pushh

grab.py

@@ -29,6 +29,10 @@ class Part:
     
 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
@@ -124,7 +128,26 @@ class LatexFile:
         self.add_footer()
         self.save()
 
-def fetch_chapitre(quoi):
+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',
@@ -142,12 +165,7 @@ def fetch_chapitre(quoi):
         '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',
     }
-    params = {
-        'action': 'affiche',
-        'quoi': quoi,
-        'type': 'fexo',
-    }
-    response = requests.get('https://bibmath.net/ressources/index.php', headers=headers, params=params)
+    response = requests.get(page, headers=headers)
     if response.status_code == 200:
         soup = BeautifulSoup(response.text, 'lxml')
         article = soup.find('article', id='contenugauche')
@@ -175,20 +193,16 @@ def fetch_chapitre(quoi):
 
                     stars_count = len(exo_title_div.find_all('img'))
 
-                    enonce = element.find('div', class_='enonce').find('div', class_='inner').get_text(strip=True)
-                    if ".Existe-t" in enonce:
-                        print(element)
+                    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').get_text(strip=True) 
-                        if indication_div else "No 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').get_text(strip=True)
-                        if answer_div else "No answer"
-                    )
+                    answer = answer_div.find('div', class_='inner')
+                    answer = parse(answer)
 
                     exercise = Exercise(
                         number=exercise_number,
@@ -207,9 +221,17 @@ def fetch_chapitre(quoi):
     else:
         print(f"Request failed with status code: {response.status_code}")
 
-quoi = 'mpsi/feuillesexo/matrices'
-chapitre = fetch_chapitre(quoi)
+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")
 
-latex_file = LatexFile('file.tex')
-latex_file.generate_latex(chapitre)
-print("LaTeX file generated: file.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)