import requests, re, json, time
HDRS={"User-Agent":"Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 Chrome/126 Safari/537.36","HX-Request":"true"}
seen=set(); stale=0; page=1
while stale<3 and page<200:
    r=requests.get(f"https://alimentsduquebec.com/entreprises?page={page}",headers=HDRS,timeout=25)
    links=set(re.findall(r'href="(https://alimentsduquebec\.com/entreprises/[a-z0-9\-]+)"',r.text))
    new=links-seen
    if not new: stale+=1
    else: stale=0
    seen|=links
    if page%10==0: print(page,len(seen),flush=True)
    page+=1; time.sleep(0.15)
print("final pages:",page,"unique:",len(seen))
open("data/raw/adq_enterprise_urls.txt","w").write("\n".join(sorted(seen)))