From 4a733545867a014eb786348f8fb9e6ae95850742 Mon Sep 17 00:00:00 2001 From: Alex Seiler Date: Sun, 5 Nov 2017 18:07:35 +0100 Subject: [PATCH] [zattoo] Add extractor (closes #14668) --- youtube_dl/extractor/extractors.py | 6 + youtube_dl/extractor/zattoo.py | 234 +++++++++++++++++++++++++++++ 2 files changed, 240 insertions(+) create mode 100644 youtube_dl/extractor/zattoo.py diff --git a/youtube_dl/extractor/extractors.py b/youtube_dl/extractor/extractors.py index 6fb65e4fe..9fe3f649d 100644 --- a/youtube_dl/extractor/extractors.py +++ b/youtube_dl/extractor/extractors.py @@ -1418,5 +1418,11 @@ ) from .zapiks import ZapiksIE from .zaq1 import Zaq1IE +from .zattoo import ( + QuicklineIE, + QuicklineLiveIE, + ZattooIE, + ZattooLiveIE, +) from .zdf import ZDFIE, ZDFChannelIE from .zingmp3 import ZingMp3IE diff --git a/youtube_dl/extractor/zattoo.py b/youtube_dl/extractor/zattoo.py new file mode 100644 index 000000000..928f22566 --- /dev/null +++ b/youtube_dl/extractor/zattoo.py @@ -0,0 +1,234 @@ +# coding: utf-8 +from __future__ import unicode_literals + +from uuid import uuid4 +import re + +from .common import InfoExtractor +from ..utils import ( + compat_str, + ExtractorError, + sanitized_Request, + urlencode_postdata, +) + + +class ZattooBaseIE(InfoExtractor): + + _NETRC_MACHINE = 'zattoo' + _HOST_URL = 'https://zattoo.com' + + _power_guide_hash = None + + def _login(self, uuid, session_id): + (username, password) = self._get_login_info() + if not username or not password: + raise ExtractorError( + 'A valid %s account is needed to access this media.' % self._NETRC_MACHINE, + expected=True) + login_form = { + 'login': username, + 'password': password, + 'remember': True, + } + request = sanitized_Request( + '%s/zapi/v2/account/login' % self._HOST_URL, + urlencode_postdata(login_form)) + request.add_header( + 'Referer', '%s/login' % self._HOST_URL) + request.add_header( + 'Content-Type', 'application/x-www-form-urlencoded; charset=UTF-8') + request.add_header( + 'Cookie', 'uuid=%s; beaker.session.id=%s' % (uuid, session_id)) + response = self._request_webpage( + request, None, 'Logging in') + data = self._parse_json(response.read(), None) + return data['session']['power_guide_hash'] + + def _get_app_token_and_version(self): + host_webpage = self._download_webpage( + self._HOST_URL, None, 'Downloading %s' % self._HOST_URL) + app_token = self._html_search_regex( + r'[^/]+)/(?P[0-9]+)' + + def _real_extract(self, url): + channel_name, video_id = re.match(self._VALID_URL, url).groups() + return self._extract_video(channel_name, video_id) + + +class QuicklineLiveIE(QuicklineBaseIE): + _VALID_URL = r'https?://(?:www\.)?mobiltv\.quickline\.com/watch/(?P[^/]+)$' + + def _real_extract(self, url): + channel_name = video_id = self._match_id(url) + return self._extract_video(channel_name, video_id, is_live=True) + + +class ZattooIE(ZattooBaseIE): + _VALID_URL = r'https?://(?:www\.)?zattoo\.com/watch/(?P[^/]+?)/(?P[0-9]+)[^/]+(?:/(?P[0-9]+))?' + + # Since regular videos are only available for 7 days and recorded videos + # are only available for a specific user, we cannot have detailed tests. + _TESTS = [{ + 'url': 'https://zattoo.com/watch/prosieben/130671867-maze-runner-die-auserwaehlten-in-der-brandwueste', + 'only_matching': True, + }, { + 'url': 'https://zattoo.com/watch/srf_zwei/132905652-eishockey-spengler-cup/102791477/1512211800000/1514433500000/92000', + 'only_matching': True, + }] + + def _real_extract(self, url): + channel_name, video_id, record_id = re.match(self._VALID_URL, url).groups() + return self._extract_video(channel_name, video_id, record_id) + + +class ZattooLiveIE(ZattooBaseIE): + _VALID_URL = r'https?://(?:www\.)?zattoo\.com/watch/(?P[^/]+)$' + + _TEST = { + 'url': 'https://zattoo.com/watch/srf1', + 'only_matching': True, + } + + def _real_extract(self, url): + channel_name = video_id = self._match_id(url) + return self._extract_video(channel_name, video_id, is_live=True)