import requests
from bs4 import BeautifulSoup
url = "https://codeforces.com/problemset/page/11?tags=binary+search"
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
questions = soup.find_all('div', class_='problem-statement')
question_texts = [q.find('div', class_='title').text for q in questions]
total_questions = len(question_texts)
first_five_words = [q.split()[:5] for q in question_texts[:5]]
last_five_words = [q.split()[:5] for q in question_texts[-5:]]
print("Total questions:", total_questions)
print("First 5 words of the first question:", first_five_words)
print("First 5 words of the last 5 questions:", last_five_words)
I know this code isn't working bcoz its web scrapping, can anyone tell me how do I use Codeforces API for the same? To fetch all the questions under binary search and store them as a Python list. I am doing this for a Project where I have to train a Transformer model over Programming Problem Statements.
Auto comment: topic has been updated by illuminati_13 (previous revision, new revision, compare).
Auto comment: topic has been updated by illuminati_13 (previous revision, new revision, compare).
Auto comment: topic has been updated by illuminati_13 (previous revision, new revision, compare).
Auto comment: topic has been updated by illuminati_13 (previous revision, new revision, compare).
here is the corrected and working code without codeforces api that i have wrote ,hope it helps
import requests
from bs4 import BeautifulSoup
def getproblems(url):
problems= [] response = requests.get(url) soup = BeautifulSoup(response.content, 'html.parser') problem_links = soup.find_all('a', href=lambda href: href and "/problemset/problem" in href) for link in problem_links: name=(link.get_text().strip()) original_link = link['href'] # Extracting the number and problem code from the original link parts = original_link.split("/") number = parts[-2] problem_code = parts[-1] # Constructing the full link with the correct format full_link = f"https://codeforces.com/problemset/status/{number}/problem/{problem_code}" if(name !=(number+problem_code)): problems.append(name) return problemsurl = "https://codeforces.com/problemset/page/11?tags=binary+search"
response = requests.get(url)
soup = BeautifulSoup(response.text, 'html.parser')
questions = getproblems(url)
total_questions = len(questions) first_five_words = [q[:5] for q in questions[:5]] last_five_words = [q[-5:] for q in questions[-5:]]
print("Total questions:", total_questions) print("First 5 words of the first question:", first_five_words) print("First 5 words of the last 5 questions:", last_five_words)
print(questions)