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_iframe_page(self, seriehd_page):
hdpass_iframe = scraper_lib.Element(seriehd_page,
'iframe',
el_id='iframeVid').get_element()
return scraper_lib.get_page_soup(url=hdpass_iframe["src"])
def get_episodes(self, episodes_url):
episodes = []
page = scraper_lib.get_page_soup(url=episodes_url)
episodes_container = scraper_lib.Container(
page,
tag="div",
first=True,
container_class="buttons-bar episodes").get_container()
episode_soup = scraper_lib.get_soup_prettified(episodes_container)
episodes_block = scraper_lib.Container(episode_soup,
tag="li").get_container()
for episode in episodes_block:
episode_no = scraper_lib.get_text(episode).strip()
episodes.append(
Episode(title="Episodio {0}".format(episode_no),
episode_no=episode_no,
urls=scraper_lib.get_hrefs(episode)[0]))
return episodes
def get_seasons(self, tvshow_page_url):
seasons = []
page = scraper_lib.get_page_soup(url=tvshow_page_url)
iframe = self.__get_iframe_page(page)
seasons_container = scraper_lib.Container(
iframe,
tag="div",
first=True,
container_class="buttons-bar seasons").get_container()
season_soup = scraper_lib.get_soup_prettified(seasons_container)
seasons_block = scraper_lib.Container(season_soup,
tag="li").get_container()
for season in seasons_block:
season_no = scraper_lib.get_text(season).strip()
seasons.append(
Season(title="Stagione {0}".format(
scraper_lib.get_text(season).strip()),
season_no=season_no,
ref_url=scraper_lib.get_hrefs(season)[0]))
return seasons
def get_hdload_frame(self, title, movie_url):
altadefinizione_page = scraper_lib.get_page_soup(movie_url)
hdpass_iframe = scraper_lib.Element(altadefinizione_page,
'iframe',
el_id='iframeVid').get_element()
hdpass_iframe_url = hdpass_iframe["src"]
return hdpass_iframe_url
def get_search_result(self, keyword):
keyword = keyword.replace(" ", "+")
self.cf_session = scraper_lib.get_cf_session()
search_result = scraper_lib.get_page_soup(url=self.search_url.format(
self.domain, keyword),
scraper=self.cf_session)
tvshow = scraper_lib.Container(
block=search_result,
tag='div',
first=True,
container_class='col-xs-6 col-sm-2-5').get_container()
info = self.__get_post_info(tvshow)
time.sleep(1)
return self.get_seasons(
scraper_lib.get_page_soup(info["url"], scraper=self.cf_session))
def get_first_result(search_string, destination_url):
soup = scraper_lib.get_page_soup(
url=__get_request_url(search_string, destination_url))
first_result = soup.find('div', class_='r')
if (first_result):
first_anchor = first_result.find('a')
if first_anchor:
return first_anchor["href"]
return None
def get_filmpertutti_domain(self):
try:
soup = scraper_lib.get_page_soup(self.url_check_domain, timeout=5)
wrapper = scraper_lib.Container(block=soup, tag='div', first=True,
container_class="content").get_container()
domain_url = scraper_lib.get_hrefs(wrapper, ["filmpertutti."])[0]
return domain_url
except:
return self.default_domain
def get_all_players(self):
self.hdpass_page = scraper_lib.get_page_soup(self.current_url)
hosts = scraper_lib.Container(self.hdpass_page,
'div',
container_class='hosts-bar',
first=True).get_container()
players = scraper_lib.Container(hosts, 'li').get_container()
return [scraper_lib.get_text(player) for player in players]
def get_seasons(self, page_url):
seasons_page = []
page = scraper_lib.get_page_soup(page_url)
seasons = scraper_lib.Container(
page, tag="div",
container_class="su-spoiler-title").get_container()
for i, season in enumerate(seasons, start=1):
seasons_page.append(
Season(title="stagione: {0}".format(i), season_no=i))
return seasons_page
def get_results(search_string, destination_url):
soup = scraper_lib.get_page_soup(
url=__get_request_url(search_string, destination_url))
results = []
