def __get_post_info(self, fpt_post):
try:
post_title = scraper_lib.Element(block=fpt_post,
el_tag="h5",
el_class="titleFilm",
get_text=True).get_element()
except:
post_title = scraper_lib.Element(block=fpt_post,
el_tag="h2",
el_class="titleFilm",
get_text=True).get_element()
post_ref_url = scraper_lib.Element(block=fpt_post,
el_tag="a",
el_property="href").get_element()
try:
image = scraper_lib.Element(
block=fpt_post,
el_tag="img",
el_class="attachment-loc-film size-loc-film wp-post-image",
el_property="src").get_element()
except:
image = "n.d."
movie = Movie(title=post_title, page_url=post_ref_url)
movie.image_url = image
return movie
def get_search_result(self, keyword):
movies_list = []
raw_keyword = keyword
keyword = raw_keyword.replace(" ", "+")
search_result = scraper_lib.get_page_soup(url=self.search_url.format(
self.domain, keyword),
check_result=True)
if (search_result == -1):
result_url = self.get_movie_url_from_google(keyword)
search_result = scraper_lib.get_page_soup(url=result_url)
movies = scraper_lib.Container(
block=search_result,
tag='div',
container_class='col-lg-3 col-md-4 col-xs-4 mb-30').get_container(
)
for movie in movies:
movies_list.append(self.__get_post_info(movie))
if (not movies_list):
try:
title = scraper_lib.Element(block=search_result,
el_tag='title',
get_text=True).get_element()
except:
title = raw_keyword
movie = Movie(title=title, page_url=result_url)
movie.image_url = "n.d."
movies_list.append(movie)
return movies_list
def _get_movie_result(self, tmdb_url):
result = requests.get(tmdb_url).json()
movies = []
for x in result["results"]:
movie = Movie(title=x["title"])
movie.overview = x["overview"]
movie.release_date = x.get("release_date", '-').split('-')[0]
movie.image_url = x["poster_path"]
movies.append(movie)
return movies
def get_post_info(self, fpt_post, media_type):
post_title = scraper_lib.Element(block=fpt_post, el_tag="div",
el_class="title", get_text=True).get_element()
post_ref_url = scraper_lib.Element(block=fpt_post, el_tag="a",
el_property="href").get_element()
image = scraper_lib.Element(block=fpt_post, el_tag="a",
el_property="data-thumbnail").get_element()
if media_type == "movie":
movie = Movie(title=post_title, page_url=post_ref_url)
movie.image_url = image
return movie
else:
tvshow = TvShow(title=post_title, page_url=post_ref_url)
tvshow.image_url = image
return tvshow
def load_movies_from_json():
json_path = os.path.dirname(os.path.realpath(__file__))
json_fullname = json_path + "/example.json"
movies = []
with open(json_fullname) as json_file:
data = json.load(json_file)
for json_movie in data["movies"]:
movie = Movie(title=json_movie["title"], urls=json_movie["url"])
movies.append(movie)
return movies
def get_players(self, title, hdpass_iframe_url):
hdload = HDLoad(hdpass_iframe_url)
players = hdload.get_all_players()
return Movie(title=title, page_url=hdpass_iframe_url, urls=players)
def get_movie(self, title, fpt_movie_url):
self.soup = scraper_lib.get_page_soup(fpt_movie_url)
urls = self.__get_movies_url()
movie = Movie(title, urls)
return movie