mirror of
https://github.com/NohamR/Bibmath2Tex.git
synced 2026-05-24 19:58:43 +00:00
239 lines
8.6 KiB
Python
239 lines
8.6 KiB
Python
from pprint import pprint
|
|
from bs4 import BeautifulSoup
|
|
import requests
|
|
import urllib.parse as urlparse
|
|
|
|
class Exercise:
|
|
def __init__(self, number, title, id, stars, enonce, indication, answer):
|
|
self.number = number
|
|
self.title = title
|
|
self.id = id
|
|
self.stars = stars
|
|
self.enonce = enonce
|
|
self.indication = indication
|
|
self.answer = answer
|
|
|
|
def __repr__(self):
|
|
return f"Exercise({self.number}, {self.title}, {self.id}, {self.stars})"
|
|
|
|
class Part:
|
|
def __init__(self, title):
|
|
self.title = title
|
|
self.exercises = []
|
|
|
|
def add_exercise(self, exercise):
|
|
self.exercises.append(exercise)
|
|
|
|
def __repr__(self):
|
|
return f"Part({self.title}, {len(self.exercises)} exercises)"
|
|
|
|
class Chapitre:
|
|
def __init__(self, title, url=None):
|
|
if ':' in title:
|
|
title = title.split(':')[1].strip()
|
|
title = title.lower()
|
|
title = title[0].upper() + title[1:] if title else ""
|
|
self.title = title
|
|
self.parts = []
|
|
self.url = url
|
|
|
|
def add_part(self, part):
|
|
self.parts.append(part)
|
|
|
|
def __repr__(self):
|
|
return f"Chapitre({self.title}, {len(self.parts)} parts)"
|
|
|
|
def show(self):
|
|
print(f"Chapitre: {self.title}")
|
|
for part in self.parts:
|
|
print(f" Part: {part.title}")
|
|
for exercise in part.exercises:
|
|
print(f" Exercise: {exercise.number}, {exercise.title}, {exercise.id}, {exercise.stars} stars")
|
|
print(f" Enonce: {exercise.enonce}")
|
|
print(f" Indication: {exercise.indication}")
|
|
print(f" Answer: {exercise.answer}")
|
|
|
|
class LatexFile:
|
|
def __init__(self, filename):
|
|
self.filename = filename
|
|
self.content = ""
|
|
|
|
def add_header(self):
|
|
with open('parts/header.tex', 'r') as f:
|
|
self.content += f.read()
|
|
|
|
def add_footer(self):
|
|
with open('parts/footer.tex', 'r') as f:
|
|
self.content += f.read()
|
|
|
|
def add_content(self, content):
|
|
self.content += content + "\n"
|
|
|
|
def add_pagebreak(self):
|
|
self.content += "\\newpage\n"
|
|
|
|
def add_source(self, chapitre):
|
|
self.content += f"\\noindent\\textbf{{Chapitre:}} \\href{{{chapitre.url}}}{{{chapitre.title}}}\n"
|
|
|
|
def add_exercise(self, exercise):
|
|
self.content += f"""\\exercice{{{exercise.id}, name, date, {exercise.stars}, {exercise.title}}}\n"""
|
|
self.content += f"""\\enonce{{{exercise.id}}}{{}}\n"""
|
|
self.content += f"{exercise.enonce}\n"
|
|
self.content += f"""\\finenonce{{{exercise.id}}}\n"""
|
|
self.content += f"""\\finexercice\n"""
|
|
self.content += "\n"
|
|
self.add_pagebreak()
|
|
self.content += "\n"
|
|
|
|
def add_indication(self, exercise):
|
|
self.content += f"""\\indication{{{exercise.id}}}\n"""
|
|
self.content += f"{exercise.indication}\n"
|
|
self.content += f"""\\finindication\n"""
|
|
self.content += "\n"
|
|
|
|
def add_answer(self, exercise):
|
|
self.content += f"""\\correction{{{exercise.id}}}\n"""
|
|
self.content += f"{exercise.answer}\n"
|
|
self.content += f"""\\fincorrection\n"""
|
|
self.content += "\n"
|
|
|
|
def sanitize(self):
|
|
# return self.content.encode('utf-8', 'ignore').decode('utf-8')
|
|
return self.content
|
|
|
|
def save(self):
|
|
with open(self.filename, 'w') as f:
|
|
f.write(self.sanitize())
|
|
|
|
def generate_latex(self, chapitre):
|
|
self.add_header()
|
|
|
|
self.add_source(chapitre)
|
|
|
|
self.add_content(f"\\title{{{chapitre.title}}}")
|
|
for part in chapitre.parts:
|
|
self.add_content(f"\\section{{{part.title}}}")
|
|
for ex in part.exercises:
|
|
self.add_exercise(ex)
|
|
|
|
self.add_pagebreak()
|
|
|
|
for part in chapitre.parts:
|
|
for ex in part.exercises:
|
|
self.add_indication(ex)
|
|
self.add_pagebreak()
|
|
|
|
for part in chapitre.parts:
|
|
for ex in part.exercises:
