File size: 3,132 Bytes
f438d4c 6f71715 f438d4c 86f48c4 598ca45 f438d4c 598ca45 f438d4c 598ca45 f438d4c 598ca45 f438d4c 598ca45 f438d4c 598ca45 f438d4c 598ca45 f438d4c 598ca45 f438d4c 598ca45 f438d4c 598ca45 f438d4c 598ca45 f438d4c 598ca45 f438d4c 598ca45 f438d4c 598ca45 86f48c4 598ca45 f438d4c 598ca45 f438d4c 86f48c4 6f71715 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 |
from bs4 import BeautifulSoup
import requests
import numpy as np
from datetime import datetime
from xhtml2pdf import pisa
import io
def gen_link():
if np.random.choice([True, False]):
# AMC
np.random.seed()
year = np.random.randint(2015, 2023)
AB = np.random.choice(['A', 'B'])
# Question
mu, sigma = 18, 5
s = np.random.normal(mu, sigma, 1000)
s = np.round(s)
s = s[(s >= 10) & (s <= 25)]
q = int(np.random.choice(s))
link = f'https://artofproblemsolving.com/wiki/index.php/{year}_AMC_12{AB}_Problems/Problem_{q}'
else:
# AIME
np.random.seed()
year = np.random.randint(2005, 2023)
I = np.random.choice(['I', 'II'])
mu, sigma = 6, 4
s = np.random.normal(mu, sigma, 1000)
s = np.round(s)
s = s[(s >= 1) & (s <= 15)]
q = int(np.random.choice(s))
link = f'https://artofproblemsolving.com/wiki/index.php/{year}_AIME_{I}_Problems/Problem_{q}'
return link
def convert_to_renderable_html(text):
text = text.replace('//latex.artofproblemsolving.com', 'https://latex.artofproblemsolving.com')
return text
def get_problem(url):
headers = {
"User-Agent": "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.3"
}
response = requests.get(url, headers=headers)
soup = BeautifulSoup(response.text, 'html.parser')
problem_headline = soup.find('span', {'class': 'mw-headline', 'id': 'Problem'})
if problem_headline:
problem_content = []
for sibling in problem_headline.parent.find_next_siblings():
if sibling.name == 'h2':
break
elif sibling.name == 'p':
problem_content.append(convert_to_renderable_html(str(sibling)))
problem_html = " ".join(problem_content)
return problem_html
else:
print("No problem found")
def gen_html(num):
all_q = str()
num_tried = 0
num_succ = 0
while True:
try:
link = gen_link()
print(link)
hype = f'<a href="{link}" target="_blank">to link</a>'
qhtml = get_problem(link)
all_q += (hype + qhtml)
num_succ += 1
except Exception as e:
print(f"Error: {e}")
pass
num_tried += 1
if num_succ >= num or num_tried > 20:
break
all_q = f'''
<html>
<head>
<style>
body {{
font-family: Arial, sans-serif;
font-size: 12pt;
}}
img.latex {{
font-size: 12pt; /* Ensure math font size matches the body text size */
}}
</style>
</head>
<body>
{all_q}
</body>
</html>
'''
return all_q
def convert_html_to_pdf(source_html, output_filename):
result_file = open(output_filename, "w+b")
pisa_status = pisa.CreatePDF(
io.StringIO(source_html),
dest=result_file
)
result_file.close()
return pisa_status.err
|