爬虫_豆瓣全部正在热映电影 （xpath）

单纯地练习一下xpath

import requests
from lxml import etree


def get_url(url):
    html = requests.get(url)
    return html.text


def parse_html(html):
    informations = []
    html_element = etree.HTML(html)
    ul = html_element.xpath('//ul[@class="lists"]')[0]
    for li in ul:
        href = li.xpath('.//li[@class="poster"]/a/@href')
        title = li.xpath('normalize-space(.//li[@class="stitle"]/a/@title)')  #normalize-space 去掉换行符
        mark = li.xpath('.//span[@class="subject-rate"]/text()')
        actor = li.xpath('@data-actors')
        director = li.xpath('@data-director')
    # print(etree.tostring(uls, encoding='utf-8').decode('utf-8'))
        information = {
            'href': href,
            'title': title,
            'mark': mark,
            'actors': actor,
            'director': director
        }
        informations.append(information)
    
    print(informations)


def main():
    url = 'https://movie.douban.com/cinema/nowplaying/beijing/'
    html = get_url(url)
    parse_html(html)


if __name__ == '__main__':
    main()