:obj:`list` of :obj:`dict`
List of all the serialized data pulled out of the pagws <script/> tags
"""
- scripts = page_soup.find_all('script', attrs={'src': None});
+ scripts = page_soup.find_all('script', attrs={'src': None})
self.log(msg='Trying sloppy inline data parser')
inline_data = self._sloppy_parse_inline_data(scripts=scripts)
if self._verfify_auth_and_profiles_data(data=inline_data) != False:
for key in self.video_list_keys:
video_list_ids[key] = {}
+ # check if the list items are hidden behind a `value` sub key
+ # this is the case when we fetch the lists via POST, not via a GET preflight request
+ if 'value' in response_data.keys():
+ response_data = response_data['value']
+
# subcatogorize the lists by their context
video_lists = response_data['lists']
for video_list_id in video_lists.keys():
},
}
"""
+ mpaa = ''
+ if episode.get('maturity', None) is not None:
+ if episode['maturity'].get('board', None) is not None and episode['maturity'].get('value', None) is not None:
+ mpaa = str(episode['maturity'].get('board', '').encode('utf-8')) + '-' + str(episode['maturity'].get('value', '').encode('utf-8'))
+
return {
episode['summary']['id']: {
'id': episode['summary']['id'],
'title': episode['info']['title'],
'year': episode['info']['releaseYear'],
'genres': self.parse_genres_for_video(video=episode, genres=genres),
- 'mpaa': str(episode['maturity']['rating']['board']) + ' ' + str(episode['maturity']['rating']['value']),
+ 'mpaa': mpaa,
'maturity': episode['maturity'],
'playcount': (0, 1)[episode['watched']],
'rating': episode['userRating'].get('average', 0) if episode['userRating'].get('average', None) != None else episode['userRating'].get('predicted', 0),
response = self._session_get(component='browse')
return BeautifulSoup(response.text, 'html.parser')
- def fetch_video_list_ids (self, list_from=0, list_to=50):
+ def fetch_video_list_ids_via_preflight (self, list_from=0, list_to=50):
"""Fetches the JSON with detailed information based on the lists on the landing page (browse page) of Netflix
+ via the preflight (GET) request
Parameters
----------
response = self._session_get(component='video_list_ids', params=payload, type='api')
return self._process_response(response=response, component=self._get_api_url_for(component='video_list_ids'))
- def fetch_search_results (self, search_str, list_from=0, list_to=10):
- """Fetches the JSON which contains the results for the given search query
+ def fetch_video_list_ids (self, list_from=0, list_to=50):
+ """Fetches the JSON with detailed information based on the lists on the landing page (browse page) of Netflix
Parameters
----------
- search_str : :obj:`str`
- String to query Netflix search for
-
list_from : :obj:`int`
Start entry for pagination
:obj:`dict` of :obj:`dict` of :obj:`str`
Raw Netflix API call response or api call error
"""
- # properly encode the search string
- encoded_search_string = quote(search_str)
-
paths = [
- ['search', encoded_search_string, 'titles', {'from': list_from, 'to': list_to}, ['summary', 'title']],
- ['search', encoded_search_string, 'titles', {'from': list_from, 'to': list_to}, 'boxarts', '_342x192', 'jpg'],
- ['search', encoded_search_string, 'titles', ['id', 'length', 'name', 'trackIds', 'requestId']],
- ['search', encoded_search_string, 'suggestions', 0, 'relatedvideos', {'from': list_from, 'to': list_to}, ['summary', 'title']],
- ['search', encoded_search_string, 'suggestions', 0, 'relatedvideos', {'from': list_from, 'to': list_to}, 'boxarts', '_342x192', 'jpg'],
- ['search', encoded_search_string, 'suggestions', 0, 'relatedvideos', ['id', 'length', 'name', 'trackIds', 'requestId']]
+ ['lolomo', {'from': list_from, 'to': list_to}, ['displayName', 'context', 'id', 'index', 'length']]
]
- response = self._path_request(paths=paths)
- return self._process_response(response=response, component='Search results')
-
- def get_lolomo_for_kids (self):
- """Fetches the lolomo ID for Kids profiles
- Returns
- -------
- :obj:`str`
- Kids Lolomo ID
- """
- response = self._session_get(component='kids')
