumps(asdict(result)))
|
||||
sys.exit(1)
|
||||
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue