# ---------------------------------------------------------------------- # 1️⃣ CONFIGURATION # ---------------------------------------------------------------------- TITLE = "Manual de psihologie clasa a X-a" PUBLISHER_URL = "https://www.editura-aramis.ro/search?q={}" WORLD_CAT_URL = "https://www.worldcat.org/search?q={}" GOOGLE_SEARCH = "https://www.google.com/search?q={}" HEADERS = "User-Agent": ( "Mozilla/5.0 (Windows NT 10.0; Win64; x64) " "AppleWebKit/537.36 (KHTML, like Gecko) " "Chrome/124.0 Safari/537.36" )
def google_safe_search(): """Google limited to trusted domains; we only scrape the first page.""" query = urllib.parse.quote_plus( f'"TITLE" filetype:pdf site:.edu OR site:.gov OR site:.org' ) url = GOOGLE_SEARCH.format(query) r = safe_get(url) if not r: return None manual de psihologie clasa a x a editura aramis pdf
def safe_get(url): """Simple wrapper that retries once on failure.""" try: r = requests.get(url, headers=HEADERS, timeout=12) r.raise_for_status() return r except Exception as e: print(f"⚠️ Request failed (url): e", file=sys.stderr) return None x64) " "AppleWebKit/537.36 (KHTML
def main(): print(f"🔎 Searching legal sources for: TITLE\n") steps = [ ("Publisher (official)", check_publisher), ("WorldCat / library loan", check_worldcat), ("Google – trusted domains", google_safe_search), ("Commercial retailers", check_commercial), ] ("WorldCat / library loan"
import requests from bs4 import BeautifulSoup import urllib.parse import json import sys import time
def check_publisher(): """Look for an official e‑book / PDF on Editura Aramis.""" query = urllib.parse.quote_plus(TITLE) url = PUBLISHER_URL.format(query) r = safe_get(url) if not r: return None