- for cookie in response.cookies:
- if cookie.name.find('lhpuuidh-browse-' + self.user_data['guid']) != -1 and cookie.name.rfind('-T') == -1:
- start = unquote(cookie.value).rfind(':')
- return unquote(cookie.value)[start+1:]
- return None
+ response = self._path_request(paths=paths)
+ return self._process_response(response=response, component='Video list ids')
- def fetch_lists_for_kids (self, lolomo, list_from=0, list_to=50):
- """Fetches the JSON which contains the contents of a the video list for kids users
+ def fetch_search_results (self, search_str, list_from=0, list_to=10):
+ """Fetches the JSON which contains the results for the given search query
Parameters
----------
- lolomo : :obj:`str`
- Lolomo ID for the Kids profile
+ search_str : :obj:`str`
+ String to query Netflix search for
list_from : :obj:`int`
Start entry for pagination
:obj:`dict` of :obj:`dict` of :obj:`str`
Raw Netflix API call response or api call error
"""
+ # properly encode the search string
+ encoded_search_string = quote(search_str)
+
paths = [
- ['lists', lolomo, {'from': list_from, 'to': list_to}, ['displayName', 'context', 'genreId', 'id', 'index', 'length']]
+ ['search', encoded_search_string, 'titles', {'from': list_from, 'to': list_to}, ['summary', 'title']],
+ ['search', encoded_search_string, 'titles', {'from': list_from, 'to': list_to}, 'boxarts', '_342x192', 'jpg'],
+ ['search', encoded_search_string, 'titles', ['id', 'length', 'name', 'trackIds', 'requestId']],
+ ['search', encoded_search_string, 'suggestions', 0, 'relatedvideos', {'from': list_from, 'to': list_to}, ['summary', 'title']],
+ ['search', encoded_search_string, 'suggestions', 0, 'relatedvideos', {'from': list_from, 'to': list_to}, 'boxarts', '_342x192', 'jpg'],
+ ['search', encoded_search_string, 'suggestions', 0, 'relatedvideos', ['id', 'length', 'name', 'trackIds', 'requestId']]
]
-
response = self._path_request(paths=paths)
- res = self._process_response(response=response, component='Kids lists')
- return self.parse_video_list_ids(response_data=res['value'])
+ return self._process_response(response=response, component='Search results')
- def fetch_video_list (self, list_id, list_from=0, list_to=20):
+ def fetch_video_list (self, list_id, list_from=0, list_to=26):
"""Fetches the JSON which contains the contents of a given video list
Parameters
User Agent for platform
"""
import platform
- if platform == 'linux' or platform == 'linux2':
- return 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
- elif platform == 'darwin':
+ self.log(msg='Building User Agent for platform: ' + str(platform.system()) + ' - ' + str(platform.machine()))
+ if platform.system() == 'Darwin':
return 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_10_1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
- elif platform == 'win32':
+ if platform.system() == 'Windows':
return 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
- else:
- return 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
+ if platform.machine().startswith('arm'):
+ return 'Mozilla/5.0 (X11; CrOS armv7l 7647.78.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.109 Safari/537.36'
+ return 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
def _session_post (self, component, type='document', data={}, headers={}, params={}):
"""Executes a get request using requests for the current session & measures the duration of that request
important_fields = [
'profileName',
'isActive',
- 'isFirstUse',
'isAccountOwner',
'isKids'
]
profile.update({important_field: netflix_page_data['profiles'][profile_id]['summary'][important_field]})
avatar_base = netflix_page_data['nf'].get(netflix_page_data['profiles'][profile_id]['summary']['avatarName'], False);
avatar = 'https://secure.netflix.com/ffe/profiles/avatars_v2/320x320/PICON_029.png' if avatar_base == False else avatar_base['images']['byWidth']['320']['value']
- profile.update({'avatar': avatar})
+ profile.update({'avatar': avatar, 'isFirstUse': False})
profiles.update({profile_id: profile})
return profiles