initial commit
This commit is contained in:
commit
dcb7debff6
29 changed files with 1276 additions and 0 deletions
87
templates/scrapers/atcoder.py
Normal file
87
templates/scrapers/atcoder.py
Normal file
|
|
@ -0,0 +1,87 @@
|
|||
#!/usr/bin/env python3
|
||||
|
||||
import sys
|
||||
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
|
||||
def parse_problem_url(contest_id: str, problem_letter: str) -> str:
|
||||
task_id = f"{contest_id}_{problem_letter}"
|
||||
return f"https://atcoder.jp/contests/{contest_id}/tasks/{task_id}"
|
||||
|
||||
|
||||
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")
|
||||
|
||||
tests = []
|
||||
|
||||
sample_headers = soup.find_all(
|
||||
"h3", string=lambda x: x and "sample" in x.lower() if x else False
|
||||
)
|
||||
|
||||
i = 0
|
||||
while i < len(sample_headers):
|
||||
header = sample_headers[i]
|
||||
if "input" in header.get_text().lower():
|
||||
input_pre = header.find_next("pre")
|
||||
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 = input_pre.get_text().strip().replace("\r", "")
|
||||
output_text = (
|
||||
output_pre.get_text().strip().replace("\r", "")
|
||||
)
|
||||
if input_text and output_text:
|
||||
tests.append((input_text, output_text))
|
||||
i += 2
|
||||
continue
|
||||
i += 1
|
||||
|
||||
return tests
|
||||
|
||||
except Exception as e:
|
||||
print(f"Error scraping AtCoder: {e}", file=sys.stderr)
|
||||
return []
|
||||
|
||||
|
||||
def main():
|
||||
if len(sys.argv) != 3:
|
||||
print("Usage: atcoder.py <contest_id> <problem_letter>", file=sys.stderr)
|
||||
print("Example: atcoder.py abc042 a", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
contest_id = sys.argv[1]
|
||||
problem_letter = sys.argv[2]
|
||||
|
||||
url = parse_problem_url(contest_id, problem_letter)
|
||||
print(f"Scraping: {url}", file=sys.stderr)
|
||||
|
||||
tests = scrape(url)
|
||||
|
||||
if not tests:
|
||||
print(f"No tests found for {contest_id} {problem_letter}", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
print("---INPUT---")
|
||||
print(len(tests))
|
||||
for input_data, output_data in tests:
|
||||
print(input_data)
|
||||
print("---OUTPUT---")
|
||||
for input_data, output_data in tests:
|
||||
print(output_data)
|
||||
print("---END---")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
104
templates/scrapers/codeforces.py
Normal file
104
templates/scrapers/codeforces.py
Normal file
|
|
@ -0,0 +1,104 @@
|
|||
#!/usr/bin/env python3
|
||||
|
||||
import sys
|
||||
|
||||
import cloudscraper
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
|
||||
def scrape(url: str):
|
||||
try:
|
||||
scraper = cloudscraper.create_scraper()
|
||||
response = scraper.get(url, timeout=10)
|
||||
response.raise_for_status()
|
||||
|
||||
soup = BeautifulSoup(response.text, "html.parser")
|
||||
tests = []
|
||||
|
||||
input_sections = soup.find_all("div", class_="input")
|
||||
output_sections = soup.find_all("div", class_="output")
|
||||
|
||||
for inp_section, out_section in zip(input_sections, output_sections):
|
||||
inp_pre = inp_section.find("pre")
|
||||
out_pre = out_section.find("pre")
|
||||
|
||||
if inp_pre and out_pre:
|
||||
input_lines = []
|
||||
output_lines = []
|
||||
|
||||
for line_div in inp_pre.find_all("div", class_="test-example-line"):
|
||||
input_lines.append(line_div.get_text().strip())
|
||||
|
||||
output_divs = out_pre.find_all("div", class_="test-example-line")
|
||||
if not output_divs:
|
||||
output_text_raw = out_pre.get_text().strip().replace("\r", "")
|
||||
output_lines = [
|
||||
line.strip()
|
||||
for line in output_text_raw.split("\n")
|
||||
if line.strip()
|
||||
]
|
||||
else:
|
||||
for line_div in output_divs:
|
||||
output_lines.append(line_div.get_text().strip())
|
||||
|
||||
if input_lines and output_lines:
|
||||
if len(input_lines) > 1 and input_lines[0].isdigit():
|
||||
test_count = int(input_lines[0])
|
||||
remaining_input = input_lines[1:]
|
||||
for i in range(min(test_count, len(output_lines))):
|
||||
if i < len(remaining_input):
|
||||
tests.append((remaining_input[i], output_lines[i]))
