Merge branch 'main' into feat/test

scrapers/atcoder.py

@@ -12,10 +12,36 @@ def parse_problem_url(contest_id: str, problem_letter: str) -> str:
     return f"https://atcoder.jp/contests/{contest_id}/tasks/{task_id}"
 
 
+def extract_problem_from_row(row, contest_id: str) -> dict[str, str] | None:
+    cells = row.find_all("td")
+    if len(cells) < 2:
+        return None
+
+    task_link = cells[1].find("a")
+    if not task_link:
+        return None
+
+    task_name = task_link.get_text(strip=True)
+    task_href = task_link.get("href", "")
+
+    if not task_href:
+        return None
+
+    task_id = task_href.split("/")[-1]
+    if not task_id.startswith(contest_id + "_"):
+        return None
+
+    problem_letter = task_id[len(contest_id) + 1 :]
+    if not problem_letter or not task_name:
+        return None
+
+    return {"id": problem_letter.lower(), "name": task_name}
+
+
 def scrape_contest_problems(contest_id: str) -> list[dict[str, str]]:
     try:
-        contest_url: str = f"https://atcoder.jp/contests/{contest_id}/tasks"
+        contest_url = f"https://atcoder.jp/contests/{contest_id}/tasks"
-        headers: dict[str, str] = {
+        headers = {
             "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
         }
 
@@ -23,31 +49,18 @@ def scrape_contest_problems(contest_id: str) -> list[dict[str, str]]:
         response.raise_for_status()
 
         soup = BeautifulSoup(response.text, "html.parser")
-        problems: list[dict[str, str]] = []
-
         task_table = soup.find("table", class_="table")
+
         if not task_table:
             return []
 
-        rows = task_table.find_all("tr")[1:]  # Skip header row
+        rows = task_table.find_all("tr")[1:]
+        problems = []
 
         for row in rows:
-            cells = row.find_all("td")
+            problem = extract_problem_from_row(row, contest_id)
-            if len(cells) >= 2:
+            if problem:
-                task_link = cells[1].find("a")
+                problems.append(problem)
-                if task_link:
-                    task_name: str = task_link.get_text(strip=True)
-                    task_href: str = task_link.get("href", "")
-
-                    # Extract problem letter from task name or URL
-                    task_id: str = task_href.split("/")[-1] if task_href else ""
-                    if task_id.startswith(contest_id + "_"):
-                        problem_letter: str = task_id[len(contest_id) + 1 :]
-
-                        if problem_letter and task_name:
-                            problems.append(
-                                {"id": problem_letter.lower(), "name": task_name}
-                            )
 
         problems.sort(key=lambda x: x["id"])
         return problems
@@ -57,9 +70,38 @@ def scrape_contest_problems(contest_id: str) -> list[dict[str, str]]:
         return []
 
 
+def extract_test_case_from_headers(sample_headers, i: int) -> tuple[str, str] | None:
+    if i >= len(sample_headers):
+        return None
+
+    header = sample_headers[i]
+    if "input" not in header.get_text().lower():
+        return None
+
+    input_pre = header.find_next("pre")
+    if not input_pre or i + 1 >= len(sample_headers):
+        return None
+
+    next_header = sample_headers[i + 1]
+    if "output" not in next_header.get_text().lower():
+        return None
+
+    output_pre = next_header.find_next("pre")
+    if not output_pre:
+        return None
+
+    input_text = input_pre.get_text().strip().replace("\r", "")
+    output_text = output_pre.get_text().strip().replace("\r", "")
+
+    if not input_text or not output_text:
+        return None
+
+    return (input_text, output_text)
+
+
 def scrape(url: str) -> list[tuple[str, str]]:
     try:
-        headers: dict[str, str] = {
+        headers = {
             "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
         }
 
@@ -68,32 +110,19 @@ def scrape(url: str) -> list[tuple[str, str]]:
 
         soup = BeautifulSoup(response.text, "html.parser")
 
-        tests: list[tuple[str, str]] = []
-
         sample_headers = soup.find_all(
             "h3", string=lambda x: x and "sample" in x.lower() if x else False
         )
 
