test / development_logs /legacy_src /bs_02_open_china_page.py
Kirtan001's picture
Fresh Start: Clean Repo without binaries
ad06665
import sqlite3
import requests
from bs4 import BeautifulSoup
# -----------------------------
# 1️⃣ Get China URL from DB
# -----------------------------
conn = sqlite3.connect("data/satellites.db")
cursor = conn.cursor()
china_row = cursor.execute("""
SELECT country_url
FROM countries
WHERE country='China'
""").fetchone()
conn.close()
china_url = china_row[0]
print("China page URL:", china_url)
# -----------------------------
# 2️⃣ Request China page
# -----------------------------
response = requests.get(china_url)
soup = BeautifulSoup(response.text, "lxml")
# -----------------------------
# 3️⃣ Verify page content
# -----------------------------
title = soup.find("title").text
print("\nPage title:", title)
print("\nPage preview:")
print(soup.get_text()[:500])