# ---------------------------------------------------------------------- # 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 check_commercial(): """Look for a paid e‑book version on major Romanian retailers.""" retailers = "eMAG": f"https://www.emag.ro/search/urllib.parse.quote_plus(TITLE)", "Carturesti": f"https://www.carte-romanesti.ro/cautare?search=urllib.parse.quote_plus(TITLE)", results = [] for name, url in retailers.items(): r = safe_get(url) if not r: continue if "pdf" in r.text.lower() or "ebook" in r.text.lower(): results.append("source": name, "link": url, "type": "purchase") return results if results else None
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
found_any = True # `res` may be a list (retailers) or a dict (single result) if isinstance(res, list): for r in res: print(f" ✅ r['source']: r['link'] [r['type']]") else: print(f" ✅ res['source']: res['link'] [res['type']]") print()
# ---------------------------------------------------------------------- x64) " "AppleWebKit/537.36 (KHTML
found_any = False for label, func in steps: print(f"⏳ label…") res = func() time.sleep(0.7) # polite delay for the next request if not res: print(" ❌ No legal PDF found in this step.\n") continue
import requests from bs4 import BeautifulSoup import urllib.parse import json import sys import time results = [] for name
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