123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108 |
- import datetime as dt
- from .common import InfoExtractor
- from ..utils import (
- ExtractorError,
- float_or_none,
- jwt_encode_hs256,
- try_get,
- )
- class ATVAtIE(InfoExtractor):
- _VALID_URL = r'https?://(?:www\.)?atv\.at/tv/(?:[^/]+/){2,3}(?P<id>.*)'
- _TESTS = [{
- 'url': 'https://www.atv.at/tv/bauer-sucht-frau/staffel-18/bauer-sucht-frau/bauer-sucht-frau-staffel-18-folge-3-die-hofwochen',
- 'md5': '3c3b4aaca9f63e32b35e04a9c2515903',
- 'info_dict': {
- 'id': 'v-ce9cgn1e70n5-1',
- 'ext': 'mp4',
- 'title': 'Bauer sucht Frau - Staffel 18 Folge 3 - Die Hofwochen',
- },
- }, {
- 'url': 'https://www.atv.at/tv/bauer-sucht-frau/staffel-18/episode-01/bauer-sucht-frau-staffel-18-vorstellungsfolge-1',
- 'only_matching': True,
- }]
- # extracted from bootstrap.js function (search for e.encryption_key and use your browser's debugger)
- _ACCESS_ID = 'x_atv'
- _ENCRYPTION_KEY = 'Hohnaekeishoogh2omaeghooquooshia'
- def _extract_video_info(self, url, content, video):
- clip_id = content.get('splitId', content['id'])
- formats = []
- clip_urls = video['urls']
- for protocol, variant in clip_urls.items():
- source_url = try_get(variant, lambda x: x['clear']['url'])
- if not source_url:
- continue
- if protocol == 'dash':
- formats.extend(self._extract_mpd_formats(
- source_url, clip_id, mpd_id=protocol, fatal=False))
- elif protocol == 'hls':
- formats.extend(self._extract_m3u8_formats(
- source_url, clip_id, 'mp4', 'm3u8_native',
- m3u8_id=protocol, fatal=False))
- else:
- formats.append({
- 'url': source_url,
- 'format_id': protocol,
- })
- return {
- 'id': clip_id,
- 'title': content.get('title'),
- 'duration': float_or_none(content.get('duration')),
- 'series': content.get('tvShowTitle'),
- 'formats': formats,
- }
- def _real_extract(self, url):
- video_id = self._match_id(url)
- webpage = self._download_webpage(url, video_id)
- json_data = self._parse_json(
- self._search_regex(r'<script id="state" type="text/plain">(.*)</script>', webpage, 'json_data'),
- video_id=video_id)
- video_title = json_data['views']['default']['page']['title']
- content_resource = json_data['views']['default']['page']['contentResource']
- content_id = content_resource[0]['id']
- content_ids = [{'id': id_, 'subclip_start': content['start'], 'subclip_end': content['end']}
- for id_, content in enumerate(content_resource)]
- time_of_request = dt.datetime.now()
- not_before = time_of_request - dt.timedelta(minutes=5)
- expire = time_of_request + dt.timedelta(minutes=5)
- payload = {
- 'content_ids': {
- content_id: content_ids,
- },
- 'secure_delivery': True,
- 'iat': int(time_of_request.timestamp()),
- 'nbf': int(not_before.timestamp()),
- 'exp': int(expire.timestamp()),
- }
- jwt_token = jwt_encode_hs256(payload, self._ENCRYPTION_KEY, headers={'kid': self._ACCESS_ID})
- videos = self._download_json(
- 'https://vas-v4.p7s1video.net/4.0/getsources',
- content_id, 'Downloading videos JSON', query={
- 'token': jwt_token.decode('utf-8'),
- })
- video_id, videos_data = next(iter(videos['data'].items()))
- error_msg = try_get(videos_data, lambda x: x['error']['title'])
- if error_msg == 'Geo check failed':
- self.raise_geo_restricted(error_msg)
- elif error_msg:
- raise ExtractorError(error_msg)
- entries = [
- self._extract_video_info(url, content_resource[video['id']], video)
- for video in videos_data]
- return {
- '_type': 'multi_video',
- 'id': video_id,
- 'title': video_title,
- 'entries': entries,
- }
|