2 # -*- coding: utf-8 -*-
3 # Module: NetflixSession
4 # Created on: 13.01.2017
8 from requests import session, cookies
9 from urllib import quote, unquote
11 from base64 import urlsafe_b64encode
12 from bs4 import BeautifulSoup, SoupStrainer
13 from utils import noop
15 import cPickle as pickle
20 """Helps with login/session management of Netflix users & API data fetching"""
22 base_url = 'https://www.netflix.com'
23 """str: Secure Netflix url"""
27 'browse': '/profiles/manage',
28 'video_list_ids': '/preflight',
29 'shakti': '/pathEvaluator',
30 'profiles': '/profiles/manage',
31 'switch_profiles': '/profiles/switch',
32 'adult_pin': '/pin/service',
33 'metadata': '/metadata',
34 'set_video_rating': '/setVideoRating',
35 'update_my_list': '/playlistop',
38 """:obj:`dict` of :obj:`str` List of all static endpoints for HTML/JSON POST/GET requests"""
40 video_list_keys = ['user', 'genres', 'recommendations']
41 """:obj:`list` of :obj:`str` Divide the users video lists into 3 different categories (for easier digestion)"""
45 Dict of user profiles, user id is the key:
48 "profileName": "username",
49 "avatar": "http://..../avatar.png",
51 "isAccountOwner": False,
59 dict of user data (used for authentication):
63 "authURL": "145637....",
70 dict of api data (used to build up the api urls):
73 "API_BASE_URL": "/shakti",
74 "API_ROOT": "https://www.netflix.com/api",
75 "BUILD_IDENTIFIER": "113b89c9", "
76 ICHNAEA_ROOT": "/ichnaea"
81 """str: ESN - something like: NFCDCH-MC-D7D6F54LOPY8J416T72MQXX3RD20ME"""
83 def __init__(self, cookie_path, data_path, verify_ssl=True, log_fn=noop):
84 """Stores the cookie path for later use & instanciates a requests
85 session with a proper user agent & stored cookies/data if available
89 cookie_path : :obj:`str`
92 data_path : :obj:`str`
93 User data cache location
98 self.cookie_path = cookie_path
99 self.data_path = data_path
100 self.verify_ssl = verify_ssl
103 # start session, fake chrome on the current platform (so that we get a proper widevine esn) & enable gzip
104 self.session = session()
105 self.session.headers.update({
106 'User-Agent': self._get_user_agent_for_current_platform(),
107 'Accept-Encoding': 'gzip'
110 def parse_login_form_fields (self, form_soup):
111 """Fetches all the inputfields from the login form, so that we
112 can build a request with all the fields needed besides the known email & password ones
116 form_soup : :obj:`BeautifulSoup`
117 Instance of an BeautifulSoup documet or node containing the login form
121 :obj:`dict` of :obj:`str`
122 Dictionary of all input fields with their name as the key & the default
123 value from the form field
125 login_input_fields = {}
126 login_inputs = form_soup.find_all('input')
127 # gather all form fields, set an empty string as the default value
128 for item in login_inputs:
129 keys = dict(item.attrs).keys()
130 if 'name' in keys and 'value' not in keys:
131 login_input_fields[item['name']] = ''
132 elif 'name' in keys and 'value' in keys:
133 login_input_fields[item['name']] = item['value']
134 return login_input_fields
136 def extract_inline_netflix_page_data (self, page_soup):
137 """Extracts all <script/> tags from the given document and parses the contents of each one of `em.
138 The contents of the parsable tags looks something like this:
139 <script>window.netflix = window.netflix || {} ; netflix.notification = {"constants":{"sessionLength":30,"ownerToken":"ZDD...};</script>
140 We use a JS parser to generate an AST of the code given & then parse that AST into a python dict.
141 This should be okay, as we´re only interested in a few static values & put the rest aside
145 page_soup : :obj:`BeautifulSoup`
146 Instance of an BeautifulSoup document or node containing the complete page contents
149 :obj:`list` of :obj:`dict`
150 List of all the serialized data pulled out of the pagws <script/> tags
152 scripts = page_soup.find_all('script', attrs={'src': None});
153 self.log(msg='Trying sloppy inline data parser')
154 inline_data = self._sloppy_parse_inline_data(scripts=scripts)
155 if self._verfify_auth_and_profiles_data(data=inline_data) != False:
156 self.log(msg='Sloppy inline data parsing successfull')
158 self.log(msg='Sloppy inline parser failed, trying JS parser')
159 return self._accurate_parse_inline_data(scripts=scripts)
161 def is_logged_in (self, account):
162 """Determines if a user is already logged in (with a valid cookie),
163 by fetching the index page with the current cookie & checking for the
164 `membership status` user data
168 account : :obj:`dict` of :obj:`str`
169 Dict containing an email, country & a password property
174 User is already logged in (e.g. Cookie is valid) or not
178 account_hash = self._generate_account_hash(account=account)
179 if self._load_cookies(filename=self.cookie_path + '_' + account_hash) == False:
181 if self._load_data(filename=self.data_path + '_' + account_hash) == False:
182 # load the profiles page (to verify the user)
183 response = self._session_get(component='profiles')
185 # parse out the needed inline information
186 only_script_tags = SoupStrainer('script')
187 page_soup = BeautifulSoup(response.text, 'html.parser', parse_only=only_script_tags)
188 page_data = self._parse_page_contents(page_soup=page_soup)
190 # check if the cookie is still valid
191 for item in page_data:
192 if 'profilesList' in dict(item).keys():
193 if item['profilesList']['summary']['length'] >= 1:
199 """Delete all cookies and session data
203 account : :obj:`dict` of :obj:`str`
204 Dict containing an email, country & a password property
207 self._delete_cookies(path=self.cookie_path)
208 self._delete_data(path=self.data_path)
210 def login (self, account):
211 """Try to log in a user with its credentials & stores the cookies if the action is successfull
213 Note: It fetches the HTML of the login page to extract the fields of the login form,
214 again, this is dirty, but as the fields & their values could change at any time, this
215 should be the most reliable way of retrieving the information
219 account : :obj:`dict` of :obj:`str`
220 Dict containing an email, country & a password property
225 User could be logged in or not
227 response = self._session_get(component='login')
228 if response.status_code != 200:
231 # collect all the login fields & their contents and add the user credentials
232 page_soup = BeautifulSoup(response.text, 'html.parser')
233 login_form = page_soup.find(attrs={'class' : 'ui-label-text'}).findPrevious('form')
234 login_payload = self.parse_login_form_fields(form_soup=login_form)
235 if 'email' in login_payload:
236 login_payload['email'] = account['email']
237 if 'emailOrPhoneNumber' in login_payload:
238 login_payload['emailOrPhoneNumber'] = account['email']
239 login_payload['password'] = account['password']
242 login_response = self._session_post(component='login', data=login_payload)
243 login_soup = BeautifulSoup(login_response.text, 'html.parser')
245 # we know that the login was successfull if we find an HTML element with the class of 'profile-name'
246 if login_soup.find(attrs={'class' : 'profile-name'}) or login_soup.find(attrs={'class' : 'profile-icon'}):
247 # parse the needed inline information & store cookies for later requests
248 self._parse_page_contents(page_soup=login_soup)
249 account_hash = self._generate_account_hash(account=account)
250 self._save_cookies(filename=self.cookie_path + '_' + account_hash)
251 self._save_data(filename=self.data_path + '_' + account_hash)
256 def switch_profile (self, profile_id, account):
257 """Switch the user profile based on a given profile id
259 Note: All available profiles & their ids can be found in the ´profiles´ property after a successfull login
263 profile_id : :obj:`str`
266 account : :obj:`dict` of :obj:`str`
267 Dict containing an email, country & a password property
272 User could be switched or not
275 'switchProfileGuid': profile_id,
277 'authURL': self.user_data['authURL']
280 response = self._session_get(component='switch_profiles', type='api', params=payload)
281 if response.status_code != 200:
284 account_hash = self._generate_account_hash(account=account)
285 self.user_data['guid'] = profile_id;
286 return self._save_data(filename=self.data_path + '_' + account_hash)
288 def send_adult_pin (self, pin):
289 """Send the adult pin to Netflix in case an adult rated video requests it
