wp.py

from playwright.sync_api import sync_playwright
import pandas as pd
import urllib.parse
import re
from dateutil import parser

KEYWORD = "brics"

query = f"{KEYWORD} site:washingtonpost.com after:2024-01-01 before:2026-12-31"

results = []

def extract_date(text):
    try:
        match = re.search(r'\w{3,9} \d{1,2}, \d{4}', text)
        if match:
            return parser.parse(match.group())
    except:
        return None

with sync_playwright() as p:
    browser = p.firefox.launch(headless=True)
    page = browser.new_page()

    url = f"https://www.google.com/search?q={urllib.parse.quote(query)}"
    page.goto(url)
    page.screenshot(path="debug.png")

    page.wait_for_timeout(5000)

    cards = page.query_selector_all("div.tF2Cxc")

    for c in cards:
        try:
            title = c.query_selector("h3").inner_text()
            link = c.query_selector("a").get_attribute("href")
            snippet_el = c.query_selector(".VwiC3b")

            snippet = snippet_el.inner_text() if snippet_el else ""
            date = extract_date(snippet)

            results.append({
                "title": title,
                "url": link,
                "date": date,
                "snippet": snippet
            })
        except:
            continue

    browser.close()

df = pd.DataFrame(results)
df.to_excel("washingtonpost_brics.xlsx", index=False)

print("Найдено:", len(df))