Python 爬蟲入門：用 requests 抓取網頁資料

import requests

response = requests.get('https://www.example.com')
print(response.status_code)  # 200 = 成功
print(response.text)          # 網頁原始碼

from bs4 import BeautifulSoup

soup = BeautifulSoup(response.text, 'html.parser')

# 找到所有 h2 標題
titles = soup.find_all('h2')
for t in titles:
    print(t.text.strip())

# 用 CSS 選擇器
items = soup.select('.product-name')

import requests
from bs4 import BeautifulSoup

url = 'https://www.ptt.cc/bbs/Python/index.html'
headers = {'cookie': 'over18=1'}

res = requests.get(url, headers=headers)
soup = BeautifulSoup(res.text, 'html.parser')

posts = soup.select('.r-ent .title a')
for post in posts:
    print(post.text.strip(), '→', post['href'])