|
|
self.add_answer(ex)
|
|
|
|
self.add_footer()
|
|
self.save()
|
|
|
|
def parse(content):
|
|
soup2 = BeautifulSoup(str(content), 'lxml')
|
|
for tag in soup2.find_all(['span', 'a', 'img']):
|
|
tag.extract()
|
|
questions = []
|
|
ol_list = soup2.find('ol', class_='enumeratechiffre')
|
|
|
|
if ol_list:
|
|
for i, li in enumerate(ol_list.find_all('li'), 1):
|
|
if i == 1:
|
|
# Add a line break before the first question
|
|
questions.append("\\par")
|
|
questions.append(f"{i}. {li.get_text().strip()}")
|
|
list_text = "\n\n".join(questions)
|
|
ol_list.replace_with(list_text)
|
|
|
|
content = soup2.get_text().strip()
|
|
return content
|
|
|
|
def fetch_chapitre(page):
|
|
headers = {
|
|
'accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,image/apng,*/*;q=0.8',
|
|
'accept-language': 'fr-FR,fr;q=0.7',
|
|
'cache-control': 'no-cache',
|
|
'pragma': 'no-cache',
|
|
'priority': 'u=0, i',
|
|
'sec-ch-ua': '"Brave";v="131", "Chromium";v="131", "Not_A Brand";v="24"',
|
|
'sec-ch-ua-mobile': '?0',
|
|
'sec-ch-ua-platform': '"macOS"',
|
|
'sec-fetch-dest': 'document',
|
|
'sec-fetch-mode': 'navigate',
|
|
'sec-fetch-site': 'same-origin',
|
|
'sec-fetch-user': '?1',
|
|
'sec-gpc': '1',
|
|
'upgrade-insecure-requests': '1',
|
|
'user-agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/131.0.0.0 Safari/537.36',
|
|
}
|
|
response = requests.get(page, headers=headers)
|
|
if response.status_code == 200:
|
|
soup = BeautifulSoup(response.text, 'lxml')
|
|
article = soup.find('article', id='contenugauche')
|
|
|
|
if article:
|
|
title = article.find('h1').get_text(strip=True)
|
|
chapitre = Chapitre(title, url=response.url)
|
|
current_part = None
|
|
for element in article.find_all(recursive=False):
|
|
if 'titrepartie' in element.get('class', []):
|
|
part_title = element.get_text(strip=True)
|
|
current_part = Part(part_title)
|
|
chapitre.add_part(current_part)
|
|
elif 'exo' in element.get('class', []) and current_part is not None:
|
|
exo_title_div = element.find('div', class_='titreexo')
|
|
|
|
exercise_number = exo_title_div.find_all('span')[1].text.strip()
|
|
title_start = exo_title_div.text.find(' - ') + 3
|
|
title_end = exo_title_div.text.find('[Signaler une erreur]')
|
|
exercise_title = exo_title_div.text[title_start:title_end].strip()
|
|
|
|
error_link = exo_title_div.find('a', href=lambda href: href and 'signalerreur.php' in href)['href']
|
|
parsed_url = urlparse.urlparse(error_link)
|
|
exercise_id = urlparse.parse_qs(parsed_url.query)['numero'][0]
|
|
|
|
stars_count = len(exo_title_div.find_all('img'))
|
|
|
|
enonce = element.find('div', class_='enonce').find('div', class_='inner')
|
|
enonce = parse(enonce)
|
|
|
|
indication_div = element.find('div', class_='indication')
|
|
indication = indication_div.find('div', class_='inner')
|
|
indication = parse(indication)
|
|
|
|
answer_div = element.find('div', class_='corrige')
|
|
answer = answer_div.find('div', class_='inner')
|
|
answer = parse(answer)
|
|
|
|
exercise = Exercise(
|
|
number=exercise_number,
|
|
title=exercise_title,
|
|
id=exercise_id,
|
|
stars=stars_count,
|
|
enonce=enonce,
|
|
indication=indication,
|
|
answer=answer
|
|
)
|
|
|
|
current_part.add_exercise(exercise)
|
|
return chapitre
|
|
else:
|
|
print("Article with id 'contenugauche' not found.")
|
|
else:
|
|
print(f"Request failed with status code: {response.status_code}")
|
|
|
|
def get_page(page):
|
|
chapitre = fetch_chapitre(page)
|
|
title = chapitre.title
|
|
latex_file = LatexFile(f'dump/{title}.tex')
|
|
latex_file.generate_latex(chapitre)
|
|
print(f"LaTeX file generated: dump/{title}.tex")
|
|
|
|
if __name__ == "__main__":
|
|
# page = "https://bibmath.net/ressources/index.php?action=affiche&quoi=mpsi/feuillesexo/prehilbert&type=fexo"
|
|
# get_page(page)
|
|
with open('pages.txt', 'r') as f:
|
|
for line in f:
|
|
page = line.strip()
|
|
get_page(page) |