291 Note: Once entered, it should last for the complete session (Not so sure about this)
301 Pin was accepted or not
303 :obj:`dict` of :obj:`str`
308 'authURL': self.user_data['authURL']
310 response = self._session_get(component='adult_pin', params=payload)
311 pin_response = self._process_response(response=response, component=self._get_api_url_for(component='adult_pin'))
312 keys = pin_response.keys()
313 if 'success' in keys:
319 def add_to_list (self, video_id):
320 """Adds a video to "my list" on Netflix
324 video_id : :obj:`str`
325 ID of th show/video/movie to be added
330 Adding was successfull
332 return self._update_my_list(video_id=video_id, operation='add')
334 def remove_from_list (self, video_id):
335 """Removes a video from "my list" on Netflix
339 video_id : :obj:`str`
340 ID of th show/video/movie to be removed
345 Removing was successfull
347 return self._update_my_list(video_id=video_id, operation='remove')
349 def rate_video (self, video_id, rating):
350 """Rate a video on Netflix
354 video_id : :obj:`str`
355 ID of th show/video/movie to be rated
358 Rating, must be between 0 & 10
363 Rating successfull or not
366 # dirty rating validation
368 if rating > 10 or rating < 0:
371 # In opposition to Kodi, Netflix uses a rating from 0 to in 0.5 steps
376 'Content-Type': 'application/json',
377 'Accept': 'application/json, text/javascript, */*',
385 payload = json.dumps({
386 'authURL': self.user_data['authURL']
389 response = self._session_post(component='set_video_rating', type='api', params=params, headers=headers, data=payload)
390 return response.status_code == 200
392 def parse_video_list_ids (self, response_data):
393 """Parse the list of video ids e.g. rip out the parts we need
397 response_data : :obj:`dict` of :obj:`str`
398 Parsed response JSON from the ´fetch_video_list_ids´ call
402 :obj:`dict` of :obj:`dict`
403 Video list ids in the format:
407 "3589e2c6-ca3b-48b4-a72d-34f2c09ffbf4_11568367": {
408 "displayName": "US-Serien",
409 "id": "3589e2c6-ca3b-48b4-a72d-34f2c09ffbf4_11568367",
414 "3589e2c6-ca3b-48b4-a72d-34f2c09ffbf4_11568368": {
419 "3589e2c6-ca3b-48b4-a72d-34f2c09ffbf4_11568364": {
420 "displayName": "Meine Liste",
421 "id": "3589e2c6-ca3b-48b4-a72d-34f2c09ffbf4_11568364",
426 "3589e2c6-ca3b-48b4-a72d-34f2c09ffbf4_11568365": {
431 "3589e2c6-ca3b-48b4-a72d-34f2c09ffbf4_11568382": {
432 "displayName": "Passend zu Family Guy",
433 "id": "3589e2c6-ca3b-48b4-a72d-34f2c09ffbf4_11568382",
438 "3589e2c6-ca3b-48b4-a72d-34f2c09ffbf4_11568397": {
444 # prepare the return dictionary
446 for key in self.video_list_keys:
447 video_list_ids[key] = {}
449 # check if the list items are hidden behind a `value` sub key
450 # this is the case when we fetch the lists via POST, not via a GET preflight request
451 if 'value' in response_data.keys():
452 response_data = response_data['value']
454 # subcatogorize the lists by their context
455 video_lists = response_data['lists']
456 for video_list_id in video_lists.keys():
457 video_list = video_lists[video_list_id]
458 if video_list.get('context', False) != False:
459 if video_list['context'] == 'genre':
460 video_list_ids['genres'].update(self.parse_video_list_ids_entry(id=video_list_id, entry=video_list))
461 elif video_list['context'] == 'similars' or video_list['context'] == 'becauseYouAdded':
462 video_list_ids['recommendations'].update(self.parse_video_list_ids_entry(id=video_list_id, entry=video_list))
464 video_list_ids['user'].update(self.parse_video_list_ids_entry(id=video_list_id, entry=video_list))
465 return video_list_ids
467 def parse_video_list_ids_entry (self, id, entry):
468 """Parse a video id entry e.g. rip out the parts we need
472 response_data : :obj:`dict` of :obj:`str`
473 Dictionary entry from the ´fetch_video_list_ids´ call
478 Unique id of the video list
480 entry : :obj:`dict` of :obj:`str`
481 Video list entry in the format:
483 "3589e2c6-ca3b-48b4-a72d-34f2c09ffbf4_11568382": {
484 "displayName": "Passend zu Family Guy",
485 "id": "3589e2c6-ca3b-48b4-a72d-34f2c09ffbf4_11568382",
494 'index': entry['index'],
495 'name': entry['context'],
496 'displayName': entry['displayName'],
497 'size': entry['length']
501 def parse_search_results (self, response_data):
502 """Parse the list of search results, rip out the parts we need
503 and extend it with detailed show informations
507 response_data : :obj:`dict` of :obj:`str`
508 Parsed response JSON from the `fetch_search_results` call
512 :obj:`dict` of :obj:`dict` of :obj:`str`
513 Search results in the format:
517 "boxarts": "https://art-s.nflximg.net/0d7af/d5c72668c35d3da65ae031302bd4ae1bcc80d7af.jpg",
518 "detail_text": "Die legend\u00e4re und mit 13 Emmys nominierte Serie von Gene Roddenberry inspirierte eine ganze Generation.",
520 "season_id": "70109435",
521 "synopsis": "Unter Befehl von Captain Kirk begibt sich die Besatzung des Raumschiffs Enterprise in die Tiefen des Weltraums, wo sie fremde Galaxien und neue Zivilisationen erforscht.",
522 "title": "Star Trek",
531 raw_search_results = response_data['value']['videos']
532 for entry_id in raw_search_results:
533 if self._is_size_key(key=entry_id) == False:
534 # fetch information about each show & build up a proper search results dictionary
535 show = self.parse_show_list_entry(id=entry_id, entry=raw_search_results[entry_id])
536 show[entry_id].update(self.parse_show_information(id=entry_id, response_data=self.fetch_show_information(id=entry_id, type=show[entry_id]['type'])))
537 search_results.update(show)
538 return search_results
540 def parse_show_list_entry (self, id, entry):
541 """Parse a show entry e.g. rip out the parts we need
545 response_data : :obj:`dict` of :obj:`str`
546 Dictionary entry from the ´fetch_show_information´ call
549 Unique id of the video list
553 entry : :obj:`dict` of :obj:`dict` of :obj:`str`
554 Show list entry in the format:
557 "3589e2c6-ca3b-48b4-a72d-34f2c09ffbf4_11568382": {
558 "id": "3589e2c6-ca3b-48b4-a72d-34f2c09ffbf4_11568382",
559 "title": "Enterprise",
560 "boxarts": "https://art-s.nflximg.net/.../smth.jpg",
568 'title': entry['title'],
569 'boxarts': entry['boxarts']['_342x192']['jpg']['url'],
570 'type': entry['summary']['type']
574 def parse_video_list (self, response_data):
575 """Parse a list of videos
579 response_data : :obj:`dict` of :obj:`str`
580 Parsed response JSON from the `fetch_video_list` call
584 :obj:`dict` of :obj:`dict`
585 Video list in the format:
591 "big": "https://art-s.nflximg.net/5e7d3/b3b48749843fd3a36db11c319ffa60f96b55e7d3.jpg",
592 "small": "https://art-s.nflximg.net/57543/a039845c2eb9186dc26019576d895bf5a1957543.jpg"
607 "episode_count": null,
613 "interesting_moment": "https://art-s.nflximg.net/09544/ed4b3073394b4469fb6ec22b9df81a4f5cb09544.jpg",
614 "list_id": "9588df32-f957-40e4-9055-1f6f33b60103_46891306",
617 "description": "Nur f\u00fcr Erwachsene geeignet.",
623 "regular_synopsis": "Ein Spielzeughersteller erweckt aus Versehen die Seele der M\u00f6rderpuppe Chucky erneut zum Leben, die sich unmittelbar wieder ihren m\u00f6rderischen Aktivit\u00e4ten zuwendet.",
625 "seasons_count": null,
626 "seasons_label": null,
627 "synopsis": "Die allseits beliebte, von D\u00e4monen besessene M\u00f6rderpuppe ist wieder da und verbreitet erneut Horror und Schrecken.",
632 "title": "Chucky 2 \u2013 Die M\u00f6rderpuppe ist wieder da",
640 "big": "https://art-s.nflximg.net/7c10d/5dcc3fc8f08487e92507627068cfe26ef727c10d.jpg",
641 "small": "https://art-s.nflximg.net/5bc0e/f3be361b8c594929062f90a8d9c6eb57fb75bc0e.jpg"
658 "interesting_moment": "https://art-s.nflximg.net/0188e/19cd705a71ee08c8d2609ae01cd8a97a86c0188e.jpg",
659 "list_id": "9588df32-f957-40e4-9055-1f6f33b60103_46891306",
662 "description": "Geeignet ab 12 Jahren.",
668 "regular_synopsis": "Comedy-Serie \u00fcber die Erlebnisse eines Tatortreinigers, der seine schmutzige Arbeit erst beginnen kann, wenn die Polizei die Tatortanalyse abgeschlossen hat.",
671 "seasons_label": "5 Staffeln",
672 "synopsis": "In den meisten Krimiserien werden Mordf\u00e4lle auf faszinierende und spannende Weise gel\u00f6st. Diese Serie ist anders.",
676 "title": "Der Tatortreiniger",
684 raw_video_list = response_data['value']
685 netflix_list_id = self.parse_netflix_list_id(video_list=raw_video_list);
686 for video_id in raw_video_list['videos']:
687 if self._is_size_key(key=video_id) == False:
