import requests
from bs4 import BeautifulSoup
import json
def scrape_forum(url):
res = requests.get(url)
soup = BeautifulSoup(res.text, "html.parser")
postlefts = soup.find_all("div", class_="postleft")
postmsgs = soup.find_all("div", class_="postmsg")
results = []
mois_map = {
"janvier": "01",
"février": "02",
"mars": "03",
"avril": "04",
"mai": "05",
"juin": "06",
"juillet": "07",
"août": "08",
"septembre": "09",
"octobre": "10",
"novembre": "11",
"décembre": "12"
}
for left, msg in zip(postlefts, postmsgs):
auteur_tag = left.find("strong")
auteur = auteur_tag.get_text(strip=True) if auteur_tag else "Inconnu"
dt_tags = left.find_all("dt")
date_str = dt_tags[-1].get_text(strip=True) if dt_tags else "Date inconnue"
try:
parts = date_str.split()
jour = parts[0]
mois = mois_map.get(parts[1].lower(), "01")
annee = parts[2]
date_iso = f"{annee}-{mois}-{jour.zfill(2)}"
except:
date_iso = ""
texte = msg.get_text(separator="\n", strip=True)
results.append({
"author": auteur,
"date": date_str,
"date_iso": date_iso,
"content": texte,
"tags": ["alcool","nalméfène","nalmefene"]
})
return results
def append_to_html(posts, output_file="scrappharma.html", source_url=""):
try:
with open(output_file, "r", encoding="utf-8") as f:
soup = BeautifulSoup(f.read(), "html.parser")
except FileNotFoundError:
soup = BeautifulSoup("""
Scrap Pharma
Archive des posts
""", "html.parser")
container = soup.find("div", id="posts-container")
if container is None:
container = soup.new_tag("div", id="posts-container")
soup.body.append(container)
for post in posts:
post_div = soup.new_tag("div", **{"class": "post"})
author = soup.new_tag("div", **{"class": "pseudo"})
author.string = f" {post['author']}"
date = soup.new_tag("div", **{"class": "date"})
date.string = f" {post['date']}"
content = soup.new_tag("pre")
content.string = post["content"]
post_div.append(author)
post_div.append(date)
post_div.append(content)
container.append(post_div)
with open(output_file, "w", encoding="utf-8") as f:
f.write(soup.prettify())
def export_to_json(posts, output_file="scrappharma.json"):
try:
with open(output_file, "r", encoding="utf-8") as f:
existing_posts = json.load(f)
except (FileNotFoundError, json.JSONDecodeError):
existing_posts = []
all_posts = existing_posts + posts
with open(output_file, "w", encoding="utf-8") as f:
json.dump(all_posts, f, ensure_ascii=False, indent=4)
if __name__ == "__main__":
url = "https://www.psychoactif.org/forum/t16038-p1-Selincro-avez-vous-reussi-baisser-vos-consommations-alcool.html"
posts = scrape_forum(url)
append_to_html(posts, source_url=url)
export_to_json(posts)
print(f"{len(posts)} posts ajoutés dans scrappharma.html et scrappharma.json")