58 lines
2.5 KiB
Python
58 lines
2.5 KiB
Python
from playwright.sync_api import sync_playwright
|
||
import json, time, re
|
||
|
||
def run():
|
||
with sync_playwright() as p:
|
||
try:
|
||
browser = p.chromium.connect_over_cdp('http://127.0.0.1:9222')
|
||
page = browser.contexts[0].pages[0]
|
||
|
||
# 1. Идем в список
|
||
page.goto('https://my.dom.gosuslugi.ru/citizen-cabinet/#!/appeals/applicant/search')
|
||
page.wait_for_load_state('networkidle')
|
||
time.sleep(10)
|
||
|
||
# 2. Пытаемся выставить 'По 100'
|
||
try:
|
||
# Ищем селект пагинации
|
||
page.locator('select.page-size-selector, .ui-select-container').click()
|
||
time.sleep(2)
|
||
page.get_by_text('100').click()
|
||
time.sleep(10)
|
||
except:
|
||
print('Не удалось выставить "по 100", будем собирать что есть.')
|
||
|
||
full_queue = []
|
||
|
||
# 3. Собираем со всех страниц (если их несколько)
|
||
while True:
|
||
rows = page.locator('tr').all()
|
||
for row in rows:
|
||
text = row.inner_text()
|
||
if '73-20' in text:
|
||
link = row.locator('a[href*="appeals/view/"]').first
|
||
num_match = re.search(r'73-202\d-\d+', text)
|
||
num = num_match.group(0) if num_match else "unknown"
|
||
href = link.get_attribute('href')
|
||
if href and num not in [x['number'] for x in full_queue]:
|
||
full_queue.append({'number': num, 'href': href})
|
||
|
||
# Ищем кнопку Следующая
|
||
next_btn = page.locator('a:has-text("следующая")')
|
||
if next_btn.is_visible() and next_btn.is_enabled():
|
||
print(f'Переход на следующую страницу... Уже собрано: {len(full_queue)}')
|
||
next_btn.click()
|
||
time.sleep(10)
|
||
else:
|
||
break
|
||
|
||
with open('/app/services/gis_harvester/data/full_queue.json', 'w', encoding='utf-8') as f:
|
||
json.dump(full_queue, f, ensure_ascii=False, indent=2)
|
||
|
||
print(f'ИТОГО СОБРАНО: {len(full_queue)} целей.')
|
||
browser.close()
|
||
except Exception as e:
|
||
print(f'ERROR: {e}')
|
||
|
||
if __name__ == "__main__":
|
||
run()
|