damir
a428363d42
Endpoints: - /v2/potpore/meta — dropdown options (sportovi, vrste, davatelji, godine) - /v2/potpore/by-year — sport, vrsta filters - /v2/manifestacije/meta — mjesta, razine, organizatori - /v2/manifestacije — lista s filterima HNS: - 20 PGŽ priority klubova batch harvester pokrenut (HNK Goranin, HNK Orijent 1919, HNK Rijeka, NK Crikvenica, ...) - ETA 30 min
69 lines
2.8 KiB
Python
69 lines
2.8 KiB
Python
#!/usr/bin/env python3
|
|
"""Gov.hr deep — DZS PxWeb, sudreg portal, sukobinteresa."""
|
|
import sys, json, time
|
|
sys.path.insert(0, "/opt/pgz-sport/scrapers/harvesters")
|
|
from _common import (fetch, extract_text, extract_title, chunk_text,
|
|
upsert_facts, find_internal_links, DSN)
|
|
from urllib.parse import urlparse
|
|
import psycopg2
|
|
|
|
GOV = {
|
|
"dzs_kvarner": ["https://podaci.dzs.hr/hr/podaci/stanovnistvo/popis-stanovnistva/"],
|
|
"sukobinteresa_pgz": ["https://www.sukobinteresa.hr/"],
|
|
"drzavna_revizija": ["https://www.revizija.hr/"],
|
|
"drzavna_komisija_kn": ["https://www.dkom.hr/"],
|
|
"fina_pgz": ["https://www.fina.hr/poslovni-subjekti"],
|
|
"fina_javne_objave": ["https://www.fina.hr/javne-objave-uprave"],
|
|
"porezna_uprava_ri": ["https://www.porezna-uprava.hr/"],
|
|
"ministarstvo_pgz": ["https://www.gov.hr/hr/ministarstva"],
|
|
"vlada_hr_pgz": ["https://vlada.gov.hr/"],
|
|
"uprava_polic_pgz": ["https://policija.gov.hr/policijska-uprava-primorsko-goranska/"],
|
|
"vis_hr": ["https://www.vis-hr.com/"],
|
|
}
|
|
|
|
|
|
def crawl(name, urls, max_pages=10):
|
|
conn = psycopg2.connect(DSN); conn.autocommit = True
|
|
visited = set(); queue = list(urls); facts = 0
|
|
while queue and len(visited) < max_pages:
|
|
url = queue.pop(0)
|
|
if url in visited: continue
|
|
visited.add(url)
|
|
html, status = fetch(url, timeout=15)
|
|
if not html or status != 200: continue
|
|
title = extract_title(html); text = extract_text(html)
|
|
if not text or len(text) < 200: continue
|
|
ff = []
|
|
if title and len(title) > 8:
|
|
ff.append({"fact": f"{name} - {title}", "url": url, "title": title})
|
|
for c in chunk_text(text, 800):
|
|
if len(c) > 100:
|
|
ff.append({"fact": c, "url": url, "title": title})
|
|
facts += upsert_facts(conn, ff, source_name=name,
|
|
category="gov_registri_pgz", confidence=0.88)
|
|
base = urlparse(url).hostname
|
|
for link in find_internal_links(html, url):
|
|
if link not in visited and (urlparse(link).hostname or "") == base and len(queue) < 30:
|
|
queue.append(link)
|
|
time.sleep(0.5)
|
|
conn.close()
|
|
return {"name": name, "visited": len(visited), "facts": facts}
|
|
|
|
|
|
def main():
|
|
results = []
|
|
for name, urls in GOV.items():
|
|
try:
|
|
r = crawl(name, urls, max_pages=10)
|
|
print(f" {name:25} {r['visited']:>3}p {r['facts']:>5}f")
|
|
results.append(r)
|
|
except Exception as e:
|
|
print(f" {name:25} FAIL: {str(e)[:60]}")
|
|
total = sum(r.get("facts", 0) for r in results)
|
|
print(f"=== TOTAL: {total} ===")
|
|
print(json.dumps({"gov_count": len(results), "total_facts": total}))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|