| 4 | |
| 5 | |
| 6 | def main(): |
| 7 | html = """ |
| 8 | <!DOCTYPE html> |
| 9 | <html lang="en"> |
| 10 | <head> |
| 11 | <meta charset="UTF-8"> |
| 12 | <title>首页</title> |
| 13 | </head> |
| 14 | <body> |
| 15 | <h1>Hello, world!</h1> |
| 16 | <p>这是一个<em>神奇</em>的网站！</p> |
| 17 | <hr> |
| 18 | <div> |
| 19 | <h2>这是一个例子程序</h2> |
| 20 | <p>静夜思</p> |
| 21 | <p class="foo">床前明月光</p> |
| 22 | <p id="bar">疑似地上霜</p> |
| 23 | <p class="foo">举头望明月</p> |
| 24 | <div><a href="http://www.baidu.com"><p>低头思故乡</p></a></div> |
| 25 | </div> |
| 26 | <a class="foo" href="http://www.qq.com">腾讯网</a> |
| 27 | <img src="./img/pretty-girl.png" alt="美女"> |
| 28 | <img src="./img/hellokitty.png" alt="凯蒂猫"> |
| 29 | <img src="/static/img/pretty-girl.png" alt="美女"> |
| 30 | <table> |
| 31 | <tr> |
| 32 | <th>姓名</th> |
| 33 | <th>上场时间</th> |
| 34 | <th>得分</th> |
| 35 | <th>篮板</th> |
| 36 | <th>助攻</th> |
| 37 | </tr> |
| 38 | </table> |
| 39 | </body> |
| 40 | </html> |
| 41 | """ |
| 42 | soup = BeautifulSoup(html, 'lxml') |
| 43 | # JavaScript - document.title |
| 44 | print(soup.title) |
| 45 | # JavaScript - document.body.h1 |
| 46 | print(soup.body.h1) |
| 47 | print(soup.p) |
| 48 | print(soup.body.p.text) |
| 49 | print(soup.body.p.contents) |
| 50 | for p_child in soup.body.p.children: |
| 51 | print(p_child) |
| 52 | print(len([elem for elem in soup.body.children])) |
| 53 | print(len([elem for elem in soup.body.descendants])) |
| 54 | print(soup.findAll(re.compile(r'^h[1-6]'))) |
| 55 | print(soup.body.find_all(r'^h')) |
| 56 | print(soup.body.div.find_all(re.compile(r'^h'))) |
| 57 | print(soup.find_all(re.compile(r'r$'))) |
| 58 | print(soup.find_all('img', {'src': re.compile(r'\./img/\w+.png')})) |
| 59 | print(soup.find_all(lambda x: len(x.attrs) == 2)) |
| 60 | print(soup.find_all(foo)) |
| 61 | print(soup.find_all('p', {'class': 'foo'})) |
| 62 | for elem in soup.select('a[href]'): |
| 63 | print(elem.attrs['href']) |