688 video_list.update(self.parse_video_list_entry(id=video_id, list_id=netflix_list_id, video=raw_video_list['videos'][video_id], persons=raw_video_list['person'], genres=raw_video_list['genres']))
691 def parse_video_list_entry (self, id, list_id, video, persons, genres):
692 """Parse a video list entry e.g. rip out the parts we need
697 Unique id of the video
700 Unique id of the containing list
702 video : :obj:`dict` of :obj:`str`
703 Video entry from the ´fetch_video_list´ call
705 persons : :obj:`dict` of :obj:`dict` of :obj:`str`
706 List of persons with reference ids
708 persons : :obj:`dict` of :obj:`dict` of :obj:`str`
709 List of genres with reference ids
713 entry : :obj:`dict` of :obj:`dict` of :obj:`str`
714 Video list entry in the format:
720 "big": "https://art-s.nflximg.net/5e7d3/b3b48749843fd3a36db11c319ffa60f96b55e7d3.jpg",
721 "small": "https://art-s.nflximg.net/57543/a039845c2eb9186dc26019576d895bf5a1957543.jpg"
736 "episode_count": null,
742 "interesting_moment": "https://art-s.nflximg.net/09544/ed4b3073394b4469fb6ec22b9df81a4f5cb09544.jpg",
743 "list_id": "9588df32-f957-40e4-9055-1f6f33b60103_46891306",
746 "description": "Nur f\u00fcr Erwachsene geeignet.",
752 "regular_synopsis": "Ein Spielzeughersteller erweckt aus Versehen die Seele der M\u00f6rderpuppe Chucky erneut zum Leben, die sich unmittelbar wieder ihren m\u00f6rderischen Aktivit\u00e4ten zuwendet.",
754 "seasons_count": null,
755 "seasons_label": null,
756 "synopsis": "Die allseits beliebte, von D\u00e4monen besessene M\u00f6rderpuppe ist wieder da und verbreitet erneut Horror und Schrecken.",
761 "title": "Chucky 2 \u2013 Die M\u00f6rderpuppe ist wieder da",
768 season_info = self.parse_season_information_for_video(video=video)
773 'title': video['title'],
774 'synopsis': video['synopsis'],
775 'regular_synopsis': video['regularSynopsis'],
776 'type': video['summary']['type'],
777 'rating': video['userRating'].get('average', 0) if video['userRating'].get('average', None) != None else video['userRating'].get('predicted', 0),
778 'episode_count': season_info['episode_count'],
779 'seasons_label': season_info['seasons_label'],
780 'seasons_count': season_info['seasons_count'],
781 'in_my_list': video['queue']['inQueue'],
782 'year': video['releaseYear'],
783 'runtime': self.parse_runtime_for_video(video=video),
784 'watched': video['watched'],
785 'tags': self.parse_tags_for_video(video=video),
786 'genres': self.parse_genres_for_video(video=video, genres=genres),
787 'quality': self.parse_quality_for_video(video=video),
788 'cast': self.parse_cast_for_video(video=video, persons=persons),
789 'directors': self.parse_directors_for_video(video=video, persons=persons),
790 'creators': self.parse_creators_for_video(video=video, persons=persons),
792 'board': None if 'board' not in video['maturity']['rating'].keys() else video['maturity']['rating']['board'],
793 'value': None if 'value' not in video['maturity']['rating'].keys() else video['maturity']['rating']['value'],
794 'description': None if 'maturityDescription' not in video['maturity']['rating'].keys() else video['maturity']['rating']['maturityDescription'],
795 'level': None if 'maturityLevel' not in video['maturity']['rating'].keys() else video['maturity']['rating']['maturityLevel']
798 'small': video['boxarts']['_342x192']['jpg']['url'],
799 'big': video['boxarts']['_1280x720']['jpg']['url']
801 'interesting_moment': None if 'interestingMoment' not in video.keys() else video['interestingMoment']['_665x375']['jpg']['url'],
802 'artwork': video['artWorkByType']['BILLBOARD']['_1280x720']['jpg']['url'],
806 def parse_creators_for_video (self, video, persons):
807 """Matches ids with person names to generate a list of creators
811 video : :obj:`dict` of :obj:`str`
812 Dictionary entry for one video entry
814 persons : :obj:`dict` of :obj:`str`
815 Raw resposne of all persons delivered by the API call
819 :obj:`list` of :obj:`str`
823 for person_key in dict(persons).keys():
824 if self._is_size_key(key=person_key) == False and person_key != 'summary':
825 for creator_key in dict(video['creators']).keys():
826 if self._is_size_key(key=creator_key) == False and creator_key != 'summary':
827 if video['creators'][creator_key][1] == person_key:
828 creators.append(persons[person_key]['name'])
831 def parse_directors_for_video (self, video, persons):
832 """Matches ids with person names to generate a list of directors
836 video : :obj:`dict` of :obj:`str`
837 Dictionary entry for one video entry
839 persons : :obj:`dict` of :obj:`str`
840 Raw resposne of all persons delivered by the API call
844 :obj:`list` of :obj:`str`
848 for person_key in dict(persons).keys():
849 if self._is_size_key(key=person_key) == False and person_key != 'summary':
850 for director_key in dict(video['directors']).keys():
851 if self._is_size_key(key=director_key) == False and director_key != 'summary':
852 if video['directors'][director_key][1] == person_key:
853 directors.append(persons[person_key]['name'])
856 def parse_cast_for_video (self, video, persons):
857 """Matches ids with person names to generate a list of cast members
861 video : :obj:`dict` of :obj:`str`
862 Dictionary entry for one video entry
864 persons : :obj:`dict` of :obj:`str`
865 Raw resposne of all persons delivered by the API call
869 :obj:`list` of :obj:`str`
873 for person_key in dict(persons).keys():
874 if self._is_size_key(key=person_key) == False and person_key != 'summary':
875 for cast_key in dict(video['cast']).keys():
876 if self._is_size_key(key=cast_key) == False and cast_key != 'summary':
877 if video['cast'][cast_key][1] == person_key:
878 cast.append(persons[person_key]['name'])
881 def parse_genres_for_video (self, video, genres):
882 """Matches ids with genre names to generate a list of genres for a video
886 video : :obj:`dict` of :obj:`str`
887 Dictionary entry for one video entry
889 genres : :obj:`dict` of :obj:`str`
890 Raw resposne of all genres delivered by the API call
894 :obj:`list` of :obj:`str`
898 for genre_key in dict(genres).keys():
899 if self._is_size_key(key=genre_key) == False and genre_key != 'summary':
900 for show_genre_key in dict(video['genres']).keys():
901 if self._is_size_key(key=show_genre_key) == False and show_genre_key != 'summary':
902 if video['genres'][show_genre_key][1] == genre_key:
903 video_genres.append(genres[genre_key]['name'])
906 def parse_tags_for_video (self, video):
907 """Parses a nested list of tags, removes the not needed meta information & returns a raw string list
911 video : :obj:`dict` of :obj:`str`
912 Dictionary entry for one video entry
916 :obj:`list` of :obj:`str`
920 for tag_key in dict(video['tags']).keys():
921 if self._is_size_key(key=tag_key) == False and tag_key != 'summary':
922 tags.append(video['tags'][tag_key]['name'])
925 def parse_season_information_for_video (self, video):
926 """Checks if the fiven video is a show (series) and returns season & episode information
930 video : :obj:`dict` of :obj:`str`
931 Dictionary entry for one video entry
935 :obj:`dict` of :obj:`str`
936 Episode count / Season Count & Season label if given
939 'episode_count': None,
940 'seasons_label': None,
941 'seasons_count': None
943 if video['summary']['type'] == 'show':
945 'episode_count': video['episodeCount'],
946 'seasons_label': video['numSeasonsLabel'],
947 'seasons_count': video['seasonCount']
951 def parse_quality_for_video (self, video):
952 """Transforms Netflix quality information in video resolution info
956 video : :obj:`dict` of :obj:`str`
957 Dictionary entry for one video entry
965 if video['videoQuality']['hasHD']:
967 if video['videoQuality']['hasUltraHD']:
971 def parse_runtime_for_video (self, video):
972 """Checks if the video is a movie & returns the runtime if given
976 video : :obj:`dict` of :obj:`str`
977 Dictionary entry for one video entry
982 Runtime of the video (in seconds)
985 if video['summary']['type'] != 'show':
986 runtime = video['runtime']
989 def parse_netflix_list_id (self, video_list):
990 """Parse a video list and extract the list id
994 video_list : :obj:`dict` of :obj:`str`
999 entry : :obj:`str` or None
1002 netflix_list_id = None
1003 if 'lists' in video_list.keys():
1004 for video_id in video_list['lists']:
1005 if self._is_size_key(key=video_id) == False:
1006 netflix_list_id = video_id;
1007 return netflix_list_id
1009 def parse_show_information (self, id, response_data):
1010 """Parse extended show information (synopsis, seasons, etc.)
