movies.append(movie)
for movie in movies:
driver.get(movie.link)
print('Processing ', movie.title)
movie.synopsis = driver.find_element_by_css_selector('div#sinopsis').text
datos = driver.find_element_by_css_selector(
'div#tecnicos > p').get_attribute('innerHTML')
for dato in datos.split('<br>'):
if 'Género' in dato:
movie.genre = dato.split(': ')[1]
if 'Director' in dato:
movie.director = dato.split(': ')[1]
if 'Actores' in dato:
movie.cast = dato.split(': ')[1].split(',')
if 'Duración' in dato:
movie.duration = dato.split(': ')[1]
rooms = driver.find_elements_by_css_selector('.accordion > div.card.panel')
for r in rooms:
room = r.find_element_by_css_selector('h2.panel-title')
types = r.find_elements_by_css_selector(
'.movie-showtimes-component-combination')
for t in types:
type_data = list(
map(
lambda x: x.strip(),
t.find_element_by_css_selector(
'.movie-showtimes-component-label small').
get_attribute('innerHTML').split('•')))
subtitled = 'Subtitulado' in type_data[2]
room_with_type = room.text + ' ' + \
type_data[0] + ' ' + type_data[1]
movies = []
for tag in tags:
# print("=========================")
# print(tag)
# soup.select('li[data-actors]')
# print(tag.li)
movie = Movie()
# 主演
movie.actors = tag.attrs['data-actors']
# 导演
movie.director = tag.attrs['data-director']
# 时长
movie.duration = tag.attrs['data-duration']
# 豆瓣评分
movie.rate = tag.attrs["data-rate"]
# 发布地区
movie.region = tag.attrs["data-region"]
# 发布时间
movie.release = tag.attrs["data-release"]
# 电影名称
movie.title = tag.attrs["data-title"]
# 相关视频地址
movie.trailer = tag.attrs["data-trailer"]
# 电影封面
movie.cover = tag.img.attrs["src"]
# 豆瓣地址
movie.threadUrl = tag.a.attrs["href"]