|
||||
else:
|
||||
input_text = "\n".join(input_lines)
|
||||
output_text = "\n".join(output_lines)
|
||||
tests.append((input_text, output_text))
|
||||
|
||||
return tests
|
||||
|
||||
except Exception as e:
|
||||
print(f"CloudScraper failed: {e}", file=sys.stderr)
|
||||
return []
|
||||
|
||||
|
||||
def parse_problem_url(contest_id: str, problem_letter: str) -> str:
|
||||
return (
|
||||
f"https://codeforces.com/contest/{contest_id}/problem/{problem_letter.upper()}"
|
||||
)
|
||||
|
||||
|
||||
def scrape_sample_tests(url: str):
|
||||
print(f"Scraping: {url}", file=sys.stderr)
|
||||
return scrape(url)
|
||||
|
||||
|
||||
def main():
|
||||
if len(sys.argv) != 3:
|
||||
print("Usage: codeforces.py <contest_id> <problem_letter>", file=sys.stderr)
|
||||
print("Example: codeforces.py 1234 A", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
contest_id = sys.argv[1]
|
||||
problem_letter = sys.argv[2]
|
||||
|
||||
url = parse_problem_url(contest_id, problem_letter)
|
||||
tests = scrape_sample_tests(url)
|
||||
|
||||
if not tests:
|
||||
print(f"No tests found for {contest_id} {problem_letter}", file=sys.stderr)
|
||||
print(
|
||||
"Consider adding test cases manually to the io/ directory", file=sys.stderr
|
||||
)
|
||||
sys.exit(1)
|
||||
|
||||
print("---INPUT---")
|
||||
print(len(tests))
|
||||
for input_data, output_data in tests:
|
||||
print(input_data)
|
||||
print("---OUTPUT---")
|
||||
for input_data, output_data in tests:
|
||||
print(output_data)
|
||||
print("---END---")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
88
templates/scrapers/cses.py
Executable file
88
templates/scrapers/cses.py
Executable file
|
|
@ -0,0 +1,88 @@
|
|||
#!/usr/bin/env python3
|
||||
|
||||
import sys
|
||||
|
||||
import requests
|
||||
from bs4 import BeautifulSoup
|
||||
|
||||
|
||||
def parse_problem_url(problem_input: str) -> str | None:
|
||||
if problem_input.startswith("https://cses.fi/problemset/task/"):
|
||||
return problem_input
|
||||
elif problem_input.isdigit():
|
||||
return f"https://cses.fi/problemset/task/{problem_input}"
|
||||
return None
|
||||
|
||||
|
||||
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")
|
||||
|
||||
tests = []
|
||||
example_header = soup.find("h1", string="Example")
|
||||
|
||||
if example_header:
|
||||
current = example_header.find_next_sibling()
|
||||
input_text = None
|
||||
output_text = None
|
||||
|
||||
while current:
|
||||
if current.name == "p" and "Input:" in current.get_text():
|
||||
input_pre = current.find_next_sibling("pre")
|
||||
if input_pre:
|
||||
input_text = input_pre.get_text().strip()
|
||||
elif current.name == "p" and "Output:" in current.get_text():
|
||||
output_pre = current.find_next_sibling("pre")
|
||||
if output_pre:
|
||||
output_text = output_pre.get_text().strip()
|
||||
break
|
||||
current = current.find_next_sibling()
|
||||
|
||||
if input_text and output_text:
|
||||
tests.append((input_text, output_text))
|
||||
|
||||
return tests
|
||||
|
||||
except Exception as e:
|
||||
print(f"Error scraping CSES: {e}", file=sys.stderr)
|
||||
return []
|
||||
|
||||
|
||||
def main():
|
||||
if len(sys.argv) != 2:
|
||||
print("Usage: cses.py <problem_id_or_url>", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
problem_input = sys.argv[1]
|
||||
url = parse_problem_url(problem_input)
|
||||
|
||||
if not url:
|
||||
print(f"Invalid problem input: {problem_input}", file=sys.stderr)
|
||||
print("Use either problem ID (e.g., 1068) or full URL", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
tests = scrape(url)
|
||||
|
||||
if not tests:
|
||||
print(f"No tests found for {problem_input}", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
print("---INPUT---")
|
||||
print(len(tests))
|
||||
for input_data, output_data in tests:
|
||||
print(input_data)
|
||||
print("---OUTPUT---")
|
||||
for input_data, output_data in tests:
|
||||
print(output_data)
|
||||
print("---END---")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
Loading…
Add table
Add a link
Reference in a new issue