def scrape_movies(self, max=1):
content = dict(new=list(), top=list(), popular=list(), old=list())
for categorie in content.keys():
for id in range(1, max + 1):
soup = Utils.page_downloader(
f'{self.link}{categorie}?page={id}')
con = soup.find(class_='movies movies_small')
content[categorie].extend([
Utils.pickup_class(movie['href'])
for movie in con.find_all(class_='movie')
])
return content
def filter(cls, material: str, options: list, max: int = 5) -> list:
""" filter movies based on options
options supported values:
filter : latest, top, popular
year : year if under 2000 add 's' example -> 2012, 1950s
bad usage -> 2012s, 1951
language: language example -> arabic, english
country : iso code of the country example -> us, ma
type: type -> example -> action, documentary
content rating : example -> [PG-13] +13 , unrated,
quality: example -> bluray, hdrip
precision : example -> 1080p, 720p
example of filtering - > Site.filter('tv', ['top', 'us', '1080p'])
1) order doesn't matter
2) pass options as a list
3) options are optinal you don't have to pass all of them
"""
material = material.lower()
if material not in cls.supported:
print(f'Supported filters are {", ".join(cls.supported)}')
return None
text = ''
for page in range(1, max + 1):
query = cls.filter_api.format(material=material,
options='-'.join(options),
page=page)
r = requests.get(query).json()
text += r['html']
soup = BeautifulSoup(text, 'lxml')
return [
Utils.pickup_class(link['href'],
title=link.find(class_='title').text)
for link in soup.find_all(class_='movie')
]
def test_path(self):
page = '{}{}'.format(self.elem['domain'], self.elem['test_path'])
if 'vidstream' in self.elem['domain']:
return page
link = Utils.page_downloader(page).find(
class_='nop btn g dl _open_window')['data-url']
return f'{self.elem["domain"]}{link}'
def get_mp4_link(self, item=None):
link = f'{self.api.rstrip("/")}{self.items[item]["download"]}'
vid_link = reeeeeee.get(link,
headers=parameters.headers,
cookies=self.egy_token).url
page = Utils.page_downloader(vid_link, cookies=self.vid_stream)
return page.find(class_='bigbutton').attrs['href']
def shows_container_scrape(self, item):
t = item.find(class_='contents movies_small')
return [
Utils.pickup_class(link=item['href'],
title=item.find(class_='title').text,
thumbnail=item.img['src'])
for item in t.find_all('a')
]
def __init__(self, link, **kwargs):
self.link = link
self.page_type = Utils.page_type(link)
self.access = Settings().auto_init
if not self.access:
if 'title' in kwargs:
self.title, self.year = Utils.title_parser(kwargs['title'])
if self.year is None:
year_url = Utils.url_to_name(link)[1]
self.year = year_url if year_url.isnumeric() else None
else:
self.title, self.year = Utils.url_to_name(link)
for name, value in kwargs.items():
if name != 'title':
setattr(self, name, value)
def get_seasons(self):
""" return all seasons of a serie """
container = self.soup.find(class_='contents movies_small')
return [Utils.pickup_class(
link=link['href'],
title=link.find(class_='title').text,
thumbnail=link.img['src']
)
for link in container.find_all('a')]
def get_similar(self):
"""get similar movies."""
container = self.soup.find(class_='contents movies_small')
return [Utils.pickup_class(
link['href'],
title=link.find(class_='title').text
)
for link in container.find_all('a')]
def get_episodes(self):
""" get all episodes of a Season """
container = self.soup.find(class_='movies_small')
return [
Utils.pickup_class(
link['href'],
title=link.find(class_='title').text,
thumbnail=link.img['src'],
) for link in container.find_all('a')
]
def get_actors(self):
""" get actors and thire info from a material page """
container = self.soup.find(class_='rs_scroll pdt pdr')
content = list()
for actor in container.find_all(class_='cast_item'):
name = actor.find_all(class_='td vam')[1].a.text
content.append(
Actor(actor.find_all(class_='td vam')[1].a['href'],
role=Utils.fix_actor_role(
name,
actor.find_all(class_='td vam')[1].span.text),
_name=name,
_image=actor.find_all(class_='td vam')[0].img['src']))
return content
def search(cls, query: str, access=True, **kwargs) -> list or None:
""" a class to search inside the site : movies, series ...
return instance of class's that blong the the type of result
"""
tamplate = '%s/{}' % cls.my_site
pram = (('q', query), )
r = requests.get(cls.search_api, params=pram, **kwargs).json()
if r:
return [
Utils.pickup_class(
link=tamplate.format(movie['u']),
title=movie['t'],
) for elem in r for movie in r[elem]
]
return None
def soup(self):
return Utils.page_downloader(self.link)
def name(self):
if Settings().auto_init:
return self.scrape_image()['name']
return ' '.join(Utils.url_to_name(self.link)).title()
def soup(self):
if not hasattr(self, '_soup'):
self._soup = Utils.page_downloader(self.link).find(id='mainLoad')
return self._soup
def __init__(self):
self.link = Utils.make_link()
for name, value in self.scrape_home_page().items():
setattr(self, name, value)