1017 response_data : :obj:`dict` of :obj:`str`
1018 Parsed response JSON from the `fetch_show_information` call
1022 entry : :obj:`dict` of :obj:`str`
1023 Show information in the format:
1025 "season_id": "80113084",
1026 "synopsis": "Aus verzweifelter Geldnot versucht sich der Familienvater und Drucker Jochen als Geldf\u00e4lscher und rutscht dabei immer mehr in die dunkle Welt des Verbrechens ab."
1027 "detail_text": "I´m optional"
1031 raw_show = response_data['value']['videos'][id]
1032 show.update({'synopsis': raw_show['regularSynopsis']})
1033 if 'evidence' in raw_show:
1034 show.update({'detail_text': raw_show['evidence']['value']['text']})
1035 if 'seasonList' in raw_show:
1036 show.update({'season_id': raw_show['seasonList']['current'][1]})
1039 def parse_seasons (self, id, response_data):
1040 """Parse a list of seasons for a given show
1047 response_data : :obj:`dict` of :obj:`str`
1048 Parsed response JSON from the `fetch_seasons_for_show` call
1052 entry : :obj:`dict` of :obj:`dict` of :obj:`str`
1053 Season information in the format:
1058 "shortName": "St. 1",
1060 "big": "https://art-s.nflximg.net/5e7d3/b3b48749843fd3a36db11c319ffa60f96b55e7d3.jpg",
1061 "small": "https://art-s.nflximg.net/57543/a039845c2eb9186dc26019576d895bf5a1957543.jpg"
1063 "interesting_moment": "https://art-s.nflximg.net/09544/ed4b3073394b4469fb6ec22b9df81a4f5cb09544.jpg"
1068 "shortName": "St. 2",
1070 "big": "https://art-s.nflximg.net/5e7d3/b3b48749843fd3a36db11c319ffa60f96b55e7d3.jpg",
1071 "small": "https://art-s.nflximg.net/57543/a039845c2eb9186dc26019576d895bf5a1957543.jpg"
1073 "interesting_moment": "https://art-s.nflximg.net/09544/ed4b3073394b4469fb6ec22b9df81a4f5cb09544.jpg"
1078 raw_seasons = response_data['value']
1079 for season in raw_seasons['seasons']:
1080 if self._is_size_key(key=season) == False:
1081 seasons.update(self.parse_season_entry(season=raw_seasons['seasons'][season], videos=raw_seasons['videos']))
1084 def parse_season_entry (self, season, videos):
1085 """Parse a season list entry e.g. rip out the parts we need
1089 season : :obj:`dict` of :obj:`str`
1090 Season entry from the `fetch_seasons_for_show` call
1094 entry : :obj:`dict` of :obj:`dict` of :obj:`str`
1095 Season list entry in the format:
1101 "shortName": "St. 1",
1103 "big": "https://art-s.nflximg.net/5e7d3/b3b48749843fd3a36db11c319ffa60f96b55e7d3.jpg",
1104 "small": "https://art-s.nflximg.net/57543/a039845c2eb9186dc26019576d895bf5a1957543.jpg"
1106 "interesting_moment": "https://art-s.nflximg.net/09544/ed4b3073394b4469fb6ec22b9df81a4f5cb09544.jpg"
1112 for key in videos.keys():
1113 if self._is_size_key(key=key) == False:
1117 for idx in videos[video_key]['seasonList']:
1118 if self._is_size_key(key=idx) == False and idx != 'summary':
1119 sorting[int(videos[video_key]['seasonList'][idx][1])] = int(idx)
1121 season['summary']['id']: {
1122 'idx': sorting[season['summary']['id']],
1123 'id': season['summary']['id'],
1124 'text': season['summary']['name'],
1125 'shortName': season['summary']['shortName'],
1127 'small': videos[video_key]['boxarts']['_342x192']['jpg']['url'],
1128 'big': videos[video_key]['boxarts']['_1280x720']['jpg']['url']
1130 'interesting_moment': videos[video_key]['interestingMoment']['_665x375']['jpg']['url'],
1134 def parse_episodes_by_season (self, response_data):
1135 """Parse episodes for a given season/episode list
1139 response_data : :obj:`dict` of :obj:`str`
1140 Parsed response JSON from the `fetch_seasons_for_show` call
1144 entry : :obj:`dict` of :obj:`dict` of :obj:`str`
1145 Season information in the format:
1149 "banner": "https://art-s.nflximg.net/63a36/c7fdfe6604ef2c22d085ac5dca5f69874e363a36.jpg",
1152 "fanart": "https://art-s.nflximg.net/74e02/e7edcc5cc7dcda1e94d505df2f0a2f0d22774e02.jpg",
1158 "mediatype": "episode",
1162 "plot": "Als die Griffins und andere Einwohner von Quahog in die Villa von James Woods eingeladen werden, muss pl\u00f6tzlich ein Mord aufgekl\u00e4rt werden.",
1163 "poster": "https://art-s.nflximg.net/72fd6/57088715e8d436fdb6986834ab39124b0a972fd6.jpg",
1164 "rating": 3.9111512,
1166 "thumb": "https://art-s.nflximg.net/be686/07680670a68da8749eba607efb1ae37f9e3be686.jpg",
1167 "title": "Und dann gab es weniger (Teil 1)",
1172 "banner": "https://art-s.nflximg.net/63a36/c7fdfe6604ef2c22d085ac5dca5f69874e363a36.jpg",
1175 "fanart": "https://art-s.nflximg.net/c472c/6c10f9578bf2c1d0a183c2ccb382931efcbc472c.jpg",
1181 "mediatype": "episode",
1185 "plot": "Wer ist der M\u00f6rder? Nach zahlreichen Morden wird immer wieder jemand anderes verd\u00e4chtigt.",
1186 "poster": "https://art-s.nflximg.net/72fd6/57088715e8d436fdb6986834ab39124b0a972fd6.jpg",
1187 "rating": 3.9111512,
1189 "thumb": "https://art-s.nflximg.net/15a08/857d59126641987bec302bb147a802a00d015a08.jpg",
1190 "title": "Und dann gab es weniger (Teil 2)",
1197 raw_episodes = response_data['value']['videos']
1198 for episode_id in raw_episodes:
1199 if self._is_size_key(key=episode_id) == False:
1200 if (raw_episodes[episode_id]['summary']['type'] == 'episode'):
1201 episodes.update(self.parse_episode(episode=raw_episodes[episode_id], genres=response_data['value']['genres']))
1204 def parse_episode (self, episode, genres=None):
1205 """Parse episode from an list of episodes by season
1209 episode : :obj:`dict` of :obj:`str`
1210 Episode entry from the `fetch_episodes_by_season` call
1214 entry : :obj:`dict` of :obj:`dict` of :obj:`str`
1215 Episode information in the format:
1219 "banner": "https://art-s.nflximg.net/63a36/c7fdfe6604ef2c22d085ac5dca5f69874e363a36.jpg",
1222 "fanart": "https://art-s.nflximg.net/74e02/e7edcc5cc7dcda1e94d505df2f0a2f0d22774e02.jpg",
1228 "mediatype": "episode",
1232 "plot": "Als die Griffins und andere Einwohner von Quahog in die Villa von James Woods eingeladen werden, muss pl\u00f6tzlich ein Mord aufgekl\u00e4rt werden.",
1233 "poster": "https://art-s.nflximg.net/72fd6/57088715e8d436fdb6986834ab39124b0a972fd6.jpg",
1234 "rating": 3.9111512,
1236 "thumb": "https://art-s.nflximg.net/be686/07680670a68da8749eba607efb1ae37f9e3be686.jpg",
1237 "title": "Und dann gab es weniger (Teil 1)",
1244 episode['summary']['id']: {
1245 'id': episode['summary']['id'],
1246 'episode': episode['summary']['episode'],
1247 'season': episode['summary']['season'],
1248 'plot': episode['info']['synopsis'],
1249 'duration': episode['info']['runtime'],
1250 'title': episode['info']['title'],
1251 'year': episode['info']['releaseYear'],
1252 'genres': self.parse_genres_for_video(video=episode, genres=genres),
1253 'mpaa': str(episode['maturity']['rating']['board']) + ' ' + str(episode['maturity']['rating']['value']),
1254 'maturity': episode['maturity'],
1255 'playcount': (0, 1)[episode['watched']],
1256 'rating': episode['userRating'].get('average', 0) if episode['userRating'].get('average', None) != None else episode['userRating'].get('predicted', 0),
1257 'thumb': episode['info']['interestingMoments']['url'],
1258 'fanart': episode['interestingMoment']['_1280x720']['jpg']['url'],
1259 'poster': episode['boxarts']['_1280x720']['jpg']['url'],
1260 'banner': episode['boxarts']['_342x192']['jpg']['url'],
1261 'mediatype': {'episode': 'episode', 'movie': 'movie'}[episode['summary']['type']],
1262 'my_list': episode['queue']['inQueue'],
1263 'bookmark': episode['bookmarkPosition']
