X-Git-Url: https://git.rapsys.eu/youtubedl/blobdiff_plain/9ed7fe4fe4c445eb7d9f3197bb300d0db8f1807a..712213a489c35dbaf5120268f1a309dc457cea29:/youtube_dl/extractor/tubitv.py?ds=sidebyside diff --git a/youtube_dl/extractor/tubitv.py b/youtube_dl/extractor/tubitv.py index 6d78b5d..a51fa65 100644 --- a/youtube_dl/extractor/tubitv.py +++ b/youtube_dl/extractor/tubitv.py @@ -1,39 +1,42 @@ # coding: utf-8 from __future__ import unicode_literals -import codecs import re from .common import InfoExtractor -from ..compat import compat_urllib_parse from ..utils import ( ExtractorError, int_or_none, sanitized_Request, + urlencode_postdata, ) class TubiTvIE(InfoExtractor): - _VALID_URL = r'https?://(?:www\.)?tubitv\.com/video\?id=(?P[0-9]+)' + _VALID_URL = r'https?://(?:www\.)?tubitv\.com/(?:video|movies|tv-shows)/(?P[0-9]+)' _LOGIN_URL = 'http://tubitv.com/login' _NETRC_MACHINE = 'tubitv' - _TEST = { - 'url': 'http://tubitv.com/video?id=54411&title=The_Kitchen_Musical_-_EP01', + _GEO_COUNTRIES = ['US'] + _TESTS = [{ + 'url': 'http://tubitv.com/video/283829/the_comedian_at_the_friday', + 'md5': '43ac06be9326f41912dc64ccf7a80320', 'info_dict': { - 'id': '54411', + 'id': '283829', 'ext': 'mp4', - 'title': 'The Kitchen Musical - EP01', - 'thumbnail': 're:^https?://.*\.png$', - 'description': 'md5:37532716166069b353e8866e71fefae7', - 'duration': 2407, + 'title': 'The Comedian at The Friday', + 'description': 'A stand up comedian is forced to look at the decisions in his life while on a one week trip to the west coast.', + 'uploader_id': 'bc168bee0d18dd1cb3b86c68706ab434', }, - 'params': { - 'skip_download': 'HLS download', - }, - } + }, { + 'url': 'http://tubitv.com/tv-shows/321886/s01_e01_on_nom_stories', + 'only_matching': True, + }, { + 'url': 'http://tubitv.com/movies/383676/tracker', + 'only_matching': True, + }] def _login(self): - (username, password) = self._get_login_info() + username, password = self._get_login_info() if username is None: return self.report_login() @@ -41,7 +44,7 @@ class TubiTvIE(InfoExtractor): 'username': username, 'password': password, } - payload = compat_urllib_parse.urlencode(form_data).encode('utf-8') + payload = urlencode_postdata(form_data) request = sanitized_Request(self._LOGIN_URL, payload) request.add_header('Content-Type', 'application/x-www-form-urlencoded') login_page = self._download_webpage( @@ -55,26 +58,39 @@ class TubiTvIE(InfoExtractor): def _real_extract(self, url): video_id = self._match_id(url) + video_data = self._download_json( + 'http://tubitv.com/oz/videos/%s/content' % video_id, video_id) + title = video_data['title'] - webpage = self._download_webpage(url, video_id) - if re.search(r"<(?:DIV|div) class='login-required-screen'>", webpage): - self.raise_login_required('This video requires login') + formats = self._extract_m3u8_formats( + self._proto_relative_url(video_data['url']), + video_id, 'mp4', 'm3u8_native') + self._sort_formats(formats) - title = self._og_search_title(webpage) - description = self._og_search_description(webpage) - thumbnail = self._og_search_thumbnail(webpage) - duration = int_or_none(self._html_search_meta( - 'video:duration', webpage, 'duration')) + thumbnails = [] + for thumbnail_url in video_data.get('thumbnails', []): + if not thumbnail_url: + continue + thumbnails.append({ + 'url': self._proto_relative_url(thumbnail_url), + }) - apu = self._search_regex(r"apu='([^']+)'", webpage, 'apu') - m3u8_url = codecs.decode(apu, 'rot_13')[::-1] - formats = self._extract_m3u8_formats(m3u8_url, video_id, ext='mp4') + subtitles = {} + for sub in video_data.get('subtitles', []): + sub_url = sub.get('url') + if not sub_url: + continue + subtitles.setdefault(sub.get('lang', 'English'), []).append({ + 'url': self._proto_relative_url(sub_url), + }) return { 'id': video_id, 'title': title, 'formats': formats, - 'thumbnail': thumbnail, - 'description': description, - 'duration': duration, + 'subtitles': subtitles, + 'thumbnails': thumbnails, + 'description': video_data.get('description'), + 'duration': int_or_none(video_data.get('duration')), + 'uploader_id': video_data.get('publisher_id'), }