Web Scraping Bằng Python: Thu Thập Dữ Liệu Từ Website Với BeautifulSoup Và Requests

pip install requests beautifulsoup4 pandas

import requests
from bs4 import BeautifulSoup

url = "https://vnexpress.net"
response = requests.get(url)
soup = BeautifulSoup(response.text, "html.parser")

# Lấy tất cả tiêu đề bài viết
headlines = soup.find_all("h3", class_="title-news")

for h in headlines[:10]:
    link = h.find("a")
    if link:
        print(f"📰 {link.text.strip()}")
        print(f"   🔗 {link['href']}\n")

import pandas as pd

# Pandas có thể đọc trực tiếp bảng HTML!
url = "https://en.wikipedia.org/wiki/List_of_countries_by_GDP_(nominal)"
tables = pd.read_html(url)

# Lấy bảng đầu tiên
df = tables[0]
print(df.head(10))

import requests
from bs4 import BeautifulSoup
import pandas as pd

def scrape_products(url):
    response = requests.get(url, headers={
        "User-Agent": "Mozilla/5.0"
    })
    soup = BeautifulSoup(response.text, "html.parser")
    
    products = []
    for item in soup.find_all("div", class_="product-item"):
        name = item.find("h2").text.strip()
        price = item.find("span", class_="price").text.strip()
        products.append({"name": name, "price": price})
    
    return pd.DataFrame(products)

df = scrape_products("https://example.com/products")
df.to_csv("products.csv", index=False)
print(f"Đã lưu {len(df)} sản phẩm!")

import time

all_data = []
for page in range(1, 11):  # 10 trang
    url = f"https://example.com/products?page={page}"
    response = requests.get(url)
    soup = BeautifulSoup(response.text, "html.parser")
    
    # Parse data...
    items = soup.find_all("div", class_="item")
    all_data.extend(items)
    
    print(f"Trang {page}: {len(items)} items")
    time.sleep(1)  # Đợi 1s giữa các request (lịch sự!)