1267 def fetch_browse_list_contents (self):
1268 """Fetches the HTML data for the lists on the landing page (browse page) of Netflix
1272 :obj:`BeautifulSoup`
1273 Instance of an BeautifulSoup document containing the complete page contents
1275 response = self._session_get(component='browse')
1276 return BeautifulSoup(response.text, 'html.parser')
1278 def fetch_video_list_ids_via_preflight (self, list_from=0, list_to=50):
1279 """Fetches the JSON with detailed information based on the lists on the landing page (browse page) of Netflix
1280 via the preflight (GET) request
1284 list_from : :obj:`int`
1285 Start entry for pagination
1287 list_to : :obj:`int`
1288 Last entry for pagination
1292 :obj:`dict` of :obj:`dict` of :obj:`str`
1293 Raw Netflix API call response or api call error
1296 'fromRow': list_from,
1298 'opaqueImageExtension': 'jpg',
1299 'transparentImageExtension': 'png',
1301 'authURL': self.user_data['authURL']
1304 response = self._session_get(component='video_list_ids', params=payload, type='api')
1305 return self._process_response(response=response, component=self._get_api_url_for(component='video_list_ids'))
1307 def fetch_video_list_ids (self, list_from=0, list_to=50):
1308 """Fetches the JSON with detailed information based on the lists on the landing page (browse page) of Netflix
1312 list_from : :obj:`int`
1313 Start entry for pagination
1315 list_to : :obj:`int`
1316 Last entry for pagination
1320 :obj:`dict` of :obj:`dict` of :obj:`str`
1321 Raw Netflix API call response or api call error
1324 ['lolomo', {'from': list_from, 'to': list_to}, ['displayName', 'context', 'id', 'index', 'length']]
1327 response = self._path_request(paths=paths)
1328 return self._process_response(response=response, component='Video list ids')
1330 def fetch_search_results (self, search_str, list_from=0, list_to=10):
1331 """Fetches the JSON which contains the results for the given search query
1335 search_str : :obj:`str`
1336 String to query Netflix search for
1338 list_from : :obj:`int`
1339 Start entry for pagination
1341 list_to : :obj:`int`
1342 Last entry for pagination
1346 :obj:`dict` of :obj:`dict` of :obj:`str`
1347 Raw Netflix API call response or api call error
1349 # properly encode the search string
1350 encoded_search_string = quote(search_str)
1353 ['search', encoded_search_string, 'titles', {'from': list_from, 'to': list_to}, ['summary', 'title']],
1354 ['search', encoded_search_string, 'titles', {'from': list_from, 'to': list_to}, 'boxarts', '_342x192', 'jpg'],
1355 ['search', encoded_search_string, 'titles', ['id', 'length', 'name', 'trackIds', 'requestId']],
1356 ['search', encoded_search_string, 'suggestions', 0, 'relatedvideos', {'from': list_from, 'to': list_to}, ['summary', 'title']],
1357 ['search', encoded_search_string, 'suggestions', 0, 'relatedvideos', {'from': list_from, 'to': list_to}, 'boxarts', '_342x192', 'jpg'],
1358 ['search', encoded_search_string, 'suggestions', 0, 'relatedvideos', ['id', 'length', 'name', 'trackIds', 'requestId']]
1360 response = self._path_request(paths=paths)
1361 return self._process_response(response=response, component='Search results')
1363 def fetch_video_list (self, list_id, list_from=0, list_to=20):
1364 """Fetches the JSON which contains the contents of a given video list
1368 list_id : :obj:`str`
1369 Unique list id to query Netflix for
1371 list_from : :obj:`int`
1372 Start entry for pagination
1374 list_to : :obj:`int`
1375 Last entry for pagination
1379 :obj:`dict` of :obj:`dict` of :obj:`str`
1380 Raw Netflix API call response or api call error
1383 ['lists', list_id, {'from': list_from, 'to': list_to}, ['summary', 'title', 'synopsis', 'regularSynopsis', 'evidence', 'queue', 'episodeCount', 'info', 'maturity', 'runtime', 'seasonCount', 'releaseYear', 'userRating', 'numSeasonsLabel', 'bookmarkPosition', 'watched', 'videoQuality']],
1384 ['lists', list_id, {'from': list_from, 'to': list_to}, 'cast', {'from': 0, 'to': 15}, ['id', 'name']],
1385 ['lists', list_id, {'from': list_from, 'to': list_to}, 'cast', 'summary'],
1386 ['lists', list_id, {'from': list_from, 'to': list_to}, 'genres', {'from': 0, 'to': 5}, ['id', 'name']],
1387 ['lists', list_id, {'from': list_from, 'to': list_to}, 'genres', 'summary'],
1388 ['lists', list_id, {'from': list_from, 'to': list_to}, 'tags', {'from': 0, 'to': 9}, ['id', 'name']],
1389 ['lists', list_id, {'from': list_from, 'to': list_to}, 'tags', 'summary'],
1390 ['lists', list_id, {'from': list_from, 'to': list_to}, ['creators', 'directors'], {'from': 0, 'to': 49}, ['id', 'name']],
1391 ['lists', list_id, {'from': list_from, 'to': list_to}, ['creators', 'directors'], 'summary'],
1392 ['lists', list_id, {'from': list_from, 'to': list_to}, 'bb2OGLogo', '_400x90', 'png'],
1393 ['lists', list_id, {'from': list_from, 'to': list_to}, 'boxarts', '_342x192', 'jpg'],
1394 ['lists', list_id, {'from': list_from, 'to': list_to}, 'boxarts', '_1280x720', 'jpg'],
1395 ['lists', list_id, {'from': list_from, 'to': list_to}, 'storyarts', '_1632x873', 'jpg'],
1396 ['lists', list_id, {'from': list_from, 'to': list_to}, 'interestingMoment', '_665x375', 'jpg'],
1397 ['lists', list_id, {'from': list_from, 'to': list_to}, 'artWorkByType', 'BILLBOARD', '_1280x720', 'jpg']
1400 response = self._path_request(paths=paths)
1401 return self._process_response(response=response, component='Video list')
1403 def fetch_video_list_information (self, video_ids):
1404 """Fetches the JSON which contains the detail information of a list of given video ids
1408 video_ids : :obj:`list` of :obj:`str`
1409 List of video ids to fetch detail data for
1413 :obj:`dict` of :obj:`dict` of :obj:`str`
1414 Raw Netflix API call response or api call error
1417 for video_id in video_ids:
1418 paths.append(['videos', video_id, ['summary', 'title', 'synopsis', 'regularSynopsis', 'evidence', 'queue', 'episodeCount', 'info', 'maturity', 'runtime', 'seasonCount', 'releaseYear', 'userRating', 'numSeasonsLabel', 'bookmarkPosition', 'watched', 'videoQuality']])
1419 paths.append(['videos', video_id, 'cast', {'from': 0, 'to': 15}, ['id', 'name']])
1420 paths.append(['videos', video_id, 'cast', 'summary'])
1421 paths.append(['videos', video_id, 'genres', {'from': 0, 'to': 5}, ['id', 'name']])
1422 paths.append(['videos', video_id, 'genres', 'summary'])
1423 paths.append(['videos', video_id, 'tags', {'from': 0, 'to': 9}, ['id', 'name']])
1424 paths.append(['videos', video_id, 'tags', 'summary'])
1425 paths.append(['videos', video_id, ['creators', 'directors'], {'from': 0, 'to': 49}, ['id', 'name']])
1426 paths.append(['videos', video_id, ['creators', 'directors'], 'summary'])
1427 paths.append(['videos', video_id, 'bb2OGLogo', '_400x90', 'png'])
1428 paths.append(['videos', video_id, 'boxarts', '_342x192', 'jpg'])
1429 paths.append(['videos', video_id, 'boxarts', '_1280x720', 'jpg'])
1430 paths.append(['videos', video_id, 'storyarts', '_1632x873', 'jpg'])
1431 paths.append(['videos', video_id, 'interestingMoment', '_665x375', 'jpg'])
1432 paths.append(['videos', video_id, 'artWorkByType', 'BILLBOARD', '_1280x720', 'jpg'])
1434 response = self._path_request(paths=paths)
1435 return self._process_response(response=response, component='fetch_video_list_information')
1437 def fetch_metadata (self, id):
1438 """Fetches the JSON which contains the metadata for a given show/movie or season id
