|
| 1 | +from selenium import webdriver |
| 2 | +from selenium.webdriver.common.desired_capabilities import DesiredCapabilities |
| 3 | +from selenium.webdriver.support.ui import WebDriverWait |
| 4 | +from selenium.webdriver.support import expected_conditions as EC |
| 5 | +from selenium.webdriver.common.by import By |
| 6 | +from selenium.common.exceptions import NoSuchElementException |
| 7 | +from selenium.common.exceptions import TimeoutException |
| 8 | +import os |
| 9 | +from fpdf import FPDF |
| 10 | + |
| 11 | +options = webdriver.ChromeOptions() |
| 12 | +options.add_argument("--headless") |
| 13 | + |
| 14 | + |
| 15 | +capa = DesiredCapabilities.CHROME |
| 16 | +capa["pageLoadStrategy"] = "none" |
| 17 | + |
| 18 | +print("Enter Chrome Driver path: ") |
| 19 | +input_driver_path = input() |
| 20 | +driver = webdriver.Chrome(input_driver_path) |
| 21 | +#the base url of leetcode problem set page |
| 22 | +baseurl="https://leetcode.com/problemset/all" |
| 23 | +wait = WebDriverWait(driver, 15) |
| 24 | + |
| 25 | +#the difficulty level of all the of all the problems |
| 26 | +problem_difficulty = {"Easy": "?difficulty=Easy", "Medium": "?difficulty=Medium", "Hard": "?difficulty=hard"} |
| 27 | + |
| 28 | +def get_problem(category, no_of_problems): |
| 29 | + |
| 30 | + prblm_info = {} |
| 31 | + try: |
| 32 | + #checking if there is no network or any other iisue |
| 33 | + driver.get(baseurl + '/' + category) |
| 34 | + wait.until(EC.element_to_be_clickable((By.XPATH, "//*[@id='question-app']/div/div[2]/div[2]/div[2]/table/tbody[1]/tr[1]"))) |
| 35 | + except TimeoutException as exception: |
| 36 | + print("Couldn't fetch problem. Network issue or page slow to render. Try again") |
| 37 | + os._exit(-1) |
| 38 | + |
| 39 | + for problem_index in range(1, no_of_problems + 1): |
| 40 | + #set problem name |
| 41 | + problem_name = driver.find_element_by_xpath("//*[@id='question-app']/div/div[2]/div[2]/div[2]/table/tbody[1]/tr[{}]/td[3]".format(problem_index)).text |
| 42 | + #set problem url |
| 43 | + problem_url = driver.find_element_by_xpath("//*[@id='question-app']/div/div[2]/div[2]/div[2]/table/tbody[1]/tr[{}]/td[3]/div/a".format(problem_index)).get_attribute('href') |
| 44 | + print(problem_name," ",problem_url) |
| 45 | + prblm_info[problem_name] = problem_url |
| 46 | + return prblm_info |
| 47 | + |
| 48 | +def get_description(problem_url,problem_name): |
| 49 | + try: |
| 50 | + #check if the element is founded, and located in the correct format |
| 51 | + driver.get(problem_url) |
| 52 | + wait.until(EC.element_to_be_clickable((By.XPATH, "//*[@id='app']/div/div[2]/div/div/div[1]/div/div[1]/div[1]/div/div[2]/div/div[2]/div/p[1]"))) |
| 53 | + problem_title= problem_name |
| 54 | + problem_statement = driver.find_element_by_xpath("//*[@id='app']/div/div[2]/div/div/div[1]/div/div[1]/div[1]/div/div[2]/div/div[2]/div/p[1]").text |
| 55 | + problem_test_cases = driver.find_element_by_xpath("//*[@id='app']/div/div[2]/div/div/div[1]/div/div[1]/div[1]/div/div[2]/div/div[2]/div/pre[1]").text |
| 56 | + |
| 57 | + |
| 58 | + if (problem_test_cases.find("Output") == -1): |
| 59 | + problem_test_cases = "Input\n" + problem_test_cases |
| 60 | + problem_test_cases+="\nOutput\n" |
| 61 | + problem_test_cases += driver.find_element_by_xpath("//*[@id='problem-statement']/pre[2]").text |
| 62 | + |
| 63 | + else: |
| 64 | + driver.execute_script("window.stop();") |
| 65 | + problem={'title':problem_title,'statement':problem_statement,'test_case':problem_test_cases,'url':problem_url} |
| 66 | + return problem |
| 67 | + |
| 68 | + except NoSuchElementException as e: |
| 69 | + print("Couldn't scrap the element, Unable to locate it") |
| 70 | + problem=None |
| 71 | + except TimeoutException as exception: |
| 72 | + print("Couldn't scrap the element, Unable to locate it") |
| 73 | + problem=None |
| 74 | + |
| 75 | +def to_pdf(problem): |
| 76 | + pdf = FPDF() |
| 77 | + pdf.add_page() |
| 78 | + pdf.set_font("Arial", size = 15) |
| 79 | + #set title |
| 80 | + title=problem["title"].encode('latin-1', 'replace').decode('latin-1') |
| 81 | + #set statement |
| 82 | + statement=problem["statement"].encode('latin-1', 'replace').decode('latin-1') |
| 83 | + #set test cases |
| 84 | + test_case=problem["test_case"].encode('latin-1', 'replace').decode('latin-1') |
| 85 | + #set url |
| 86 | + url=problem["url"] |
| 87 | + pdf.cell(200, 10, txt =title, ln = 1, align = 'C') |
| 88 | + pdf.multi_cell(200, 10, txt =statement, align = 'L') |
| 89 | + pdf.multi_cell(200, 10, txt =test_case, align = 'L') |
| 90 | + pdf.write(5, 'Problem_Link: ') |
| 91 | + pdf.write(5,url,url) |
| 92 | + title = title.rstrip() |
| 93 | + pdf.output("./LeetCode-Scrapper/"+title+".pdf") |
| 94 | + |
| 95 | + |
| 96 | +def main(): |
| 97 | + category=input("Choose difficulty level from \n Easy \n Medium \n Hard \n\n : ") |
| 98 | + no_of_problems=int(input("Enter the number of problems to be scrapped : ")) |
| 99 | + info = get_problem(problem_difficulty[category], no_of_problems) |
| 100 | + for name, url in info.items(): |
| 101 | + problem=get_description(url,name) |
| 102 | + if(problem is not None ): |
| 103 | + to_pdf(problem) |
| 104 | + else: |
| 105 | + pass |
| 106 | + |
| 107 | +if __name__ == '__main__': |
| 108 | + main() |
| 109 | + |
| 110 | +#Close the driver path |
| 111 | +driver.close() |
0 commit comments