使用lxml来爬取某地区豆瓣正在上映的电影

具体代码如下

# print(etree.tostring(html,encoding="utf-8").decode("utf-8"))
lis = ul.xpath("./li[@class='list-item']")
movies =  []
for li in lis:
    # print(etree.tostring(li,encoding="utf-8").decode("utf-8"))
    date_title = li.xpath("@data-title")[0]
    date_score = li.xpath("@data-score")
    data_release = li.xpath("@data-release")[0]
    data_duration = li.xpath("@data-duration")[0]
    data_region = li.xpath("@data-region")[0]
    data_director = li.xpath("@data-director")[0]
    data_actors = li.xpath("@data-actors")[0]
    img = li.xpath("//img/@src")[0]
    movie = {
        "date_title":date_title,
        "date_score":date_score,
        "data_release":data_release,
        "data_region":data_region,
        "data_director":data_director,
        "data_actors":data_actors,
        "img":img
    }
    movies.append(movie)

print(movies)