1443 Show id, movie id or season id
1447 :obj:`dict` of :obj:`dict` of :obj:`str`
1448 Raw Netflix API call response or api call error
1452 'imageformat': 'jpg',
1455 response = self._session_get(component='metadata', params=payload, type='api')
1456 return self._process_response(response=response, component=self._get_api_url_for(component='metadata'))
1458 def fetch_show_information (self, id, type):
1459 """Fetches the JSON which contains the detailed contents of a show
1464 Unique show id to query Netflix for
1467 Can be 'movie' or 'show'
1471 :obj:`dict` of :obj:`dict` of :obj:`str`
1472 Raw Netflix API call response or api call error
1474 # check if we have a show or a movie, the request made depends on this
1477 ['videos', id, ['requestId', 'regularSynopsis', 'evidence']],
1478 ['videos', id, 'seasonList', 'current', 'summary']
1481 paths = [['videos', id, ['requestId', 'regularSynopsis', 'evidence']]]
1482 response = self._path_request(paths=paths)
1483 return self._process_response(response=response, component='Show information')
1485 def fetch_seasons_for_show (self, id, list_from=0, list_to=30):
1486 """Fetches the JSON which contains the seasons of a given show
1491 Unique show id to query Netflix for
1493 list_from : :obj:`int`
1494 Start entry for pagination
1496 list_to : :obj:`int`
1497 Last entry for pagination
1501 :obj:`dict` of :obj:`dict` of :obj:`str`
1502 Raw Netflix API call response or api call error
1505 ['videos', id, 'seasonList', {'from': list_from, 'to': list_to}, 'summary'],
1506 ['videos', id, 'seasonList', 'summary'],
1507 ['videos', id, 'boxarts', '_342x192', 'jpg'],
1508 ['videos', id, 'boxarts', '_1280x720', 'jpg'],
1509 ['videos', id, 'storyarts', '_1632x873', 'jpg'],
1510 ['videos', id, 'interestingMoment', '_665x375', 'jpg']
1512 response = self._path_request(paths=paths)
1513 return self._process_response(response=response, component='Seasons')
1515 def fetch_episodes_by_season (self, season_id, list_from=-1, list_to=40):
1516 """Fetches the JSON which contains the episodes of a given season
1518 TODO: Add more metadata
1522 season_id : :obj:`str`
1523 Unique season_id id to query Netflix for
1525 list_from : :obj:`int`
1526 Start entry for pagination
1528 list_to : :obj:`int`
1529 Last entry for pagination
1533 :obj:`dict` of :obj:`dict` of :obj:`str`
1534 Raw Netflix API call response or api call error
1537 ['seasons', season_id, 'episodes', {'from': list_from, 'to': list_to}, ['summary', 'queue', 'info', 'maturity', 'userRating', 'bookmarkPosition', 'creditOffset', 'watched', 'videoQuality']],
1538 #['videos', season_id, 'cast', {'from': 0, 'to': 15}, ['id', 'name']],
1539 #['videos', season_id, 'cast', 'summary'],
1540 #['videos', season_id, 'genres', {'from': 0, 'to': 5}, ['id', 'name']],
1541 #['videos', season_id, 'genres', 'summary'],
1542 #['videos', season_id, 'tags', {'from': 0, 'to': 9}, ['id', 'name']],
1543 #['videos', season_id, 'tags', 'summary'],
1544 #['videos', season_id, ['creators', 'directors'], {'from': 0, 'to': 49}, ['id', 'name']],
1545 #['videos', season_id, ['creators', 'directors'], 'summary'],
1546 ['seasons', season_id, 'episodes', {'from': list_from, 'to': list_to}, 'genres', {'from': 0, 'to': 1}, ['id', 'name']],
1547 ['seasons', season_id, 'episodes', {'from': list_from, 'to': list_to}, 'genres', 'summary'],
1548 ['seasons', season_id, 'episodes', {'from': list_from, 'to': list_to}, 'interestingMoment', '_1280x720', 'jpg'],
1549 ['seasons', season_id, 'episodes', {'from': list_from, 'to': list_to}, 'interestingMoment', '_665x375', 'jpg'],
1550 ['seasons', season_id, 'episodes', {'from': list_from, 'to': list_to}, 'boxarts', '_342x192', 'jpg'],
1551 ['seasons', season_id, 'episodes', {'from': list_from, 'to': list_to}, 'boxarts', '_1280x720', 'jpg']
1553 response = self._path_request(paths=paths)
1554 return self._process_response(response=response, component='fetch_episodes_by_season')
1556 def refresh_session_data (self, account):
1557 """Reload the session data (profiles, user_data, api_data)
1561 account : :obj:`dict` of :obj:`str`
1562 Dict containing an email, country & a password property
1564 # load the profiles page (to verify the user)
1565 response = self._session_get(component='profiles')
1566 # parse out the needed inline information
1567 only_script_tags = SoupStrainer('script')
1568 page_soup = BeautifulSoup(response.text, 'html.parser', parse_only=only_script_tags)
1569 page_data = self._parse_page_contents(page_soup=page_soup)
1570 account_hash = self._generate_account_hash(account=account)
1571 self._save_data(filename=self.data_path + '_' + account_hash)
1573 def _path_request (self, paths):
1574 """Executes a post request against the shakti endpoint with Falcor style payload
1578 paths : :obj:`list` of :obj:`list`
1579 Payload with path querys for the Netflix Shakti API in Falcor style
1583 :obj:`requests.response`
1584 Response from a POST call made with Requests
1587 'Content-Type': 'application/json',
1588 'Accept': 'application/json, text/javascript, */*',
1593 'authURL': self.user_data['authURL']
1597 'model': self.user_data['gpsModel']
1600 return self._session_post(component='shakti', type='api', params=params, headers=headers, data=data)
1602 def _is_size_key (self, key):
1603 """Tiny helper that checks if a given key is called $size or size, as we need to check this often
1608 Key to check the value for
1613 Key has a size value or not
1615 return key == '$size' or key == 'size'
1617 def _get_api_url_for (self, component):
1618 """Tiny helper that builds the url for a requested API endpoint component
1622 component : :obj:`str`
1623 Component endpoint to build the URL for
1630 if self.api_data['API_ROOT'].find(self.api_data['API_BASE_URL']) > -1:
1631 return self.api_data['API_ROOT'] + '/' + self.api_data['BUILD_IDENTIFIER'] + self.urls[component]
1633 return self.api_data['API_ROOT'] + self.api_data['API_BASE_URL'] + '/' + self.api_data['BUILD_IDENTIFIER'] + self.urls[component]
1635 def _get_document_url_for (self, component):
1636 """Tiny helper that builds the url for a requested document endpoint component
1640 component : :obj:`str`
1641 Component endpoint to build the URL for
1648 return self.base_url + self.urls[component]
1650 def _process_response (self, response, component):
1651 """Tiny helper to check responses for API requests
1655 response : :obj:`requests.response`
1656 Response from a requests instance
1658 component : :obj:`str`
1663 :obj:`dict` of :obj:`dict` of :obj:`str` or :obj:`dict` of :obj:`str`
1664 Raw Netflix API call response or api call error
1666 # check if we´re not authorized to make thios call
1667 if response.status_code == 401:
1670 'message': 'Session invalid',
1673 # check if somethign else failed
1674 if response.status_code != 200:
1677 'message': 'API call for "' + component + '" failed',
1678 'code': response.status_code
1680 # return the parsed response & everything´s fine
1681 return response.json()
1683 def _to_unicode(self, str):
1684 '''Attempt to fix non uft-8 string into utf-8, using a limited set of encodings
1696 # fuller list of encodings at http://docs.python.org/library/codecs.html#standard-encodings
1697 if not str: return u''
1699 # we could add more encodings here, as warranted.