for g in soup.find_all('div', class_='r'):
anchors = g.find_all('a')
if anchors:
link = anchors[0]['href']
title = g.find('h3').text
item = {"title": title, "link": link}
results.append(item)
return results
def get_embed_values_by_player(self, player_name):
href = None
if self.hdpass_page is None:
self.hdpass_page = scraper_lib.get_page_soup(self.current_url)
hosts = scraper_lib.Container(self.hdpass_page,
'div',
container_class='hosts-bar',
first=True).get_container()
players = scraper_lib.Container(hosts, 'li').get_container()
for player in players:
if player_name == scraper_lib.get_text(player):
a_href = scraper_lib.get_tag(player, 'a')
href = a_href["href"].replace("amp;", "")
break
if href is not None:
r = scraper_lib.get_page_soup(url=href)
return scraper_lib.Element(r, 'iframe',
el_property="custom-src").get_element()
return None
def get_search_result(self, keyword):
results = []
search_result = scraper_lib.get_page_soup(
url=self.search_url.format(self.domain, keyword))
tvshows = scraper_lib.Container(
block=search_result,
tag='div',
container_class='col-xl-3 col-lg-3 col-md-3 col-sm-6 col-6'
).get_container()
for tvshow in tvshows:
results.append(self.__get_post_info(tvshow))
return results
def get_fpt_posts(self, keyword, media_type):
try:
posts_list = []
key_search = keyword.replace(" ", "+")
url_search = self.filmpertutti_url.format(self.domain, key_search)
soup = scraper_lib.get_page_soup(url_search)
container = scraper_lib.Container(block=soup, tag='ul',
first=True, container_class="posts").get_container()
posts = scraper_lib.Container(block=container, tag='li').get_container()
for post in posts:
posts_list.append(self.get_post_info(post, media_type))
return posts_list
except:
return None
def get_search_result(self, keyword):
tvshow_lst = []
keyword = keyword.replace(" ", "+")
search_result = scraper_lib.get_page_soup(
url=self.search_url.format(self.domain, keyword))
div_posts = scraper_lib.Container(block=search_result,
tag='ul',
container_class='recent-posts',
first=True).get_container()
tvshows = scraper_lib.Container(block=div_posts,
tag='li').get_container()
for tvshow in tvshows:
try:
tvshow_lst.append(self.__get_post_info(tvshow))
except:
pass
return tvshow_lst
def play(title, streaming_url):
streaming_source_name = kodiutilsitem.get_streaming_source_name(
streaming_url)
if streaming_source_name == "speedvideo":
playable_url = speedvideo.get_stream_url(streaming_url)
if streaming_url != '' and streaming_url != '404':
kodiplayer.play_video(playable_url)
else:
kodiplayer.play_video_with_resolver(streaming_url)
elif streaming_source_name == "vcrypt":
page = scraper_lib.get_page_soup(url=streaming_url)
mixdrop_url = scraper_lib.Element(
page,
'iframe',
).get_element()["src"]
mixdrop_obj = Mixdrop(mixdrop_url)
kodiplayer.play_video(mixdrop_obj.get_final_url())
else:
kodiplayer.play_video_with_resolver(streaming_url)
def get_episodes(self, page_url, season_no=1):
episodes_lst = []
block = scraper_lib.get_page_soup(page_url)
episodes_container = scraper_lib.Container(
block, tag="div",
container_class="su-spoiler-content").get_container()[season_no -
1]
episodes_block = scraper_lib.Container(
episodes_container, tag="div",
container_class="su-link-ep").get_container()
for i, episode in enumerate(episodes_block, start=1):
urls = []
ep_title = scraper_lib.get_text(episode).replace('\n', '').strip()
urls.append(
scraper_lib.Element(episode, el_tag="a",
el_property="href").get_element())
episodes_lst.append(
Episode(title=ep_title, urls=urls, episode_no=i))
return episodes_lst
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
def scrape(self, fpt_tvshow_url):
self.soup = scraper_lib.get_page_soup(fpt_tvshow_url)
self.seasons_wrapper = self.get_seasons_wrapper()