+        tests = []
         i = 0
+
         while i < len(sample_headers):
-            header = sample_headers[i]
+            test_case = extract_test_case_from_headers(sample_headers, i)
-            if "input" in header.get_text().lower():
+            if test_case:
-                input_pre = header.find_next("pre")
+                tests.append(test_case)
-                if input_pre and i + 1 < len(sample_headers):
-                    next_header = sample_headers[i + 1]
-                    if "output" in next_header.get_text().lower():
-                        output_pre = next_header.find_next("pre")
-                        if output_pre:
-                            input_text: str = (
-                                input_pre.get_text().strip().replace("\r", "")
-                            )
-                            output_text: str = (
-                                output_pre.get_text().strip().replace("\r", "")
-                            )
-                            if input_text and output_text:
-                                tests.append((input_text, output_text))
                 i += 2
-                        continue
+            else:
                 i += 1
 
         return tests

scrapers/cses.py

@@ -15,10 +15,36 @@ def parse_problem_url(problem_input: str) -> str | None:
     return None
 
 
+def process_problem_element(
+    element, current_category: str, all_categories: dict
+) -> str | None:
+    if element.name == "h1":
+        category_name = element.get_text().strip()
+        if category_name not in all_categories:
+            all_categories[category_name] = []
+        return category_name
+
+    if element.name != "a" or "/problemset/task/" not in element.get("href", ""):
+        return current_category
+
+    href = element.get("href", "")
+    if not href:
+        return current_category
+
+    problem_id = href.split("/")[-1]
+    problem_name = element.get_text(strip=True)
+
+    if not (problem_id.isdigit() and problem_name and current_category):
+        return current_category
+
+    all_categories[current_category].append({"id": problem_id, "name": problem_name})
+    return current_category
+
+
 def scrape_all_problems() -> dict[str, list[dict[str, str]]]:
     try:
-        problemset_url: str = "https://cses.fi/problemset/"
+        problemset_url = "https://cses.fi/problemset/"
-        headers: dict[str, str] = {
+        headers = {
             "User-Agent": "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/120.0.0.0 Safari/537.36"
         }
 
@@ -26,27 +52,17 @@ def scrape_all_problems() -> dict[str, list[dict[str, str]]]:
         response.raise_for_status()
 
         soup = BeautifulSoup(response.text, "html.parser")
-        all_categories: dict[str, list[dict[str, str]]] = {}
+        all_categories = {}
 
         problem_links = soup.find_all(
             "a", href=lambda x: x and "/problemset/task/" in x
         )
         print(f"Found {len(problem_links)} problem links", file=sys.stderr)
 
-        current_category: str | None = None
+        current_category = None
         for element in soup.find_all(["h1", "a"]):
-            if element.name == "h1":
+            current_category = process_problem_element(
-                current_category = element.get_text().strip()
+                element, current_category, all_categories
-                if current_category not in all_categories:
-                    all_categories[current_category] = []
-            elif element.name == "a" and "/problemset/task/" in element.get("href", ""):
-                href: str = element.get("href", "")
-                problem_id: str = href.split("/")[-1]
-                problem_name: str = element.get_text(strip=True)
-
-                if problem_id.isdigit() and problem_name and current_category:
-                    all_categories[current_category].append(
-                        {"id": problem_id, "name": problem_name}
             )
 
         for category in all_categories:
@@ -60,24 +76,14 @@ def scrape_all_problems() -> dict[str, list[dict[str, str]]]:
         return {}
 
 
-def scrape(url: str) -> list[tuple[str, str]]:
+def extract_example_test_case(soup) -> tuple[str, str] | None:
-    try:
-        headers: dict[str, str] = {
-            "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")
-
-        tests: list[tuple[str, str]] = []
     example_header = soup.find("h1", string="Example")
+    if not example_header:
+        return None
 
-        if example_header:
     current = example_header.find_next_sibling()
-            input_text: str | None = None
+    input_text = None
-            output_text: str | None = None
+    output_text = None
 
     while current:
         if current.name == "p" and "Input:" in current.get_text():
@@ -91,10 +97,28 @@ def scrape(url: str) -> list[tuple[str, str]]:
                 break
         current = current.find_next_sibling()
 
-            if input_text and output_text:
+    if not input_text or not output_text:
-                tests.append((input_text, output_text))
+        return None
 
-        return tests
+    return (input_text, output_text)
+
+
+def scrape(url: str) -> list[tuple[str, str]]:
+    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")
+
+        test_case = extract_example_test_case(soup)
+        if not test_case:
+            return []
+
+        return [test_case]
 
     except Exception as e:
         print(f"Error scraping CSES: {e}", file=sys.stderr)