1700 encodings = ('ascii', 'utf8', 'latin1')
1701 for enc in encodings:
1704 u = unicode(str,enc)
1705 except UnicodeDecodeError:
1708 u = unicode(str, errors='replace')
1711 def _update_my_list (self, video_id, operation):
1712 """Tiny helper to add & remove items from "my list"
1716 video_id : :obj:`str`
1717 ID of the show/movie to be added
1719 operation : :obj:`str`
1720 Either "add" or "remove"
1725 Operation successfull
1728 'Content-Type': 'application/json',
1729 'Accept': 'application/json, text/javascript, */*',
1732 payload = json.dumps({
1733 'operation': operation,
1734 'videoId': int(video_id),
1735 'authURL': self.user_data['authURL']
1738 response = self._session_post(component='update_my_list', type='api', headers=headers, data=payload)
1739 return response.status_code == 200
1741 def _save_data(self, filename):
1742 """Tiny helper that stores session data from the session in a given file
1746 filename : :obj:`str`
1747 Complete path incl. filename that determines where to store the cookie
1752 Storage procedure was successfull
1754 if not os.path.isdir(os.path.dirname(filename)):
1756 with open(filename, 'w') as f:
1759 'user_data': self.user_data,
1760 'api_data': self.api_data,
1761 'profiles': self.profiles
1764 def _load_data(self, filename):
1765 """Tiny helper that loads session data into the active session from a given file
1769 filename : :obj:`str`
1770 Complete path incl. filename that determines where to load the data from
1775 Load procedure was successfull
1777 if not os.path.isfile(filename):
1780 with open(filename) as f:
1781 data = pickle.load(f)
1783 self.profiles = data['profiles']
1784 self.user_data = data['user_data']
1785 self.api_data = data['api_data']
1789 def _delete_data (self, path):
1790 """Tiny helper that deletes session data
1794 filename : :obj:`str`
1795 Complete path incl. filename that determines where to delete the files
1798 head, tail = os.path.split(path)
1799 for subdir, dirs, files in os.walk(head):
1802 os.remove(os.path.join(subdir, file))
1804 def _save_cookies(self, filename):
1805 """Tiny helper that stores cookies from the session in a given file
1809 filename : :obj:`str`
1810 Complete path incl. filename that determines where to store the cookie
1815 Storage procedure was successfull
1817 if not os.path.isdir(os.path.dirname(filename)):
1819 with open(filename, 'w') as f:
1821 pickle.dump(self.session.cookies._cookies, f)
1823 def _load_cookies(self, filename):
1824 """Tiny helper that loads cookies into the active session from a given file
1828 filename : :obj:`str`
1829 Complete path incl. filename that determines where to load the cookie from
1834 Load procedure was successfull
1836 if not os.path.isfile(filename):
1839 with open(filename) as f:
1840 _cookies = pickle.load(f)
1842 jar = cookies.RequestsCookieJar()
1843 jar._cookies = _cookies
1844 self.session.cookies = jar
1848 def _delete_cookies (self, path):
1849 """Tiny helper that deletes cookie data
1853 filename : :obj:`str`
1854 Complete path incl. filename that determines where to delete the files
1857 head, tail = os.path.split(path)
1858 for subdir, dirs, files in os.walk(head):
1861 os.remove(os.path.join(subdir, file))
1863 def _generate_account_hash (self, account):
1864 """Generates a has for the given account (used for cookie verification)
1868 account : :obj:`dict` of :obj:`str`
1869 Dict containing an email, country & a password property
1876 return urlsafe_b64encode(account['email'])
1878 def _get_user_agent_for_current_platform (self):
1879 """Determines the user agent string for the current platform (to retrieve a valid ESN)
1884 User Agent for platform
1887 self.log(msg='Building User Agent for platform: ' + str(platform.system()) + ' - ' + str(platform.machine()))
1888 if platform.system() == 'Darwin':
1889 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'
1890 if platform.system() == 'Windows':
1891 return 'Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
1892 if platform.machine().startswith('arm'):
1893 return 'Mozilla/5.0 (X11; CrOS armv7l 7647.78.0) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/48.0.2564.109 Safari/537.36'
1894 return 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/56.0.2924.87 Safari/537.36'
1896 def _session_post (self, component, type='document', data={}, headers={}, params={}):
1897 """Executes a get request using requests for the current session & measures the duration of that request
1901 component : :obj:`str`
1905 Is it a document or API request ('document' is default)
1907 data : :obj:`dict` of :obj:`str`
1908 Payload body as dict
1910 header : :obj:`dict` of :obj:`str`
1911 Additional headers as dict
1913 params : :obj:`dict` of :obj:`str`
1919 Contents of the field to match
1921 url = self._get_document_url_for(component=component) if type == 'document' else self._get_api_url_for(component=component)
1923 response = self.session.post(url=url, data=data, params=params, headers=headers, verify=self.verify_ssl)
1925 self.log(msg='[POST] Request for "' + url + '" took ' + str(end - start) + ' seconds')
1928 def _session_get (self, component, type='document', params={}):
1929 """Executes a get request using requests for the current session & measures the duration of that request
1933 component : :obj:`str`
1937 Is it a document or API request ('document' is default)
1939 params : :obj:`dict` of :obj:`str`
1945 Contents of the field to match
1947 url = self._get_document_url_for(component=component) if type == 'document' else self._get_api_url_for(component=component)
1949 response = self.session.get(url=url, verify=self.verify_ssl, params=params)
1951 self.log(msg='[GET] Request for "' + url + '" took ' + str(end - start) + ' seconds')
1954 def _sloppy_parse_user_and_api_data (self, key, contents):
1955 """Try to find the user & API data from the inline js by using a string parser
1960 Key to match in the inline js
1962 contents : :obj:`str`
1968 Contents of the field to match
1970 key_start = contents.find(key + '"')
1971 if int(key_start) == -1:
1973 sub_contents = contents[int(key_start):]
1974 l = sub_contents.find('",')
1975 return contents[(int(key_start)+len(key)+3):int(key_start)+l].decode('string_escape')
1977 def _sloppy_parse_profiles (self, contents):
1978 """Try to find the profile data from the inline js by using a string parser & parse/convert the result to JSON
1982 contents : :obj:`str`
1987 :obj:`dict` of :obj:`str` or None
1990 profile_start = contents.find('profiles":')
1991 profile_list_start = contents.find('profilesList')
1992 if int(profile_start) > -1 and int(profile_list_start) > -1:
1995 return json.loads('{"a":{"' + contents[profile_start:profile_list_start-2].decode('string_escape') + '}}').get('a').get('profiles')
1996 except ValueError, e:
1998 except TypeError, e:
2002 def _sloppy_parse_avatars (self, contents):
2003 """Try to find the avatar data from the inline js by using a string parser & parse/convert the result to JSON
2007 contents : :obj:`str`
2012 :obj:`dict` of :obj:`str` or None
2015 avatars_start = contents.find('"nf":')
2016 avatars_list_start = contents.find('"profiles"')
2017 if int(avatars_start) > -1 and int(avatars_list_start) > -1:
2020 return json.loads('{' + contents[avatars_start:avatars_list_start-2].decode('string_escape') + '}')
2021 except ValueError, e:
2023 except TypeError, e:
2027 def _verfify_auth_and_profiles_data (self, data):
2028 """Checks if the authURL has at least a certain length & doesn't overrule a certain length & if the profiles dict exists
2029 Simple validity check for the sloppy data parser
2033 data : :obj:`dict` of :obj:`str`
2041 if type(data.get('profiles')) == dict:
2042 if len(str(data.get('authURL', ''))) > 10 and len(str(data.get('authURL', ''))) < 50:
2046 def _sloppy_parse_inline_data (self, scripts):
2047 """Strips out all the needed user, api & profile data from the inline JS by string parsing
2048 Might fail, so if this doesn't succeed, a proper JS parser will chime in
2050 Note: This has been added for performance reasons only
2054 scripts : :obj:`list` of :obj:`BeautifoulSoup`
2055 Script tags & contents from the Netflix browse page
2059 :obj:`dict` of :obj:`str`
2060 Dict containijg user, api & profile data
