BeautifulSoup和lxml的基本用法示例

上一篇里面已经有一种方法了，现在再介绍两种

def get_input(html):
    data = {}
    soup = BeautifulSoup(html, 'html.parser')
    inputs = soup.form.findAll('input')
    for input in inputs:
        if input.get('name'):
            data[input.get('name')] = input.get('value')
    return data

from lxml import etree

def get_video_url(page_url):
    response = requests.get(page_url).text
    selector = etree.HTML(response.encode('utf-8'))
    x = selector.xpath('//*[@id="player"]/script/text()')
    return re.findall('src="(.*?)&', x[0])[0]