2063 for script in scripts:
2064 contents = str(script.contents[0])
2065 important_data = ['authURL', 'API_BASE_URL', 'API_ROOT', 'BUILD_IDENTIFIER', 'ICHNAEA_ROOT', 'gpsModel', 'guid', 'esn']
2067 for key in important_data:
2068 _res = self._sloppy_parse_user_and_api_data(key, contents)
2070 res.update({key: _res})
2072 inline_data.update(res)
2075 profiles = self._sloppy_parse_profiles(contents)
2076 avatars = self._sloppy_parse_avatars(contents)
2077 if profiles != None:
2078 inline_data.update({'profiles': profiles})
2080 inline_data.update(avatars)
2083 def _accurate_parse_inline_data (self, scripts):
2084 """Uses a proper JS parser to fetch all the api, iser & profile data from within the inline JS
2086 Note: This is slow but accurate
2090 scripts : :obj:`list` of :obj:`BeautifoulSoup`
2091 Script tags & contents from the Netflix browse page
2095 :obj:`dict` of :obj:`str`
2096 Dict containing user, api & profile data
2099 from pyjsparser import PyJsParser
2100 parser = PyJsParser()
2101 for script in scripts:
2103 # unicode escape that incoming script stuff
2104 contents = self._to_unicode(str(script.contents[0]))
2105 # parse the JS & load the declarations we´re interested in
2106 parsed = parser.parse(contents)
2107 if len(parsed['body']) > 1 and parsed['body'][1]['expression']['right'].get('properties', None) != None:
2108 declarations = parsed['body'][1]['expression']['right']['properties']
2109 for declaration in declarations:
2110 for key in declaration:
2111 # we found the correct path if the declaration is a dict & of type 'ObjectExpression'
2112 if type(declaration[key]) is dict:
2113 if declaration[key]['type'] == 'ObjectExpression':
2114 # add all static data recursivly
2115 for expression in declaration[key]['properties']:
2116 data[expression['key']['value']] = self._parse_rec(expression['value'])
2117 inline_data.append(data)
2120 def _parse_rec (self, node):
2121 """Iterates over a JavaScript AST and return values found
2129 :obj:`dict` of :obj:`dict` or :obj:`str`
2130 Parsed contents of the node
2132 if node['type'] == 'ObjectExpression':
2134 for prop in node['properties']:
2135 _ret.update({prop['key']['value']: self._parse_rec(prop['value'])})
2137 if node['type'] == 'Literal':
2138 return node['value']
2140 def _parse_user_data (self, netflix_page_data):
2141 """Parse out the user data from the big chunk of dicts we got from
2142 parsing the JSON-ish data from the netflix homepage
2146 netflix_page_data : :obj:`list`
2147 List of all the JSON-ish data that has been extracted from the Netflix homepage
2148 see: extract_inline_netflix_page_data
2152 :obj:`dict` of :obj:`str`
2155 "guid": "72ERT45...",
2156 "authURL": "145637....",
2157 "gpsModel": "harris"
2161 important_fields = [
2167 # values are accessible via dict (sloppy parsing successfull)
2168 if type(netflix_page_data) == dict:
2169 for important_field in important_fields:
2170 user_data.update({important_field: netflix_page_data.get(important_field, '')})
2173 # values are stored in lists (returned from JS parser)
2174 for item in netflix_page_data:
2175 if 'memberContext' in dict(item).keys():
2176 for important_field in important_fields:
2177 user_data.update({important_field: item['memberContext']['data']['userInfo'][important_field]})
2181 def _parse_profile_data (self, netflix_page_data):
2182 """Parse out the profile data from the big chunk of dicts we got from
2183 parsing the JSON-ish data from the netflix homepage
2187 netflix_page_data : :obj:`list`
2188 List of all the JSON-ish data that has been extracted from the Netflix homepage
2189 see: extract_inline_netflix_page_data
2193 :obj:`dict` of :obj:`dict
2197 "profileName": "username",
2198 "avatar": "http://..../avatar.png",
2200 "isAccountOwner": False,
2207 important_fields = [
2213 # values are accessible via dict (sloppy parsing successfull)
2214 if type(netflix_page_data) == dict:
2215 for profile_id in netflix_page_data.get('profiles'):
2216 if self._is_size_key(key=profile_id) == False and type(netflix_page_data['profiles'][profile_id]) == dict and netflix_page_data['profiles'][profile_id].get('avatar', False) != False:
2217 profile = {'id': profile_id}
2218 for important_field in important_fields:
2219 profile.update({important_field: netflix_page_data['profiles'][profile_id]['summary'][important_field]})
2220 avatar_base = netflix_page_data['nf'].get(netflix_page_data['profiles'][profile_id]['summary']['avatarName'], False);
2221 avatar = 'https://secure.netflix.com/ffe/profiles/avatars_v2/320x320/PICON_029.png' if avatar_base == False else avatar_base['images']['byWidth']['320']['value']
2222 profile.update({'avatar': avatar, 'isFirstUse': False})
2223 profiles.update({profile_id: profile})
2226 # values are stored in lists (returned from JS parser)
2227 # TODO: get rid of this christmas tree of doom
2228 for item in netflix_page_data:
2229 if 'hasViewedRatingWelcomeModal' in dict(item).keys():
2230 for profile_id in item:
2231 if self._is_size_key(key=profile_id) == False and type(item[profile_id]) == dict and item[profile_id].get('avatar', False) != False:
2232 profile = {'id': profile_id}
2233 for important_field in important_fields:
2234 profile.update({important_field: item[profile_id]['summary'][important_field]})
2235 avatar_base = item['nf'].get(item[profile_id]['summary']['avatarName'], False);
2236 avatar = 'https://secure.netflix.com/ffe/profiles/avatars_v2/320x320/PICON_029.png' if avatar_base == False else avatar_base['images']['byWidth']['320']['value']
2237 profile.update({'avatar': avatar})
2238 profiles.update({profile_id: profile})
2241 def _parse_api_base_data (self, netflix_page_data):
2242 """Parse out the api url data from the big chunk of dicts we got from
2243 parsing the JSOn-ish data from the netflix homepage
2247 netflix_page_data : :obj:`list`
2248 List of all the JSON-ish data that has been extracted from the Netflix homepage
2249 see: extract_inline_netflix_page_data
2253 :obj:`dict` of :obj:`str
2256 "API_BASE_URL": "/shakti",
2257 "API_ROOT": "https://www.netflix.com/api",
2258 "BUILD_IDENTIFIER": "113b89c9",
2259 "ICHNAEA_ROOT": "/ichnaea"
2263 important_fields = [
2270 # values are accessible via dict (sloppy parsing successfull)
2271 if type(netflix_page_data) == dict:
2272 for important_field in important_fields:
2273 api_data.update({important_field: netflix_page_data.get(important_field, '')})
2276 for item in netflix_page_data:
2277 if 'serverDefs' in dict(item).keys():
2278 for important_field in important_fields:
2279 api_data.update({important_field: item['serverDefs']['data'][important_field]})
2282 def _parse_esn_data (self, netflix_page_data):
2283 """Parse out the esn id data from the big chunk of dicts we got from
2284 parsing the JSOn-ish data from the netflix homepage
2288 netflix_page_data : :obj:`list`
2289 List of all the JSON-ish data that has been extracted from the Netflix homepage
2290 see: extract_inline_netflix_page_data
2294 :obj:`str` of :obj:`str
2295 ESN, something like: NFCDCH-MC-D7D6F54LOPY8J416T72MQXX3RD20ME
2298 # values are accessible via dict (sloppy parsing successfull)
2299 if type(netflix_page_data) == dict:
2300 return netflix_page_data.get('esn', '')
2302 # values are stored in lists (returned from JS parser)
2303 for item in netflix_page_data:
2304 if 'esnGeneratorModel' in dict(item).keys():
2305 esn = item['esnGeneratorModel']['data']['esn']
2308 def _parse_page_contents (self, page_soup):
2309 """Call all the parsers we need to extract all the session relevant data from the HTML page
2310 Directly assigns it to the NetflixSession instance
2314 page_soup : :obj:`BeautifulSoup`
2315 Instance of an BeautifulSoup document or node containing the complete page contents
2317 netflix_page_data = self.extract_inline_netflix_page_data(page_soup=page_soup)
2318 self.user_data = self._parse_user_data(netflix_page_data=netflix_page_data)
2319 self.esn = self._parse_esn_data(netflix_page_data=netflix_page_data)
2320 self.api_data = self._parse_api_base_data(netflix_page_data=netflix_page_data)
2321 self.profiles = self._parse_profile_data(netflix_page_data=netflix_page_data)
2322 self.log(msg='Found ESN "' + self.esn + '"')
2323 return netflix_page_data